Sie sind hier

## Accepted manuscript for publication in the IEEE Signal Processing Letters: 'Joint Source-Channel Coding for Semantics-Aware Grant-Free Radio Access in IoT Fog Networks'

Mittwoch, 03. März 2021

We are glad to announce that the manuscript 'Joint Source-Channel Coding for Semantics-Aware Grant-Free Radio Access in IoT Fog Networks' has been accepted for publication in the IEEE Signal Processing Letters.

Authors: Johannes Dommel, Zoran Utkovski, Osvaldo Simeone and Slawomir Stanczak

Title: Joint Source-Channel Coding for Semantics-Aware Grant-Free Radio Access in IoT Fog Networks

Abstract: A fog-radio access network (F-RAN) architecture is studied for an Internet-of-Things (IoT) system in which wireless sensors monitor a number of multi-valued events and transmit in the uplink using grant-free random access to multiple edge nodes (ENs). Each EN is connected to a central processor (CP) via a finite-capacity fronthaul link. In contrast to conventional information-agnostic protocols based on separate source-channel (SSC) coding, where each device uses a separate codebook, this paper considers an information-centric approach based on joint source-channel (JSC) coding via a non-orthogonal generalization of type-based multiple access (TBMA). By leveraging the semantics of the observed signals, all sensors measuring the same event share the same codebook (with non-orthogonal codewords), and all such sensors making the same local estimate of the event transmit the same codeword. The F-RAN architecture directly detects the events values without first performing individual decoding for each device. Cloud and edge detection schemes based on Bayesian message passing are designed and trade-offs between cloud and edge processing are assessed.

## New joint project TRURL between TU Berlin NetIT, NCO Torun, TITECH and Keio University starting in June 2021

Montag, 01. März 2021

Distributed learning has been identified as a crucial enabler for future AI tools in heterogeneous environments. However, current work on distributed AI is based on standard optimization tools that, for example, consider the research on distributed algorithms as a separate topic from wireless communication. As a consequence, the resulting systems scale unfavorably with the number of communication partners involved and have major deficits in terms of security, privacy and robustness against partial failures in the wireless network.

Therefore we initiated a new joint project entitled "TRUstworthy distRibuted Learning" (TRURL) in cooperation with the Nicolaus Copernicus University (NCO) in Toruń, the Keio University and the Tokyo Institute of Technology (TITECH), which will start in June 2021.

The main objective of this project is to devise AI algorithms that:

(1) are truly nonhierarchical (no single point of failure) and asynchronous;

(2) provide confidence intervals for the estimates;

(3) detect attacks and eavesdroppers in the network;

(4) are privacy preserving;

(5) solve real-world problems (and, in particular, problems related to environmental modelling and network cyber security); and

(6) use practical communication protocols tailored to the optimization methods being proposed.

The research work will be divided among the partners as follows: TU Berlin will develop methods of Over-the-Air computation and Federated Learning schemes making use of them as well as defenses against eavesdroppers. NCO Torun will investigate how privacy can be preserved when carrying out these schemes. TITECH will focus on defenses agains active attacks with a focus on DDoS (Distributed Denial of Service). Keio University will work on robustness against partial communication failures and reliability of the proposed schemes.

Concert Japan EU (TRURL): http://www.concert-japan.eu/

## New project "Computation for Communication: Bridging the Digital and Analog Worlds" between TU Berlin and University of Melbourne

Montag, 01. März 2021

Within the project "Computation for Communication: Bridging the Digital and Analog Worlds", researchers from Technische Universität Berlin (TUB) and University of Melbourne (UoM) will work on a fundamental problem that comes with the increasing ubiquity of wireless communications: While the available bandwidth remains limited, the number of devices that share it is ever increasing.

The TUB researchers have focused mostly on analog approaches to make communication in massively-sized wireless networks hugely more efficient by tailoring the communication schemes to the applications they are used for, while the UoM researchers have approached the problem with digitally coded communication schemes. The support of the BUA-UoM Seed Fund means that the two groups have an opportunity to combine their complimentary expertise to jointly develop unifying approaches that can combine the advantages of the digital and analog worlds as well as foster a longer-term academic cooperation.

## Upcoming talk with Prof. Dr.-Ing. Slawomir Stanczak at NVIDIA GTC'21: Key challenges and technology drivers for open 5G/6G networks // April 12-16, 2021

Sonntag, 28. Februar 2021

We are glad to announce that Prof. Dr.-Ing. Slawomir Stanczak will give a talk at the NVIDIA GTC 2021 (April 12 -16).

Title: Key challenges and technology drivers for open 5G/6G networks

NVIDIA GTC 2021 will take place online April 12 -16. Registration will be free. We encourage you to invite your colleagues to register and attend.

## Invited talk of Prof. Dr.-Ing. Slawomir Stanczak at 5G Masters: OpenRAN, technische Evolution oder Revolution? // February 26, 2021

Mittwoch, 24. Februar 2021

Prof. Dr.-Ing. Slawomir Stanczak has been invited to give a talk on the topic "OpenRAN, technische Evolution oder Revolution?". The event took place on the 26th February 2021 and was supported by Huawei and GvW Graf von Westphalen.

Visit the event website for more details: https://5gmasters.de/#partner

## Accepted paper for presentation at IEEE VTC2021-Spring: 'AI4Mobile: Use Cases and Challenges of AI-based QoS Prediction for High-Mobility Scenarios'

Mittwoch, 03. Februar 2021

The paper 'AI4Mobile: Use Cases and Challenges of AI-based QoS Prediction for High-Mobility Scenarios' has been accepted for presentation and publication at the IEEE 93rd Vehicular Technology Conference (VTC2021-Spring). The conference will be held virtually from 25-28 April 2021.

Authors: Daniel Fabian Külzer, Martin Kasparick, Alexandros Palaios, Raja Sattiraju, Oscar Dario Ramos-Cantor, Dennis Wieruch, Hugues Tchouankem, Fabian Göttsch, Philipp Geuer, Jens Schwardmann, Gerhard Fettweis, Hans Dieter Schotten and Slawomir Stanczak

Title: AI4Mobile: Use Cases and Challenges of AI-based QoS Prediction for High-Mobility Scenarios

Abstract: The integration of functions into future communication systems that predict crucial Quality of Service (QoS) parameters is expected to enable many new or enhanced use cases, for example, in vehicular networks and Industry 4.0. Especially with high user mobility, QoS prediction is required in an End-to-End (E2E) fashion to guarantee uninterrupted connectivity and provisioning of real-time applications. In this paper, we present a concise list of mobility use cases, both from automotive and industrial production domains, that benefit from Artificial Intelligence-based QoS prediction. These applications are investigated in the publicly-funded research project AI4Mobile by a representative consortium of industry and academia. Based on a literature review, we identify the main challenges in realizing predictive QoS at
high mobility, and we propose research directions to enable the envisioned E2E solutions.

Conference: IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), in Helsinki, Finland, 25-28 April 2021 (virtual conference)

## Accepted paper for presentation at IEEE VTC2021-Spring: 'Terminal-Side Data Rate Prediction For High-Mobility Users'

Montag, 01. Februar 2021

The paper 'Terminal-Side Data Rate Prediction For High-Mobility Users' has been accepted for presentation and publication at the IEEE 93rd Vehicular Technology Conference (VTC2021-Spring). The conference will be held virtually in April 2021.

Authors: Daniel Schäufele, Martin Kasparick, Jens Schwardmann, Johannes Morgenroth, and Slawomir Stanczak

Title: Terminal-Side Data Rate Prediction For High-Mobility Users

Conference: IEEE 93rd Vehicular Technology Conference (VTC2021-Spring), Helsinki, Finland, April 2021 (virtual conference)

## Accepted paper for presentation at IEEE ICC 2021: 'On Latency Prediction with Deep Learning and Passive Probing at High Mobility'

Dienstag, 26. Januar 2021

We are glad to announce that the paper entitled 'On Latency Prediction with Deep Learning and Passive Probing at High Mobility' has been accepted for presentation and publication at the IEEE International Conference on Communications (ICC) 2021.This will be a virtual conference which will take place in June 14-23, 2021.

Authors: Daniel Fabian Külzer, Firas Debbichi, Slawomir Stanczak, Mladen Botsov

Title: On Latency Prediction with Deep Learning and Passive Probing at High Mobility

Abstract: In autonomous driving, several applications like teleoperated driving, back-end status verification, or online gaming for customer infotainment rely on low-latency communication. Ideally, we can select a route that best supports the applications' requirements before the journey. Therefore, route selection for autonomous vehicles might require in-advance latency predictions. End-to-end (E2E) latency prediction is a difficult task, especially when considering that it needs to be achieved with limited active probing due to cost constraints. We study continuous latency prediction and application feasibility assessment (in terms of meeting the applications' E2E latency requirements), using a custom-designed deep learning model that leverages feature engineering for prediction error reduction. We provide insights into the model behavior utilizing recent advances in explainable artificial intelligence. Moreover, we present a novel model-agnostic approach based on active learning to leverage passive probing data. A pre-trained model performs certainty sampling, predicts artificial labels to enlarge the training dataset, and trains iteratively on the augmented set. The results show a 5 % reduction in mean average error for continuous latency prediction and an increase of up to 2.8 % in macro F1 score due to the use of passive probing data.

Conference: IEEE International Conference on Communications, 14-23 June 2021 //Montreal, Canada (virtual conference)

Website: https://icc2021.ieee-icc.org/

## Accepted paper for publication in IEEE Communications Letters: 'Online Learning of Any-to-Any Path Loss Maps'

Montag, 04. Januar 2021

We are glad to announce that the paper entitled 'Online Learning of Any-to-Any Path Loss Maps' has been accepted for publication in the IEEE Communications Letters.

Authors: Miguel Angel Gutierrez-Estevez, Martin Kasparick, and Slawomir Stanczak

Title: Online Learning of Any-to-Any Path Loss Maps

Abstract: Learning any-to-any (A2A) path loss maps might be a key enabler for many applications that rely on a device-todevice (D2D) communication, such as vehicle-to-vehicle (V2V) communications. Current approaches for learning A2A maps have a number of important limitations, including i) a high complexity that increases rapidly with the number of samples, making the problems quickly intractable, and ii) the inability of coping with a time-varying environment, among others. In this paper, we propose a novel approach that reconstruct A2A path loss maps in an online fashion. To that end, we leverage on the framework of stochastic learning to deal with the sequential arrival of samples, and propose an online algorithm based on the forward-backward splitting method. Preliminary simulation results show a signiﬁcant decrease in complexity, while its performance is comparable to that of a batch approach.

## Accepted paper for IEEE Transactions on Control of Network Systems: 'Max-Consensus Over Fading Wireless Channels'

Donnerstag, 17. Dezember 2020

We are glad to announce that the paper entitled 'Max-Consensus Over Fading Wireless Channels' has been accepted for publication in the IEEE Transactions on Control of Network Systems.

Authors: Fabio Molinari, Navneet Agrawal, Slawomir Stanczak and Jörg Raisch

Title: Max-Consensus Over Fading Wireless Channels

Abstract: The topic of this paper is achieving ﬁnite-time maxconsensus in a multi-agent system that communicates over a fading wireless channel and exploits its interference property. This phenomenon corrupts the desired information when data is transmitted synchronously. In fact, each transmitted signal is attenuated by an unknown and time-varying factor (fading coefﬁcient), then, by interference, all such attenuated signals are summed up at a receiver. Rather than combatting interference, we design a communication system that exploits it. Our strategy yields a more efﬁcient usage of wireless resources compared to other algorithms. By simultaneously accessing this communication system, each agent obtains a weighted average of the neighbouring agents’ information states. With this piece of information at hand and with a switching consensus protocol employing broadcast authorisations for agents, max-consensus can be achieved within a ﬁnite number of iterations.

## Upcoming Bitkom Webmeeting with Prof. Dr.-Ing. Slawomir Stanczak: Wie steht es um Open RAN? Und was ist das eigentlich? // December 15, 2020

Montag, 07. Dezember 2020

We are glad to announce that Prof. Dr.-Ing. Slawomir Stanczak has been invited to share his expertise in a talk and in a discussion on Open RAN. This event will take place on the 15th December 2020 as a webmeeting and is organized by Bitkom.

Visit the event website of bitkom for more details: https://www.bitkom.org/Termine/index.jsp

## Invitation to the IEEE WCNC'2021 Panel - Trends and Technologies for 5G Evolution // March 29-April 1, 2021

Mittwoch, 11. November 2020

We are glad to announce that Prof. Dr.-Ing. Slawomir Stanczak confirmed to be one of the panelists of the panel "Trends and Technologies for 5G Evolution" at the IEEE WCNC'2021 conference.

The IEEE Wireless Communications and Networking Conference (WCNC), is an IEEE premier annual event in the wireless research arena, bringing together researchers, academics, and industry professionals. The conference will take place from March 29 - April 1, 2021 in Nanjing, China!

Visit the IEEE WCNC'2021 conference website and the program for more details.

## Prof. Dr.-Ing. Slawomir Stanczak will serve as Technical Program Committee (TPC) Vice-Chair at the IEEE PIMRC 2021

Montag, 09. November 2020

Prof. Dr.-Ing. Slawomir Stanczak has been invited to serve as Technical Program Committee (TPC) Vice-Chair for IEEE PIMRC 2021(IEEE International Symposium on Personal, Indoor and Mobile Radio Communications 2021) which he gladly accepted. The conference will take place next year in Helsinki, Finland from 13 -16 September 2021.

PIMRC has attracted major figures in the cellular, PCS, wireless LAN, and mobile data industries. Conference topics are presented in keynotes, tutorials, technical, and panel sessions.

Visit the IEEE PIMRC 2021 website for more details!

## Prof. Dr.-Ing. Slawomir Stanczak will serve on the technical program committe for IEEE ICC'21 - SAC-05 MLC Track

Sonntag, 20. September 2020

We are glad to announce that Prof. Dr.-Ing. Slawomir Stanczak has been invited to serve on the technical program committee for IEEE ICC'21 - SAC-05 MLC Track (2021 IEEE International Conference on Communications (ICC): SAC Machine Learning for Communications Track).

The IEEE International Conference on Communications will take place from 14-18 June 2021 in Montreal, Canada. More information regarding the conference and program can be found on the conference website.

## Invited panel: "5G developments, 5G platform and toolbox, standard iREF and interoperability through Open-RAN" with Prof. Dr.-Ing. Slawomir Stanczak // Tag der Digitalen Technologien 2020

Mittwoch, 02. September 2020

We are very pleased to announce that Prof. Stanczak has again been invited to participate in this year's Digital Technology Day 2020. Prof. Stanczak will especially participate as an expert in the highly professional panel on "5G developments, 5G platform and toolbox, standard iREF and interoperability through Open-RAN".

This year's Digital Technologies Day will take place on November 17, 2020 from 09:30 to 16:00 as an interactive online conference with live streaming from KOSMOS, Berlin (www.kosmos-berlin.de).

Companies and research institutions from projects in the application-oriented technology programs of the BMWi will present their results in 10 expert forums and discuss current topics of digital technologies, from digital sovereignty to digital business models.

More details on this event can be found on the official website.

## Industry convened Panel: The Outlook of Wireless Research Beyond 5G in Europe with Prof. Dr.-Ing. Slawomir Stanczak - 03rd Sep. 2020 // IEEE PIMRC (Virtual Conference)

Donnerstag, 27. August 2020

We are very pleased to announce that Prof. Dr.-Ing. Slawomir Stanczak has been invited to share his expertise in the panel discussion which is part of the 2020 Annual IEEE International Symposium on Personal, Indoor and Mobile Radio Communications (IEEE PIMRC 2020). The panel is convened by Huawei and will discuss the outlook of wireless research beyond 5G in Europe. The IEEE PIMRC 2020 will take place this year virtually from 31 August - 03 September 2020.

Date & Time: September 03, 2020 from 14.00-15.30 CEST

Title: Industry convened Panel: The Outlook of Wireless Research Beyond 5G in Europe

Abstract: Now that the deployment of the 5th Generation of mobile networks (5G) has successfully started all over the world, the obligatory “what is next?” question has appeared in the research community. From 3rd generation era, Europe has been kept playing the pioneer role in defining “What is next?” for each new generation. With the spirit of open research and innovation, quite a lot successful joint research and exploration activities between industry and academy have been supported by European Union. And now, as Commissioner Thierry Breton proposed, “without even waiting for the end of 5G roll-out, I want us to start working on 6G”. It is time to start think about how we could go together with join effort to create another technological miracle in next decade.

6G will be an achievement of globally joint effort from all beneficial partners on the ICT value chain. How the industry and academy from Europe can create the joint momentum and riding on the peak of the tide is question to be explored. The panel will investigate, with this joint momentum, how we can find out the new requirements, the new business models, the new technology trend, and maybe even more important, the new mode of joint exploration and innovation.

Panel Organizer: Petar Popovski, Professor of Wireless Communications, Aalborg University

Panel Members: Nancy Alonistioti (Associate Professor, National and Kapodistrian University of Athens, Greece), Luke Ibbetson (Group R&D Director, Vodafone, UK), Slawomir Stanczak (Professor, Fraunhofer HHI & TU Berlin, Germany), Alexander Werlberger (Chief Technology Officer, Holo-light, Germany)

Conference program: https://pimrc2020.ieee-pimrc.org/program/

## Accepted paper for IEEE Globecom 2020: 'Predictive Resource Allocation for Automotive Applications using Interference Calculus'

Montag, 17. August 2020

We are glad to announce that the paper entitled 'Predictive Resource Allocation for Automotive Applications using Interference Calculus' has been accepted for presentation at IEEE Globecom 2020. The paper has been also accepted for publication in its proceedings.

Title: Predictive Resource Allocation for Automotive Applications using Interference Calculus

Authors: Daniel Fabian Külzer, Slawomir Stanczak, Renato L.G. Cavalcante and Mladen Botsov

Abstract: In autonomous driving, several safety-related connected applications will co-exist with infotainment services for passenger entertainment. Serving the resulting set of diverse quality of service (QoS) requirements poses a tremendous challenge for future cellular networks. For example, safety-related applications require low latency, while infotainment services are associated with high throughput demands. To address the co-existence challenge, we propose a multi-cell anticipatory networking framework with interference coordination based on channel distribution information. The iterative approach first optimizes packet transmission times by so-called statistical look-ahead scheduling leveraging service properties. Interference calculus is applied for estimating the network's load in each step. Finally, packets are forwarded to an online scheduler based on the found transmission schedule. Simulations show that inter-cell interference management is crucial in provisioning the desired QoS. The iterative optimization framework offers superior transmission reliability and spectral efficiency.

The 2020 IEEE Global Communications Conference (GLOBECOM) will be held in the lively and picturesque city of Taipei, Taiwan, from 7 to 11 December 2020.

Themed “Communications for Human and Machine Intelligence,” this flagship conference of the IEEE Communications Society will feature a comprehensive high-quality technical program including 13 symposia and a variety of tutorials and workshops. IEEE GLOBECOM 2020 will also include an attractive industry program aimed at practitioners, with keynotes and panels from prominent research, industry and government leaders, business and industry panels, and technological exhibits.

Conference Website: https://globecom2020.ieee-globecom.org/

## Accepted paper for IEEE Globecom 2020: 'Mobility Modes for Pulse-Shaped OTFS with Linear Equalizer'

Montag, 17. August 2020

We are glad to announce that the paper entitled 'Mobility Modes for Pulse-Shaped OTFS with Linear Equalizer' has been accepted for presentation at IEEE Globecom 2020. The paper has been also accepted for publication in its proceedings.

Title: Mobility Modes for Pulse-Shaped OTFS with Linear Equalizer

Authors: Andreas Pfadler, Peter Jung and Slawomir Stanczak

Abstract: Orthogonal time frequency and space (OTFS) modulation is a pulse-shaped Gabor signaling scheme with additional time-frequency (TF) spreading using the symplectic finite Fourier transform (SFFT). With sufficient accurate channel information and sophisticated equalizers it promises performance gains in terms of robustness for high mobility users. To fully exploit diversity in OTFS, the 2D-deconvolution implemented by a linear equalizer should approximately invert the doubly dispersive channel operation, which however is a twisted convolution. In theory, this is achieved in a first step by matching the TF grid and the Gabor synthesis and analysis pulses to the delay and Doppler spread of the channel. However, in practice, one always has to balance between supporting high granularity in delay-Doppler (DD) spread, and multi-user and network aspects. In this paper, we propose mobility modes with distinct grid and pulse matching for different doubly dispersive channel. To account for remaining self-interference, we tune the minimum mean square error (MMSE) linear equalizer without the need of estimating channel cross talk coefficients. We evaluate our approach with the QuaDRiGa channel simulator and with OTFS transceiver architecture based on a polyphase implementation for orthogonalized Gaussian pulses. In addition, we compare OTFS to a IEEE 802.11p compliant design of cyclic prefix (CP) based orthogonal frequency-division multiplexing (OFDM). Our results indicate that with an appropriate mobility mode, the potential OTFS gains can be indeed achieved with linear equalizers to significantly outperforms OFDM.

The 2020 IEEE Global Communications Conference (GLOBECOM) will be held in the lively and picturesque city of Taipei, Taiwan, from 7 to 11 December 2020.

Themed “Communications for Human and Machine Intelligence,” this flagship conference of the IEEE Communications Society will feature a comprehensive high-quality technical program including 13 symposia and a variety of tutorials and workshops. IEEE GLOBECOM 2020 will also include an attractive industry program aimed at practitioners, with keynotes and panels from prominent research, industry and government leaders, business and industry panels, and technological exhibits.

Conference Website: https://globecom2020.ieee-globecom.org/

## The paper 'Full-Duplex AF MIMO Relaying: Impairments Aware Design and Performance Analysis' has been accepted for IEEE Globecom 2020

Montag, 17. August 2020

We are glad to announce that the paper entitled 'Full-Duplex AF MIMO Relaying: Impairments Aware Design and Performance Analysis' has been accepted for presentation at IEEE Globecom 2020. The paper has been also accepted for publication in its proceedings.

Title: Full-Duplex AF MIMO Relaying: Impairments Aware Design and Performance Analysis

Authors: Omid Taghizadeh, Slawomir Stanczak, Hiroki Iimori and Giuseppe Thadeu Freitas de Abreu

Abstract: Full-Duplex (FD) Amplify-and-Forward (AF) Multiple-Input Multiple-Output (MIMO) relaying has been the focus of several recent studies, due to the potential for achieving a higher spectral efficiency and lower latency, together with the inherent processing simplicity. However, when the impact of hardware distortions are considered, such relays suffer from a distortion-amplification loop, due to the inter-dependent nature of the relay transmit signal covariance and the residual self-interference covariance. The aforementioned behavior leads to a significant performance degradation for a system with a low or medium hardware accuracy. In this work, we analyse the relay transfer function as well as the Mean Squared-Error (MSE) performance of an FD-AF MIMO relay-assisted communication, under collective sources of additive and multiplicative transmit and receive impairments. An optimization problem is then devised over the linear transmit and receive strategies to minimize the communication MSE and solved by employing the recently proposed Penalty Dual Decomposition (PDD) method. The proposed solution converges to a stationary point of the original problem via a sequence of quadratic convex programs. Numerical simulations verify the significance of the proposed distortion-aware design compared to the common simplified approaches, as the hardware accuracy degrades.

The 2020 IEEE Global Communications Conference (GLOBECOM) will be held in the lively and picturesque city of Taipei, Taiwan, from 7 to 11 December 2020.

Themed “Communications for Human and Machine Intelligence,” this flagship conference of the IEEE Communications Society will feature a comprehensive high-quality technical program including 13 symposia and a variety of tutorials and workshops. IEEE GLOBECOM 2020 will also include an attractive industry program aimed at practitioners, with keynotes and panels from prominent research, industry and government leaders, business and industry panels, and technological exhibits.

Conference Website: https://globecom2020.ieee-globecom.org/

## Accepted paper for IEEE Globecom 2020: 'Hybrid data and model driven algorithms for angular power spectrum estimation'

Montag, 17. August 2020

We are glad to announce that the paper entitled 'Hybrid data and model driven algorithms for angular power spectrum estimation' has been accepted for presentation at IEEE Globecom 2020. The paper has been also accepted for publication in its proceedings.

Title: Hybrid data and model driven algorithms for angular power spectrum estimation

Authors: Renato L.G. Cavalcante and Slawomir Stanczak

Abstract: We propose two algorithms that use both models and datasets to estimate angular power spectra from channel covariance matrices in massive MIMO systems. The first algorithm is an iterative fixed-point method that solves a hierarchical problem. It uses model knowledge to narrow down candidate angular power spectra to a set that is consistent with a measured covariance matrix. Then, from this set, the algorithm selects the angular power spectrum with minimum distance to its expected value with respect to a Hilbertian metric learned from data. The second algorithm solves an alternative optimization problem with a single application of a solver for nonnegative least squares programs. By fusing information obtained from datasets and models, both algorithms can outperform existing approaches based on models, and they are also robust against environmental changes and small datasets.

ArXiv: arXiv:2005.14003

The 2020 IEEE Global Communications Conference (GLOBECOM) will be held in the lively and picturesque city of Taipei, Taiwan, from 7 to 11 December 2020.

Themed “Communications for Human and Machine Intelligence,” this flagship conference of the IEEE Communications Society will feature a comprehensive high-quality technical program including 13 symposia and a variety of tutorials and workshops. IEEE GLOBECOM 2020 will also include an attractive industry program aimed at practitioners, with keynotes and panels from prominent research, industry and government leaders, business and industry panels, and technological exhibits.

Conference Website: https://globecom2020.ieee-globecom.org/

## The paper 'Deploying Two-Tiered Wireless Sensor/Actuator Networks Supporting In-Network Computation' has been presented at IEEE INDIN 2020

Montag, 10. August 2020

We are glad to announce that the paper entitled 'Deploying Two-Tiered Wireless Sensor/Actuator Networks Supporting In-Network Computation' has been presented at the 18th IEEE International Conference on Industrial Informatics (INDIN), Warwick, UK, 2020.

Title: Deploying Two-Tiered Wireless Sensor/Actuator Networks Supporting In-Network Computation

Authors: Chaofan Ma, Meng Zheng, Wei Liang, Martin Kasparick, and Yufeng Lin

IEEE INDIN is the premier conference series presenting the state of the art and future perspectives of industrial information technologies, where industry experts, researchers, and academics share ideas and report on recent developments, deployments, technology trends and research results, as well as initiatives related to industrial informatics and their application.

## The paper 'An Open Software-Defined-Radio Platform for LTE-V2X And Beyond' has been accepted for presentation at IEEE VTC2020-Fall

Freitag, 03. Juli 2020

We are glad to announce that the paper entitled 'An Open Software-Defined-Radio Platform for LTE-V2X And Beyond' has been accepted for presentation and publication at the IEEE VTC2020-Fall.

Title: An Open Software-Defined-Radio Platform for LTE-V2X And Beyond

Authors: Ralf Lindstedt, Martin Kasparick, Jens Pilz and Stephan Jaeckel

The 2020 IEEE 92nd Vehicular Technology Conference: VTC2020-Fall will be held 4 – 7 October in Victoria, BC Canada. This semi-annual flagship conference of IEEE Vehicular Technology Society will bring together individuals from academia, government, and industry to discuss and exchange ideas in the fields of wireless, mobile, and vehicular technology.

IEEE VTC2020-Fall will feature world-class plenary speakers, tutorials, technical as well as application sessions, and an innovative Industry Track, which will feature panels and presentations with industry leaders sharing their perspectives on the latest technologies.

## The paper 'A Study on Feature Processing Schemes for Deep-Learning-Based Human Activity Classification Using Frequency-Modulated Continuous-Wave Radar' has been accepted by IET Radar, Sonar & Navigation

Donnerstag, 02. Juli 2020

We are pleased to announce that our PhD Student Mr. Rodrigo Hernangómez has been submitted his paper entitled 'A Study on Feature Processing Schemes for Deep-Learning-Based Human Activity Classification Using Frequency-Modulated Continuous-Wave Radar' for publication to the IET Radar, Sonar & Navigation Journal.

The paper has been accepted and is published in the IET Radar, Sonar & Navigation, Volume 14, Issue 7, July 2020. This is a special issue which contains selected papers from the 2019 International Radar Conference (Toulon).

Title: A Study on Feature Processing Schemes for Deep-Learning-Based Human Activity Classification Using Frequency-Modulated Continuous-Wave Radar

## Prof. Dr.-Ing. Slawomir Stanczak has been nominated as editor for the newly founded IEEE JSAC Machine Learning in Communications and Networks

Mittwoch, 20. Mai 2020

We are glad to announce that Prof. Dr.-Ing. Slawomir Stanczak has accepted to support the newly founded IEEE JSAC Machine Learning Series as an editor. Based on the expertise of Prof. Dr.-Ing. Stanczak, he will serve as an editor in the area of signal processing (including topics of detection, estimation, prediction, and compression).

## Online Demo 'Machine Learning-Based Adaptive Receive Filtering: Proof-of-Concept on an SDR Platform' by Matthias Mehlhose at ICASSP2020 //06. May 2020

Mittwoch, 06. Mai 2020

Abstract

The constant demand for low latency and high data rates in a modern mobile communications network creates new scientific challenges in each new generation. An accurate reconstruction of transmission data of as many users as possible at the base station is a task that can become mathematically very complex in today's mobile networks. The scientific community and our group at Fraunhofer Institute for Telecommunications (Heinrich Hertz Institute, HHI) are therefore investigating and comparing new methods such as NOMA with conventional orthogonal multi-user recognition techniques such as OFDMA. In combination with a large number of antennas on the receiving base station, a practical implementation can become very complex. In addition, subsequent errors in estimation with methods such as successive interference cancellation (SIC) can make it impossible for some users to reconstruct the data reliably if a large number of users are affected by incorrectly estimated parameters (such as user channels, covariance matrix, noise variance, etc.). In our demonstrator, we show how a receiver based on machine learning (ML) can help with this task. With low complexity, the modulation symbols for each user are detected without the need to estimate the typical parameters. All users send their pilots and data alternately on the same resources (frequency and time). The regular pilot phases are used to relearn changes in the channel. The method has the potential to contribute significantly to latency reduction through parallel implementation.

Presenter: Matthias Mehlhose, Fraunhofer Heinrich-Hertz-Institute

Date & Time: Wed, May 6, 2020, 5:30 pm – 7:30 pm

Venue: IEEE ICASSP 2020 (online)

ICASSP is the world’s largest and most comprehensive technical conference focused on signal processing and its applications. The 2020 conference will feature world-class presentations by internationally renowned speakers, cutting-edge session topics and provide a fantastic opportunity to network with like-minded professionals from around the world.

The venue is organized by IEEE Signal Processing Society

## It's Official - We are collaborating with NVIDIA and bringing AI to telecom!

April 21, 2020 by Soma Velayutham

Calling AI: Researchers Dial in Machine Learning for 5G

5G researchers from three top institutions have joined NVIDIA in bringing AI to telecom.

The Heinrich Hertz Institute (HHI), the Technical University in Berlin (TU Berlin) and Virginia Tech are collaborating with NVIDIA to harness the power of GPUs for next-generation cellular networks.

The journey began in October at MWC Los Angeles, where NVIDIA and partners announced plans to enable virtual radio access networks (vRANs) for 5G with GPUs.

NVIDIA also debuted Aerial, a software development kit for accelerating vRANs. And partners Ericsson, Microsoft and Red Hat are working with us to deliver 5G at the edge of the network powered by GPUs.

These vRANs will bring cellular network operators the kind of operational efficiencies that cloud service providers already enjoy. Carriers will program network functions in high-level software languages, easing the work of adding new capabilities and deploying capacity where and when it’s needed.

Forging Wireless Ties

Our new research partnerships with HHI, TU Berlin and Virginia Tech will explore multiple ways to accelerate 5G with AI.

They’ll define novel techniques leveraging GPUs that help wireless networks use precious spectrum more efficiently. The work will span research in reinforcement learning and other techniques that build on the product plans announced in October.

HHI is part of Germany’s Fraunhofer Society, a research group founded in 1928 that has a history of pioneering technologies in mobile and optical networking as well as video compression. The collaboration with TU Berlin includes a new 5G test bed with participation from a number of wireless companies in Germany.

“I want to redesign many algorithms in radio access networks (RAN) so we can perform tasks in parallel, and the GPU is a good architecture for this because it exploits massive parallelism,” said Slawomir Stanczak, a professor at TU Berlin and head of HHI’s wireless networking department.

Stanczak’s teams will explore use cases such as adapting AI to deliver improved 5G receivers. “If we are successful, they could offer a breakthrough in dramatically increasing performance and improving spectral efficiency, which is important because spectrum is very expensive,” he said.

In a session for GTC Digital, Stanczak recently described ways to apply AI to the private 5G campus networks which he believes will be market drivers for vRANs. Stanczak chairs a focus group on the use of AI in 5G for the ITU, a leading communications standards group. He’s also author of a widely cited text on the math behind optimizing wireless networks.

Hitting 5G’s Tight Timing Targets

Work at Virginia Tech is led by Tom Hou, a professor of computer engineering whose team specializes in solving some of the most complex and challenging problems in telecom.

His Ph.D. student, Yan Huang, described in a 2018 paper how he used an NVIDIA Quadro P6000 GPU to solve a complex scheduling problem in a tight 100-microsecond window set by the 5G standard. His latest effort cut the time to 60 microseconds using an NVIDIA Tensor Core V100 GPU.

The work “got an enormous response because at that time people using traditional computational techniques would hit roadblocks — no one in the world could solve such a complex problem in 100 microseconds,” said Hou.

“Using GPUs transformed our research group, now we are looking at AI techniques on top of our newly acquired parallel techniques,” he added.

Specifically, Virginia Tech researchers will explore how AI can automatically find and solve in real time thorny problems optimizing 5G networks. For instance, AI could uncover new ways to weave multiple services on a single frequency band, making much better use of spectrum.

“We have found that for some very hard telecom problems, there’s no math formulation, but AI can learn the problem models automatically, enhancing our GPU-based parallel solutions” said Huang.

Groundswell Starts in AI for 5G

Other researchers, including two who presented papers at GTC Digital, are starting to explore the potential for AI in 5G.

Addressing one of 5G’s top challenges, researchers at Arizona State University showed a new method for directing millimeter wave beams, leveraging AI and the ray-tracing features in NVIDIA Turing GPUs.

And Professor Terng-Yin Hsu described a campus network at Taiwan’s National Chiao Tung University that ran a software-defined cellular base station on NVIDIA GPUs.

“We are very much at the beginning, especially in AI for vRAN,” said Stanczak. “In the end, I think we will use hybrid solutions that are driven both by data and domain knowledge.”

Compared to 4G LTE, 5G targets a much broader set of use cases with a much more complex air interface. “AI methods such as machine learning are promising solutions to tackle these challenges,” said Hou of Virginia Tech.

NVIDIA GPUs bring the programming flexibility of CUDA and cuDNN environments and the scalability of multiple GPUs connected on NVLink. That makes them the platform of choice for AI on 5G, he said.

Today we stand at a pivot point in the history of telecom. The traditional principles of wireless signal processing are based on decades-old algorithms. AI and deep learning promise a revolutionary new approach, and NVIDIA’s GPUs are at the heart of it.

## Invited talk 'AI for Industrial Communication: Delusion or Salvation' by Prof. Dr.-Ing. Slawomir Stanczak at the VDE TEC SUMMIT 2020 // Feb. 26-27 2020

Mittwoch, 12. Februar 2020

The VDE Tec Summit from 26 to 27 February 2020 in the Arena in Berlin is the leading congress in the fields of Industry, Energy, Mobility, Future Technologies and Cybersecurity. In 28 sessions, 3 plenums, various interactive formats and an accompanying trade exhibition, participants will be given a profitable cross-industry application reference.

Parallel-Sessions 7: Industry - Neue Infrastruktur: 5G treibt Industrie 4.0

5G wird die Effizienz der Produktion und der Automatisierung erhöhen und IIoT-Projekte vorantreiben. Ein wichtiges Alleinstellungsmerkmal von 5G in Deutschland ist die Möglichkeit, private lokale echtzeitfähige Netze zu betreiben. Dadurch öffnet sich ein neuer Markt für dezentral organisierte Netzwerkbetreiber. Welche neuen Geschäftsmodelle werden dadurch möglich? Wie steht Deutschland im Wettbewerbsvergleich im Bereich 5G für die industrielle Produktion?

Title of the talk: AI for Industrial Communication: Delusion or Salvation?

When: Thursday, 27. February 2020 - 14:15 - 15:15 at the ARENA Berlin

Link to the venue program: https://tecsummit.vde.com/programm/programmuebersicht/

The conference is organized by VDI/ VDE + Technik GmbH.

## Accepted paper 'Joint Source-Channel Coding for Grant-Free Radio Access in IoT Fog Networks: Edge vs Cloud Processing' for IEEE SSP2021 // July 11-14 2021

Montag, 10. Februar 2020

IEEE Statistical Signal Processing Workshop 2021 is the 21th of a series of unique meetings that bring members of the IEEE Signal Processing Society together with researchers from allied fields such as bioinformatics, communications, machine learning, and statistics. SSP 2021 is a single-track workshop that includes invited talks, demonstrations and oral and poster presentations of refereed paper.

Authors: Johannes Dommel, Zoran Utkovski, Osvaldo Simeone, Slawomir Stanczak

Title: Joint Source-Channel Coding for Grant-Free Radio Access in IoT Fog Networks: Edge vs Cloud Processing

Abstract: A multi-cell Fog-Radio Access Network (F-RAN) architecture is considered in which Internet of Things (IoT) devices monitor a number of multi-valued events and transmit in the uplink using grant-free random access. The devices in each cell are connected to an Edge Node (EN), which has a ﬁnite-capacity fronthaul link to a Central Processor (CP). In contrast to conventional information-agnostic protocols based on Separate Source-Channel (SSC) coding, where each device uses a separate codebook, this paper considers an information-centric approach based on Joint Source-Channel (JSC) coding via a non-orthogonal generalization of Type-Based Multiple Access (TBMA). According to this transmission protocol, all sensors measuring the same event share the same codebook (with non-orthogonal codewords), and the multi-cell F-RAN architecture directly detects the events' values without first performing individual decoding for each device. Cloud and edge detection schemes based on Bayesian message passing are designed and trade-offs between cloud and edge processing are assessed.

## Accepted paper 'A hybrid model-data driven approach for the estimation of the angular power spectrum in massive MIMO systems' for IEEE SSP2021 // July 11-14 2021

Montag, 10. Februar 2020

We are glad to announce that the paper entitled 'A hybrid model-data driven approach for the estimation of the angular power spectrum in massive MIMO systems' has been accepted for presentation at the IEEE Statistical Signal Processing Workshop 2021 which will be held in Rio de Janeiro, Brazil from 11th-14th July, 2021.

Author: Renato L.G. Cavalcante and Slawomir Stanczak

Title: A hybrid model-data driven approach for the estimation of the angular power spectrum in massive MIMO systems

Abstract: Information about the angular power spectra (APS) of signals impinging on antenna arrays have important applications in massive MIMO systems such as user clustering, angle-of-arrival estimation, and channel covariance estimation in FDD systems, to cite a few. Current approaches for the estimation of APS can be divided into two main groups: model based methods and data driven methods. The former methods are able to produce reliable estimates with little side information and no training , but they do not exploit any information from datasets (if available) to improve the estimates. In contrast, pure data-driven methods can provided good performance without any knowledge about physical models, but they do not provide any guarantees of robustness against sudden changes in the propagation environment, a common occurrence in wireless systems. Against this background, we propose novel hybrid model and data driven algorithms that use both information about models and any available dataset. To this end, we modify projection and optimization methods for APS estimation by using an inner product (and hence the induced norm and metric) that is learned from data. The proposed algorithms are able to produce reliable estimates that exploit both statistical information available in datasets and model knowledge. As a result, they are able to provide robustness against relatively large changes in the propagation environment without the need to perform frequent training.

## Invited talk by Prof. Dr.-Ing. Slawomir Stanczak at the GPU Technology Conference (GTC) Silicon Valley, 2020

Mittwoch, 05. Februar 2020

We are delighted that Prof. Dr.-Ing. Slawomir Stanczak has again been invited to speak at the GPU Conference in Silicon Valley, 2020. The talk S22151 will be dedicated to the topic "When Neural Networks Meet Conventional Learning and Optimization Methods: Learning Radio Maps for Enhanced Physical-Layer Security".

When Neural Networks Meet Conventional Learning and Optimization Methods: Learning Radio Maps for Enhanced Physical-Layer Security [S22151]

We'll consider neural network architectures inspired by iterative algorithms that are widely used to solve convex optimization problems in many fields, including wireless communications. We refer to such neural networks as iterative neural networks based on Mann-type iteration. In particular, we'll focus on optimization problems where the objective function can be written as the sum of a convex smooth function and a non-smooth regularizer function. This problem formulation includes the important special case of the reconstruction of sparse signals where the non-smooth function is related to the l1-norm. Sparse signals occur in many optimization problems in wireless networks, such as channel estimation or reconstruction of quality-of-service (QoS) maps. We'll focus on the problem of reconstructing secrecy maps by learning any-to-any radio maps.

Primary Topic: IoT / 5G / Edge Computing

Topics: Autonomous Machines, Deep Learning Inference - Optimization and Deployment, Inspection / Predictive Maintenance / Logistics, IoT / 5G / Edge Computing, Algorithms / Numerical Techniques, Autonomous Vehicles

Industry Segment: Telecommunications

Session Type: Talk

GTC takes place March 22-26, 2020 at the San Jose McEnery Convention Center in San Jose, California with March 22 being a pre-conference DLI workshop day.

NVIDIA’s GPU Technology Conference (GTC) is a global conference series providing training, insights, and direct access to experts on the hottest topics in computing today.

The conference is organized by NVIDIA.

## Prof. Dr.-Ing. Slawomir Stanczak will serve as TPC member for the IEEE ICC'20 Workshop - ML4COM // 7-11 June 2020 - Dublin, Ireland

Mittwoch, 05. Februar 2020

We are gald to announce that Prof. Dr.-Ing. Slawomir Stanczak has been invited to serve as TPC member for the IEEE ICC'20 Workshop - ML4COM (IEEE ICC 2020 Workshop on Machine Learning in Communications) which he gladly accepted.

WS-19: Open Workshop on Machine Learning in Communications

Workshop Overview

Within a few years, machine learning has become a prominent and rapidly growing research topic within the field of communications, both in academia and industry. Machine learning applications in communication systems hold the potential to deeply transform wireless, optical, and other modes of communication engineering. In a discipline traditionally driven by compact analytic mathematical models, machine learning brings along a methodology that is data-driven and carries a major shift in the way wireless systems are designed and optimized. This brings with it both promise of more accurately representing complexities of the real world, as well as difficulties in providing the same levels of analytic performance guarantee and validation we are used to in communications systems. Research in this field is still largely in an exploration phase, but interest and speed of exploration and adoption has been significant. While machine learning has already been applied in a range of limited applications such as self-organized networks, sensing, cognitive radio, and resource allocation, these have largely focused on more constrained tasks and learning environments. In more recent years, the algorithms, tools, computational power, availability of data, and other enablers have led machine learning to more directly solve for larger tasks and signal processing functions within communications systems. This mirrors the significant breakthroughs within the field of machine learning in applications such as computer vision and natural language processing of embracing large datasets, concurrent tensor processing, and end-to-end learning techniques in order to effectively learn solutions to high complexity tasks. This workshop seeks to provide a first-tier platform for the dissemination of fundamental and applied research results in the exciting field of machine learning for communications.

Beyond providing a platform for the latest high-quality results in the field of machine learning for communication systems and encouraging fruitful and controversial discussions on the core challenges and prospect of the field, this workshop seeks to promote and encourage open-ness, rigor, and reproducibility.  As data measurement, processing, and learning systems are often significantly more intricate and specialized than compact analytic models, they often contain numerous details regarding the composition of the dataset, hyper-parameters and processing stages used within the learning and inference process, and countless additional implementation details which are difficult to compactly document within a concise and compact paper, but are easily captured within open software and data publications.  This has become the norm in a number of machine learning centric venues (e.g. NeurIPS, ICML), and rigorous new algorithmic work requires the publication and verification of open research. To embrace this within the IEEE ecosystem, this workshop is focused on directly supporting open-ness within machine learning for communications research, and asking researchers to share datasets, code, implementations, and baselines used throughout their work to help facilitate reproducibility and quantitative comparison by others within the field who may be able to critique, leverage, or extend research when it is conducted in such an open and reproducible manner.

Workshop Organizers

This workshop is being organized as part of the IEEE Emerging Technology Initiative in Machine Learning for Communications.

Venue: IEEE International Conference on Communications, 7-11 June 2020 // Dublin, Ireland

## IEEE ICC'20 - WC Symposium - the paper 'Machine Learning-Based Adaptive Receive Filtering: Proof-of-Concept on an SDR Platform' has been accepted for presentation

Montag, 27. Januar 2020

We are glad to announce that the paper entitled 'Machine Learning-Based Adaptive Receive Filtering: Proof-of-Concept on an SDR Platform' has been accepted for presentation at the IEEE International Conference on Communications 2020.The IEEE ICC'20 will take place in June 7-11, 2020 in Dublin, Ireland.

Authors: Matthias Mehlhose, Daniyal Amir Awan, Renato L.G. Cavalcante, Martin Kurras, Slawomir Stanczak

Abstract: Conventional multiuser detection techniques either require a large number of antennas at the receiver for a desired performance, or they are too complex for practical implementation. Moreover, many of these techniques, such as successive interference cancellation (SIC), suffer from errors in parameter estimation (user channels, covariance matrix, noise variance, etc.) that is performed before detection of user data symbols. As an alternative to conventional methods, this paper proposes and demonstrates a low-complexity practical Machine Learning (ML) based receiver that achieves similar (and at times better) performance to the SIC receiver. The proposed receiver does not require parameter estimation; instead it uses supervised learning to detect the user modulation symbols directly. We perform comparisons with minimum mean square error (MMSE) and SIC receivers in terms of symbol error rate (SER) and complexity.

Link to the arXiv file: arxiv.org/abs/1911.04291

## The manuscript 'Joint source-channel coding and bayesian message passing detection for grant-free radio access in IOT' has been accepted for presentation in a poster session at the 45th ICASSP 2020

Freitag, 24. Januar 2020

The manuscript 'Joint source-channel coding and bayesian message passing detection for grant-free radio access in IOT' has been accepted for presentation in a poster session at the 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, to be held in Barcelona, Spain between May 4 and May 8, 2020.

Session Title: 'Machine Learning for Communications (MLC)'

Title: 'Joint source-channel coding and bayesian message passing detection for grant-free radio access in IOT'

Authors: Johannes Dommel, Zoran Utkovski, Slawomir Stanczak and Osvaldo Simeone

Venue: 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, to be held in Barcelona, Spain between May 4 and May 8, 2020.

The conference is organized by CTCC.

## The manuscript 'Channel covariance estimation in multiuser massive MIMO systems with an approach based on infinite dimensional hilbert spaces' has been accepted for presentation in a poster session at the 45th ICASSP 2020

Freitag, 24. Januar 2020

The manuscript 'Channel covariance estimation in multiuser massive MIMO systems with an approach based on infinite dimensional hilbert spaces' has been accepted for presentation in a poster session at the 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, to be held in Barcelona, Spain between May 4 and May 8, 2020.

Session Title: 'MIMO and multi-antenna systems'

Title: 'Channel covariance estimation in multiuser massive MIMO systems with an approach based on infinite dimensional hilbert spaces'

Authors: Renato L. G. Cavalcante, Slawomir Stanczak

Venue: 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, to be held in Barcelona, Spain between May 4 and May 8, 2020.

The conference is organized by CTCC.

## The journal paper 'Connections between spectral properties of asymptotic mappings and solutions to wireless network problems' has been accepted for presentation in a poster session at the 45th ICASSP 2020

Freitag, 24. Januar 2020

The ICASSP 2020 Technical Committee has completed the review process and we are very delighted that the journal presentation request for the Signal Processing Society journal paper 'Connections between spectral properties of asymptotic mappings and solutions to wireless network problems' has been accepted for presentation in a poster session at the at the 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020.

The conference will be held in Barcelona, Spain between May 4 and May 8, 2020.

Session Title: 'Communication signal analysis and optimization'

Journal Title: 'Connections between spectral properties of asymptotic mappings and solutions to wireless network problems'

Authors: Renato L. G. Cavalcante, Qi Liao and Slawomir Stanczak

Venue: 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, to be held in Barcelona, Spain between May 4 and May 8, 2020.

The conference is organized by CTCC.

## The manuscript entitled 'Quality-of-Service prediction for physical-layer security via secrecy maps' has been accepted for presentation in a poster session at the 45th ICASSP 2020

Freitag, 24. Januar 2020

We are glad to announce that the manuscript entitled 'Quality-of-Service prediction for physical-layer security via secrecy maps' has been accepted for presentation in a poster session at the 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, to be held in Barcelona, Spain between May 4 and May 8, 2020.

Session Title: IFS Poster Session 1

Poster Title: Online channel estimation for hybrid beamforming architectures

Authors: Miguel A. Gutierrez-Estevez, Zoran Utkovski, Patrick Agostini, Daniel Schäufele, Matthias Frey, Igor Bjelakovic and Slawomir Stanczak

Venue: 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, to be held in Barcelona, Spain between May 4 and May 8, 2020.

The conference is organized by CTCC.

## The manuscript entitled 'Online channel estimation for hybrid beamforming architectures' has been accepted for presentation in a lecture session at the 45th ICASSP 2020

Freitag, 24. Januar 2020

We are glad to announce that the manuscript entitled 'Online channel estimation for hybrid beamforming architectures' has been accepted for presentation in a lecture session at the 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, to be held in Barcelona, Spain between May 4 and May 8, 2020.

Session Type: Lecture
Session Title: Channel estimation

Title: Online channel estimation for hybrid beamforming architectures

Authors: Jochen Fink, Renato Cavalcante, Slawomir Stanczak

Venue: 45th International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2020, to be held in Barcelona, Spain between May 4 and May 8, 2020.

The conference is organized by CTCC.

## Poster presentation 'Pulse-Shaped OTFS for V2X Short-Frame Communication with Tuned One-Tap Equalization' at the 24th International ITG Workshop on Smart Antennas, February 18-20, 2020 in Hamburg, Germany

Freitag, 20. Dezember 2019

We are gald to announce that the poster entitled 'Pulse-Shaped OTFS for V2X Short-Frame Communication with Tuned One-Tap Equalization' has been accepted for presentation at the 24th International ITG Workshop on Smart Antennas.

Authors of the poster: Andreas Pfadler, Peter Jung and Slawomir Stanczak

Title: 'Pulse-Shaped OTFS for V2X Short-Frame Communication with Tuned One-Tap Equalization'

The 24th International ITG Workshop on Smart Antennas (WSA 2020) provides a forum for presenting and discussing research results on smart antennas, spanning theoretical analyses as well as technical and implementation aspects, in modern wireless communications. The objective of this event is to continue, accelerate, and broaden the momentum which has been gained through a series of ITG workshops which started in 1996.

For the first time, the Workshop on Smart Antennas will take place in the city of Hamburg. It will be hosted at Hamburg University of Technology (TUHH) and is organized by the Institute of Communications. We invite all researchers working in the field of smart antennas to submit their papers, attend the workshop and present their latest research results.

Link to the venue program: https://cgi.tu-harburg.de/~c00wsa20/index.php?page=program

## Panel Session with Prof. Dr.-Ing. Slawomir Stanczak at IEEE Globecom 2019 - Session 3, Dec. 13, 2019

Freitag, 13. Dezember 2019

Session 3: Panel Session
2:00 pm - 3:30 pm, December 13, 2019

Panelists:

• Ahmed Alkhateeb, Assistant Professor, Arizona State University
• Jeff Andrews, Professor, University of Texas at Austin
• Marco Di Renzo, CNRS Research Director - CentraleSupelec, Paris-Saclay University
• Slawomir Stanczak, Professor, TU Berlin & Fraunhofer HHI
• Geoffery Ye Li, Professor, George Tech

Organizers:

•  Elisabeth De Carvalho, Professor, Aalborg University
• Tim O'Shea, Assistant Professor, Virginia Tech & CTO DeepSig

Abstract: This panel will explore views and ideas on future promising areas and applications for ML in wireless communications systems, exploring where panelists feel are the nearest, most impactful, most proven, most unfounded and most challenging impact areas.  We will attempt to understand where ML will have a major impact, and where and why it still falls short in other areas through a range of panel introductions, prompts, open questions, and subsequent discussions.

## Industry Presentation Session II (IPS-02) with Prof. Dr.-Ing. Slawomir Stanczak "Towards AI Revolution in Mobile Networking" at IEEE Globecom 2019

Donnerstag, 12. Dezember 2019

Industry Presentation Session 2 (IPS-02): Enabling Autonomous Networking Utilizing AI/ML Approach, Seeking “Ground Truth” in Training Algorithm

Date/Time: 12 December 2019, Thursday: 08:45-10:30
Room: Hilton, Kona 5

Organizer: Jingyi Zhou, ZTE (TX) Inc., USA

Presenter: Prof. Dr.-Ing. Slawomir Stanczak, Fraunhofer HHI / TU Berlin NetIT, Germany

Talk Title: Towards AI Revolution in Mobile Networking

Abstract: 5G will bring a revolution because 5G networks will be able to support various industrial applications with stringent QoS requirements. In addition to humans, 5G will connect machines and countless sensors at any time and everywhere. Machines will be connected in control loops with extremely low response times of milliseconds and less. In this talk, however, we argue that the actual 5G revolution is still to come. This revolution will be made possible by network virtualization and novel AI technologies. This is especially true for wireless access networks, where AI and virtualization will promote new business models, the emergence of new services, and the spread of private and campus networks.

## The manuscript "Robust Cell-Load Learning with a Small Sample Set" has been accepted for publication in the IEEE Transactions on Signal Processing

Freitag, 29. November 2019

We are glad to announce that the manuscript entitled "Robust Cell-Load Learning with a Small Sample Set" has been accepted for publication as a regular paper in the IEEE Transactions on Signal Processing.

The paper is written by our researchers Mr. Daniyal Awan, Dr.-Ing. Renato L.G. Cavalcante and Prof. Dr.-Ing. Slawomir Stanczak. The published version of the paper will be available soon in the IEEE Xplore Digital Library.

## Invited talk at the 2nd Visions for Future Communications Summit - Technologies and Services Towards 6G

Mittwoch, 20. November 2019

We are glad to announce that Prof. Dr.-Ing. Slawomir Stanczak will give a talk on "Smart Secure Systems, or Controlling networks and Advanced Services" at the 2nd Visions for Future Communications Summit at ISCTE - University Institute of Lisbon, Lisbon (Portugal).

Outline

Vision of Future Communications Summit is a top-quality research workshop, with the support of IEEE, oriented to identify key research areas in informatin and communication technologies in the mid-future of 7 to 10 years. It will follow from the previous event held in 2017, considering that now 5G is upon us.

Structure

The Summit will cover multiple research lines, roughly structured along Physical Layer, Network and Control Plane, and Applications and Services. Each research line will have a keynote speaker, and a set of sessions. All sessions will be organized as panels of distinguished speakers from academia, industry and High-level European Commission officials presenting their viewpoints on a subarea within each track. Panels will be oriented to encourage interaction among the panelists and between the panelists and the audience.

Venue: 27th, 28th November 2019 at ISCTE - University Institute of Lisbon, Lisbon (Portugal)

The event is organized by Networld2020 with the support of 5G Infrastructure Association, European Commission and IEEE.

## The demo 'Machine Learning-Based Adaptive Receive Filtering: Proof-of-Concept on an SDR Platform' has been submitted to the IEEE ICC 2020

Mittwoch, 13. November 2019

We are glad to announce that the demo entitled "Machine Learning-Based Adaptive Receive Filtering: Proof-of-Concept on an SDRR Platform" was submitted in cooperation with the Fraunhofer Heinrich-Hertz-Institute to the IEEE International Conference on Communications 2020.

Abstract: Conventional multiuser detection techniques either require a large number of antennas at the receiver for a desired performance, or they are too complex for practical implementation. Moreover, many of these techniques, such as successive interference cancellation (SIC), suffer from errors in parameter estimation (user channels, covariance matrix, noise variance, etc.) that is performed before detection of user data symbols. As an alternative to conventional methods, this paper proposes and demonstrates a low-complexity practical Machine Learning (ML) based receiver that achieves similar (and at times better) performance to the SIC receiver. The proposed receiver does not require parameter estimation; instead it uses supervised learning to detect the user modulation symbols directly. We perform comparisons with minimum mean square error (MMSE) and SIC receivers in terms of symbol error rate (SER) and complexity.

Link to the arXiv file: arxiv.org/abs/1911.04291

## Invited Talk at the Chalmers University of Technology in Goteborg: Towards Robust Machine Learning in 5G Radio Access Networks

Freitag, 25. Oktober 2019

Prof. Dr.-Ing. Slawomir Stanczak is invited to give a talk at the Chalmers University of Technology in Gothenborg.

The talk will take place on Thursday, 15th November 2019, 3pm - 4pm.

Title of the talk: Towards Robust Machine Learning in 5G Radio Access Networks

Abstract: Wireless communications poses some fundamental challenges to machine learning (ML). Due to high mobility, wireless links exhibit ephemeral and highly dynamic nature; moreover, the links are corrupted by noise and are in general exposed to interference, while wireless resources (spectrum and energy) are scarce. All this may greatly limit the capacity of wireless networks. Since data (including measurement data) is not available at a single point but distributed among different locations, there is a strong need for distributed ML algorithms that efficiently use the scarce wireless resources in 5G networks. Moreover, the new ML methods need to provide robust results based on small data sets and under latency constraints.

In this talk, we will discuss why ML has the potential for substantially enhancing current radio access networks (RAN) solutions, and we will give an overview of promising techniques and algorithmic approaches for overcoming the above mentioned challenges in 5G networks. We argue in favor of hybrid-driven methods that combine purely data-driven ML approaches with classical model-based methods, while making use of the available expert knowledge. In particular, it is in general necessary to exploit structures in the wireless channel, transmission signals and various functions such as load maps. We will consider both kernel-based methods and deep neural networks. Meeting the latency requirements of 5G networks requires massive parallelization. We'll discuss how to parallelize certain radio access network (RAN) functions to GPU architectures to achieve orders-of-magnitude acceleration.

Venue: Chalmers University of Technology, Chalmersplatsen 4, 412 96 Goteborg, Sweden

## Invited Talk at NYU (Tandon School of Engineering): Towards Robust Machine Learning in 5G Radio Access Networks

Donnerstag, 17. Oktober 2019

We are glad to announce that Prof. Dr.-Ing. Slawomir Stanczak is invited to give a talk at the Fall 2019 Seminars at NYU.

The talk will take place on Thursday, 17 October 2019, 11am -12pm.

Title of the talk: Towards Robust Machine Learning in 5G Radio Access Networks

Abstract: Wireless communications poses some fundamental challenges to machine learning (ML). Due to high mobility, wireless links exhibit ephemeral and highly dynamic nature; moreover, the links are corrupted by noise and are in general exposed to interference, while wireless resources (spectrum and energy) are scarce. All this may greatly limit the capacity of wireless networks. Since data (including measurement data) is not available at a single point but distributed among different locations, there is a strong need for distributed ML algorithms that efficiently use the scarce wireless resources in 5G networks. Moreover, the new ML methods need to provide robust results based on small data sets and under latency constraints.

In this talk, we will discuss why ML has the potential for substantially enhancing current radio access networks (RAN) solutions, and we will give an overview of promising techniques and algorithmic approaches for overcoming the above mentioned challenges in 5G networks. We argue in favor of hybrid-driven methods that combine purely data-driven ML approaches with classical model-based methods, while making use of the available expert knowledge. In particular, it is in general necessary to exploit structures in the wireless channel, transmission signals and various functions such as load maps. We will consider both kernel-based methods and deep neural networks. Meeting the latency requirements of 5G networks requires massive parallelization. We'll discuss how to parallelize certain radio access network (RAN) functions to GPU architectures to achieve orders-of-magnitude acceleration.

Venue: The Fall 2019 Seminars will take place in New York City, New York, USA from 11. September till 6. December 2019. Please visit the website of NYU (Tandon School of Engineering) for more information.

The New York University Tandon School of Engineering (commonly referred to as Tandon) is the engineering and applied sciences school of New York University. Tandon is the second oldest private engineering and technology school in the United States. The school dates back to 1854 when its predecessor institutions, the University of the City of New York School of Civil Engineering and Architecture and the Brooklyn Collegiate and Polytechnic Institute, were founded. The school was renamed in 2015 in honor of NYU Trustees and Ranjan Tandon following their donation of \$100 million to the school.

## Invited Talk by Prof. Dr.-Ing Stanczak at IEEE 5G World Forum on "AI for Industrial Communication: Delusion or Salvation?"

Mittwoch, 18. September 2019

We are glad to announce that Prof. Dr.-Ing. Slawomir Stanczak is invited to give a talk at the IEEE 5G World Forum and to give an impulse for Research, Development and Applications of 5G.

The talk will take place on Monday, 30th September 2019, 11:10-11:35 at the International Congress Center Dresden, Devrienstraße 10-12, 01067 Dresden.

Title of the talk: AI for Industrial Communication: Delusion or Salvation?

Venue: From September 30 to October 2 2019, the IEEE 5G World Forum (WF) welcomes its visitors and exhibitors in Dresden, for the first European edition of the event. As a leading scientific conference, the 5G WF brings together cutting-edge research in the field of 5G technology.

Progressing standardization, frequency allocation, and first active implementations can lead to the assumption that 5G needs no further research. This view must be clearly contradicted. The widespread introduction of 5G in an industrial context, among other things, still raises open questions, including the subject areas: Local industrial networks, environmental impacts and health aspects, the uses of virtualization, dynamic infrastructure, or service environments.

The annual Future Industrial Communication conference of the BMBF 5G research initiative will this year take place as part of the IEEE 5G World Forum in Dresden. It deals with the questions “Where are we?” and “What is still to be done?”, viewed from the users’ and researchers’ perspectives.

## New ITU standard to introduce Machine Learning into 5G networks

Donnerstag, 05. September 2019

A new ITU standard has established a basis for the cost-effective integration of Machine Learning into 5G and future networks.

The standard – ITU Y.3172 –  describes an architectural framework for networks to accommodate current as well as future use cases of Machine Learning.

“Machine Learning will change the way we operate and optimize networks,” says Slawomir Stanczak, Chairman of the ITU-T Focus Group on ‘Machine Learning for Future Networks including 5G’.

“Every company in the networking business is investigating the introduction of Machine Learning, with a view to optimizing network operations, increasing energy efficiency and curtailing the costs of operating a network,” says Stanczak. “This ITU Y.3172 architectural framework provides a common point of reference to improve industry’s orientation when it comes to the introduction of Machine Learning into mobile networks.”

Enhancing network management

Machine Learning holds great promise to enhance network management and orchestration. Drawing insight from network-generated data, Machine Learning can yield predictions to support the optimization of network operations and maintenance.

This optimization is becoming increasingly challenging, and increasingly important, as networks gain in complexity to support the coexistence of a diverse range of information and communication technology (ICT) services.

Network operators aim to fuel Machine Learning models with data correlated from multiple technologies and levels of the network.

They are calling for deployment mechanisms able to ‘future-proof’ their investments in Machine Learning. And they are in need of interfaces to transfer data and trained Machine Learning models across Machine Learning functionalities at multiple levels of the network.

The ITU Y.3172 architectural framework is designed to meet these requirements.

A focus on the future

The standard includes a unique focus on the future.

“ITU Y.3172 provides for the declarative specification of Machine Learning applications, making it the first mechanism to meet industry’s need for a standard method of including future use cases,” says Vishnu Ram, the lead editor of the standard.

ITU Y.3172 is under the responsibility of the Focus Group’s parent group, ITU-T Study Group 13 (Future networks and cloud).

“This is the first time that a Study Group has approved a Focus Group deliverable as an ITU standard before the conclusion of the Focus Group’s lifetime,” says Leo Lehmann, Chairman of ITU-T Study Group 13. This represents an important achievement in ITU’s work to expedite the transition from exploratory studies to the agreement of new ITU standards.

ITU-T Focus Groups are open to all interested parties. These groups accelerate ITU studies in fields of growing strategic relevance to ITU membership, delivering base documents to inform related standardization work in membership-driven ITU-T Study Groups.

“I would like to commend the many experts participating in both the Focus Group and ITU-T Study Group 13,” says Lehmann. “This early approval required a considerable amount of planning and extremely close collaboration, which could only have been achieved with dual participation and common interest.”

How the standard works

The standard offers a common vocabulary and nomenclature for Machine Learning functionalities and their relationships with ICT networks, providing for ‘Machine Learning Overlays’ to underlying technology-specific networks such as 5G networks. It describes a ‘loosely coupled’ integration of Machine Learning and 5G functionalities, minimizing their interdependencies to account for their parallel evolution.

The components of the architectural framework include ‘Machine Learning Pipelines’ – sets of logical nodes combined to form a Machine Learning application – as well as a ‘Machine Learning Function Orchestrator’ to manage and orchestrate the nodes of these pipelines.

‘Machine Learning Sandboxes’ are another key component of the framework, offering isolated environments hosting separate Machine learning pipelines to train, test and evaluate Machine Learning applications before deploying them in a live network.

“This combination of an architectural framework for Machine Learning and this declarative language to specify new use cases will give network operators complete power over the extension of Machine Learning to new use cases, the deployment and management of Machine Learning in the network, and the correlation of data from sources at multiple levels of the network,” says Ram.

Towards a complete Machine Learning toolkit

The ITU Y.3172 architectural framework is the first of a nascent series of ITU standards addressing Machine Learning’s contribution to networking.

“A range of ITU standards under development will complement and complete the architectural framework described by ITU Y.3172,” says Ram. “Collectively these standards will provide a full toolkit to build Machine Learning into our networks.”

Two draft ITU standards will propose mechanisms for data handling and specify the design of the ‘Machine Learning Function Orchestrator’.

“If data is the blood flowing through the heart that is Machine Learning, this function orchestrator can be considered the brain,” says Ram.

Another standard will support the assessment of intelligence levels across different parts of the network.

“Different parts of the network will be supplied by different vendors,” says Ram. “We are developing a standard way for different parties to look the intelligence level of the network, helping operators to evaluate vendors and regulatory authorities to evaluate the network.”

The series of ITU standards will be completed by a standard supporting the interoperability of Machine Learning marketplaces, marketplaces hosting repositories of Machine Learning models.

“The standard would assist potential adopters both in selecting a Machine Learning model capable of addressing their specific needs and in integrating the model into the network,” says Ram.

Watch ITU interviews with key Focus Group participants filmed at the launch of the group.

## ITU Workshop on AI for 5G & Beyond #Berlin5GWeek

Donnerstag, 05. September 2019

November 05, 2019
Fraunhofer HHI, Berlin, Germany

Are you ready to be a part of the change of tomorrow’s intelligent communication?

AI and Machine Learning are disrupting whole industries and are expanding their impact on the telecommunications sector as well. AI in the physical and network layers paves the way to automatic network configuration, increase of network efficiency and optimization of resources.

To prepare you for this revolution, Fraunhofer HHI hosts the ITU Workshop on Machine Learning for 5G and Beyond, this time within the #Berlin5GWeek on November 5th in Berlin. The workshop is organized by the ITU-T Focus Group on Machine Learning for Future Networks including 5G. Experts from various industries and academia show their latest developments. How the 5G future will be powered by AI is examined in a panel discussion with representatives from research, telecommunication providers and the startup scene.

General Chair:

Prof. Dr.-Ing. Slawomir Stanczak, Chairman of the ITU-T Focus Group on Machine Learning for Future Networks including 5G

Head of Wireless Communications and Networks Department, Fraunhofer HHI

## ITU Workshop on "Machine Learning for 5G and Beyond" - Berlin, Germany, 5 November 2019

Donnerstag, 05. September 2019

The International Telecommunication Union (ITU) is organizing the ITU Workshop on Machine Learning for 5G and Beyond which will take place on 5 November 2019 at Fraunhofer HHI, Einsteinufer 37,10587 in  Berlin, Germany. The workshop will be kindly hosted by Fraunhofer Heinrich Hertz Institute (HHI) . The workshop will be followed by the seventh meeting of the Focus Group on Machine Learning for Future Networks including 5G (FG-ML5G), from 6 to 8 November  2019, taking place at the  same venue. These ITU ML5G events coincide with “#Berlin5Gweek" from 4 November (Monday) to 8 November (Friday) (https://www.berlin5gweek.org). The workshop will open at 0930 hours on 5 November 2019; the FG meeting will open at 0930 hours on 6 November 2019. The meeting and workshop will be held in English only.

Target Audience
Participation is  open to ITU Member States, Sector Members, Associates and Academic Institutions and to any individual from a country that is a member of ITU who wishes to contribute to the work. This includes individuals who are also members of international, regional and national organizations. Participation at the workshop is free of charge and open to all.

Organized by: International Telecommunication Union (ITU)

Hosted by: Fraunhofer Heinrich Hertz Institute (HHI)

Date: 5 November 2019

Venue: Fraunhofer HHI, Einsteinufer 37, 10587 Berlin, Germany

Participation: Free of charge

Discussion: English

## Tutorial at 16th International Symposium on Wireless Communication Systems (ISWCS 2019)

Montag, 19. August 2019

Dr. Renato Cavalcante and Prof. Dr.-Ing. habil. Slawomir Stanczak will be giving a tutorial on Robust Online Machine Learning in 5G Radio Access Networks.

Time and Venue: 27. August 2019       IT105

Location: University of Oulu Linnanmaa Campus (Oulu, Finland)

Title: Robust Online Machine Learning in 5G Radio Access Networks: Requirements, Challenges, Theory and Promising Approaches.

Program: ISWCS’2019 Program

Workshop Abstract:

Wireless communications poses fundamental challenges to machine learning (ML). Wireless links are subject to fading and may be exposed to strong interference. Since wireless resources are scarce, this may severely limit the capacity of wireless links, thus requiring distributed ML solutions that efficiently use the wireless resources. Moreover, ML methods need to provide robust results based on small uncertain data sets and under strict latency constraints. Current signal processing algorithms for wireless transceivers are typically based on models that assume, for example, ideal linear amplifiers, perfect channel state information, and knowledge of interference patterns. In practice, however, these assumptions are unrealistic because many parameters have to be estimated, so it is often unclear how well the idealized models can capture the true behavior of real communication systems. (Read more)

## Technical Program Committee Chair for IEEE ICC'20 - WC Symposium

Montag, 19. August 2019

We are pleased to announce that Prof. Dr. Slawomir Stanczak will have a Technical Program Committee Chair for IEEE ICC'20 - WC Symposium (2020 IEEE International Conference on Communications (ICC): Wireless Communications Symposium), which will be held in Dublin, Ireland.

More detaills about the WSA 2020 will be announced on the following website:

The IEEE ICC 2020 will take place in Dublin from 07. – 11. June 2020.

With a theme of “Communications Enabling Shared Understanding,” this flagship conference of the IEEE Communications Society will offer five full days of original paper presentations, tutorials, workshops, keynotes, demonstrations, industry panels and social events designed to further career opportunities and the in-depth understanding of the latest communications advancements worldwide.

We look forward to welcoming you to Dublin in June 2020.

## We are glad to receive another generous donation for Fundamental Research from Nokia Bell Labs

Donnerstag, 15. August 2019

The Chair of Network Information Theory received another donation of 50,000 euros from Nokia Bell Labs. We will use this money for basic research at the chair. This is not earmarked funding from Nokia Bell Labs, but we are keen to intensify our cooperation.

We would like to thank Nokia Bell Labs for their generous support.

## The paper 'Distributed Approximation of Functions over Fast Fading Channels with Applications to Distributed Learning and the Max-Consensus Problem' has been ACCEPTED - 57th Annual Allerton Conference

Montag, 05. August 2019

It is our pleasure to inform you that the paper 'Distributed Approximation of Functions over Fast Fading Channels with Applications to Distributed Learning and the Max-Consensus Problem' has been accepted and has been assigned to the session 'Statistical Signal Processing' for presentation at the 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton). The conference will take place from September 24-27, 2019 in Urbana, IL, USA.

The authors of the paper are Dr. rer. nat. Igor Bjelakovic, Matthias Frey and Prof. Dr.-Ing. Slawomir Stanczak.

Abstract of the paper: In this work, we consider the problem of distributed approximation of functions over multiple-access channels with additive noise. In contrast to previous works, we take fast fading into account and give explicit probability bounds for the approximation error allowing us to derive bounds on the number of channel uses that are needed to approximate a function up to a given approximation accuracy. Neither the fading nor the noise process is limited to Gaussian distributions. Instead, we consider sub-gaussian random variables which include Gaussian as well as many other distributions of practical relevance. The results are motivated by and have immediate applications to a) computing predictors in models for distributed machine learning and b) the max-consensus problem in ultra-dense networks.

## The paper 'Online Learning Framework for V2V Link Quality Prediction' has been ACCEPTED - Globecom 2019

Donnerstag, 18. Juli 2019

The paper entitled "Online Learning Framework for V2V Link Quality Prediction" has been accepted for presentation at the IEEE GLOBECOM 2019, December 9 – 13, in Waikoloa, Hawaii, USA and for publication in its proceedings.

The authors of the paper are Ramya Panthangi Manjunath, Mate Boban, Chan Zhou and Slawomir Stanczak.

## Technical Program Committee Chair for the Workshop on Smart Antennas (WSA) 2020

Mittwoch, 26. Juni 2019

We are pleased to announce that Prof. Dr. Slawomir Stanczak will have a Technical Program Committee Chair for the Workshop on Smart Antennas 2020, which will take place in Hamburg, Germany.

More detaills about the WSA 2020 will be announced on the following website:

The WSA 2020 will take place in Hamburg at the Technische University Hamburg (TUHH) from the 18. – 20. February 2020 and will be be hosted by Gerhard Bauch and the Institute of Communications at TUHH.

It’s the first time that the workshop is hosted in Hamburg which is a great place for this event!

## TPC Chair for the Workshop-18: Machine Learning for Wireless Communications at IEEE Globecom 2019

Mittwoch, 05. Juni 2019

This year Prof. Dr. Slawomir Stanczak will co-organize the workshop (WS-18) named "Machine Learning for Wireless Communications" which is part of the IEEE Global Communications Conference 2019.

Please click on the link below for the scope of the workshop:

Important Dates:

• Paper Submission: July 5, 2019
• Decision Notification: Aug. 15, 2019
• Camera Ready: Sept. 15, 2019
• Workshop date: morning of Dec. 2019

The 2019 IEEE Global Communications Conference (GLOBECOM) will be held in Waikoloa, Hawaii, USA, from 9 -13 December 2019.

Themed “Revolutionizing Communications,” this flagship conference of the IEEE Communications Society will feature a comprehensive high-quality technical program including 13 symposia and a variety of tutorials and workshops. IEEE GLOBECOM 2019 will also include an attractive Industry program aimed at practitioners, with keynotes and panels from prominent research, industry and government leaders, business and industry panels, and vendor exhibits.

## The paper 'A Scalable Max-Consensus Protocol For Noisy Ultra-Dense Networks' has been ACCEPTED - IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) 2019

Dienstag, 30. April 2019

We are happy to announce that the paper with the title "A Scalable Max-Consensus Protocol For Noisy Ultra-Dense Networks" has been accepted for presentation on the IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) 2019. The venue will take place in Cannes, France from July 2-5 2019.

The authors of the paper are N. Agrawal, M. Frey and S. Stanczak.

The SPAWC 2019 will exhibit a technical program complete with high profile plenaries, invited and contributed papers, all appearing under IEEE Xplore. A flagship workshop of the IEEE SP Society SPCOM technical committee, SPAWC 2019 will combine cutting edge research in the fields of signal processing, statistical learning, communication theory, wireless networking and more, together with an exciting social program on the glamorous and sunny Riviera.

## The paper 'Tensor Completion for Radio Map Reconstruction using Low Rank and Smoothness' has been ACCEPTED - IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) 2019

Dienstag, 30. April 2019

The paper with the title "Tensor Completion for Radio Map Reconstruction using Low Rank and Smoothness" has been accepted for presentation on the IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) 2019. The venue will take place in Cannes, France from July 2-5 2019.

The authors of the paper are D. Schäufele, R. L.G. Cavalcante and S. Stanczak.

The SPAWC 2019 will exhibit a technical program complete with high profile plenaries, invited and contributed papers, all appearing under IEEE Xplore. A flagship workshop of the IEEE SP Society SPCOM technical committee, SPAWC 2019 will combine cutting edge research in the fields of signal processing, statistical learning, communication theory, wireless networking and more, together with an exciting social program on the glamorous and sunny Riviera.

## The paper 'Learning radio maps for physical-layer security in the radio access' has been ACCEPTED - IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) 2019

Dienstag, 30. April 2019

The paper with the title "Learning radio maps for physical-layer security in the radio access" has been accepted for presentation on the IEEE International Workshop on Signal Processing Advances in Wireless Communications (SPAWC) 2019. The venue will take place in Cannes, France from July 2-5 2019.

The authors of the paper are Z.Utkovski, P. Agostini, M.Frey, I.Bjelakovic, and S. Stanczak.

The SPAWC 2019 will exhibit a technical program complete with high profile plenaries, invited and contributed papers, all appearing under IEEE Xplore. A flagship workshop of the IEEE SP Society SPCOM technical committee, SPAWC 2019 will combine cutting edge research in the fields of signal processing, statistical learning, communication theory, wireless networking and more, together with an exciting social program on the glamorous and sunny Riviera.

## Digital Technology Days at BMWi - Panel Discussions and Keynote Lecture with Prof. Dr.-Ing. Slawomir Stanczak - 14.+15. May 2019, Berlin, Germany

Montag, 29. April 2019

On 14 and 15 May 2019, the Federal Ministry of Economics and Energy (BMWi) will host the "Digital Technologies Days" in Berlin.

The BMWi currently supports the development of digital cutting-edge technologies in and for Germany and the European Economic Area with around 75 million euros annually via application-oriented technology programmes. The aim is to address future ICT topics at an early stage and to accelerate the transfer of scientific results to marketable products, solutions and business models. The "Digital Technologies Days" present outstanding results from these programmes.

Actors from industry, research and politics will discuss the latest developments and future-relevant topics in the fields of industry, mobility, health and energy. The two event days offer a forum for professional exchange and networking and are intended to contribute to the formation of cross-sector value creation networks.

On both days of the venue Prof. Dr.-Ing. Slawomir Stanczak is invited to share his expertise at the Panels on 5G. Following the panel discussion he will give a keynote lecture on the first day.

1. Day of the Technology Days:

• Panel Discussion: Expert Forum - 5G as cross-industry enabler for new applications, business models and value creation networks - 14:30-15:15Uhr

• Keynote Lecture: Expert Forum - Mobile communication: Beyond 5G, 15:45-16:30Uhr

• Title of the presentation: Wireless Research Towards Beyond 5G: From Evolution to Revolution in Mobile Communications
• Abstract: On the one hand, 5G will bring a revolution because 5G networks will be able to support various industrial applications with stringent QoS requirements. In addition to humans, 5G will connect machines and countless sensors at any time and everywhere. Machines will be connected in control loops with extremely low response times of milliseconds and less. On the other hand, from a technological point of view, 5G is only an evolution when compared to 4G. 5G technologies do not technically differ much from the proven 4G concepts. 5G NR is still based on multi-carrier transmission methods, while other key technologies such as massive MIMO or network sicing are largely extensions and implementations of well-known ideas that offer more flexibility.
• In this talk we will show that the actual 5G revolution is still to come. This revolution will be made possible by network virtualization and novel AI technologies. This is especially true for wireless access networks, where AI and virtualization will promote new business models, the emergence of new services, and the spread of private and campus networks. We will discuss important challenges and promising research directions for the beyond 5G revolution.

2. Day of the Technology Days:

• Panel Discussion: Expert Forum - Trust in the Digital Age: Reliability, Security and Integrity of IT Systems - 14:00-14:45Uhr

## Invited Speaker - Prof. Dr.-Ing. Slawomir Stanczak will attend the Industry Panel on 'AI/ ML in 5G PHY and Low MAC' at ICC 2019

Montag, 29. April 2019

Prof. Dr.-Ing. Slawomir Stanczak is invited to attend the Industry Panel on AI/ ML in 5G PHY and Low MAC at the 53rd IEEE International Conference on Communications (ICC) 2019.

Tuesday, 21 May, 09:00-10:30

IP01: AI/ML in 5G PHY and Low MAC
Room: Yellow River Hall, 3rd Floor
Organizer: Peiying Zhu, Huawei Fellow and IEEE Fellow, Huawei Technologies Co. Ltd., Canada
Moderator: Peiying Zhu, Huawei Fellow and IEEE Fellow, Huawei Technologies Co. Ltd., Canada
Panelists:

• Zhi Ding, University of California Davis, USA
• Haris Gacanin, Nokia Bell Labs, Belgium
• Slawomir Stanczak, Fraunhofer HHI and TU Berlin, Germany
• Jean-Claude Belfiore, Huawei, France

The rise of 5G together with artificial intelligence (AI) will revolutionize technology, create new business opportunities and change society. Research works have illustrated the benefits of applying AI/ML to wireless network and radio resource management. Some researchers also show promising results by replacing/redesigning individual or joint modules in conventional communication networks with methods developed in AI. Besides applying AI to the upper layers of wireless communication systems, AI-based PHY- and low-MAC- layer wireless communications has recently attracted a wide range of interests. In particular, autoencoder-based full end-to-end system reveals a fundamental change in the architecture of the communication systems and faces great challenges in conventional communication theories. In this panel, leading experts are invited to discuss the major benefits and challenges in bringing AI to 5G PHY and low MAC layers as well as to share their insights on how the forward path might evolve.

Venue: The ICC 2019 will take place in Shanghai, China from 20-24 May 2019. Please visit the website of IEEE ICC for more information.

Themed “Empowering Intelligent Communications,” this ﬂagship conference of the IEEE Communications Society will offer five full days of original paper presentations, tutorials, workshops, keynotes, demonstrations, industry panels and social events designed to further career opportunities and the in-depth understanding of the latest communications advancements worldwide.

## Invited Talk at the EUCNC 2019 - Workshop 7: Artificial Intelligence for 5G Networks

Donnerstag, 25. April 2019

We are glad to announce that Prof. Dr.-Ing. Slawomir Stanczak is invited to give a talk at the European Conference on Networks and Communications (EuCNC) 2019.

The talk will be part of the Workshop 7: Artificial Intelligence for 5G Networks which takes place on Thursday, 20 June 2019, 14:00-17:30 pm.

Title of the talk: Challenges and Research Directions in Machine Learning for 5G and Beyond

Abstract: Wireless communications poses some fundamental challenges to machine learning (ML). Due to high mobility, wireless links exhibit ephemeral and  highly dynamic nature; moreover, the links are corrupted by noise and are in general exposed to interference, while wireless resources (spectrum and energy) are scarce. All this may greatly limit the capacity of wireless networks. Since data (including measurement data) is not available at a single point but distributed among different locations, there is a strong need for distributed ML algorithms that efficiently use the scarce wireless resources in 5G networks. Moreover, the new ML methods need to provide robust results based on small data sets and under latency constraints.

In this talk, we will discuss why ML has the potential for substantially enhancing current radio access networks (RAN) solutions, and we will give an overview of promising techniques and algorithmic approaches for overcoming the above mentioned challenges in 5G networks. We argue in favor of hybrid-driven methods that combine purely data-driven ML approaches with classical model-based methods, while making use of the available expert knowledge. In particular, it is in general necessary to exploit structures in the wireless channel, transmission signals and various functions such as load maps. We will consider both kernel-based methods and deep neural networks. Meeting the latency requirements of 5G networks requires massive parallelization. We'll discuss how to parallelize certain radio access network (RAN) functions to GPU architectures to achieve orders-of-magnitude acceleration.

Venue: The EuCNC will take place in Valencia, Spain from 18-21 June 2019. Please visit the website of EuCNC 2019 for more information.

EuCNC 2019 is the 28th edition of a successful series of a conference in the field of telecommunications, sponsored by the IEEE Communications Society and the European Association for Signal Processing, and supported by the European Commission. This conference is one of the most prominent communications and networking conferences in Europe, which efficiently brings together cutting-edge research and world-renown industries and businesses. EuCNC attracts more than 600 delegates each year and an exhibition space of more than 1,500 m2. The conference focuses on various aspects of 5G communications systems and networks, including cloud and virtualisation solutions, management technologies, and vertical application areas. It targets to bring together researchers from all over the world to present the latest research results, and it is one of the main venues for demonstrating the results of research projects, especially from successive European R&D programmes co-financed by the European Commission.

EuCNC 2019 will be co-located with the Global 5G Event, which brings together the world 5G industrial associations: 5G-IA, IMT-2020, 5G-Forum, 5G-MF, 5G-Brasil and 5G-Americas.

## Invited Speaker - Prof. Dr.-Ing. Slawomir Stanczak will share his expertise on 5G and AI on the Panel 'B5G and AI' at the EuCNC 2019

Donnerstag, 25. April 2019

Prof. Dr.-Ing. Slawomir Stanczak is invited to attend the Panel on B5G and AI at the European Conference on Networks and Communications (EuCNC) 2019 and to share his expertise on 5G and AI. The date of the Panel will be Friday, 21 June 2019.

Venue: The EuCNC will take place in Valencia, Spain from 18-21 June 2019. Please visit the website of EuCNC 2019 for more information.

EuCNC 2019 is the 28th edition of a successful series of a conference in the field of telecommunications, sponsored by the IEEE Communications Society and the European Association for Signal Processing, and supported by the European Commission. This conference is one of the most prominent communications and networking conferences in Europe, which efficiently brings together cutting-edge research and world-renown industries and businesses. EuCNC attracts more than 600 delegates each year and an exhibition space of more than 1,500 m2. The conference focuses on various aspects of 5G communications systems and networks, including cloud and virtualisation solutions, management technologies, and vertical application areas. It targets to bring together researchers from all over the world to present the latest research results, and it is one of the main venues for demonstrating the results of research projects, especially from successive European R&D programmes co-financed by the European Commission.

EuCNC 2019 will be co-located with the Global 5G Event, which brings together the world 5G industrial associations: 5G-IA, IMT-2020, 5G-Forum, 5G-MF, 5G-Brasil and 5G-Americas.

## The paper 'Human Activity Classification with Frequency Modulated Continuous Wave Radar Using Deep Convolutional Neural Networks' has been ACCEPTED - International Radar Conference 2019

Dienstag, 23. April 2019

We are happy to announce that the paper with the title "Human Activity Classification with Frequency Moudulated Continous Wave Radar Using Deep Convolutional neural Networks" has been accepted to the International Radar Conference 2019.

The authors of the paper are R. Hernangómez Herrero, A. Santra and S. Stanczak. They are very happy about this announcement and excited to present their paper on the conference.

The conference is organized by the French SEE Society (Société de l'Electricité, de l'Electronique et des technologies de l'information et de la communication) which will take place from 23.-27. September 2019 in Toulon, France.

The conference will be organized in the frame of the International relations set up between the IET (Institution of Engineering and Technology), the IEEE (Institute of Electrical and Electronics Engineers), the CIE (Chinese Institute of Electronics), the IEAust (Institute of Engineers Australia) and SEE.

## IEEE Transactions on Signal Processing - "Connections between spectral properties of asymptotic mappings and solutions to wireless network problems" has been ACCEPTED for publication

Donnerstag, 21. März 2019

The manuscript "Connections between spectral properties of asymptotic mappings and solutions to wireless network problems" has been accepted for publication as a regular paper in the IEEE Transcations on Signal Processing. The manuscript will be available on IEEE Xplore.

Authors: R. L.G. Cavalcante, Q. Liao and S. Stanczak

## TPC Chairs for IEEE GLOBECOM 2020 - Prof. Dr.-Ing. Stanczak has been invited to serve the conference as the Chair of SAC: ML for Communications

Dienstag, 19. März 2019

As part of the IEEE GLOBECOM 2020 symposium chair nomination and selection process, Prof. Dr.-Ing. Slawomir Stanczak has been selected to serve as the chair of SAC: Machine Learning for Communications.

Prof. Dr.-Ing. Stanczak has gladly confirmed the acceptance of this invitation. The IEEE Globecom 2020 will be held in Taipei, Taiwan, in December 2020.

## Invited Talk at Technology Workshop on Machine Learning/ Artificial Intelligence in 5G Radio Access organzied by ETSI ENI - Warsaw, Poland 12 April 2019

Mittwoch, 06. März 2019

Prof. Dr.-Ing. Stanczak is invited to give a talk on Machine Learning/ Artificial Intelligence in 5G Radio Access Networks at the Technology Workshop which is organized by ETSI ENI (Experiential Networked Intelligence).

The Workshop will address Machine Learning and Artificial Intelligence in 5G Radio Access and its connection to intelligent policy management that ETSI ISG ENI is addressing. This workshop will take place on the 12 April 2019 in Warsaw, Poland.

## Invited Talk at Robert Bosch GmbH on Machine Learning for 5G and Beyond: Challenges, Opportunities and Promising Approaches - Renningen, Germany 21 March 2019

Montag, 04. März 2019

Prof. Dr.-Ing. Stanczak is invited to give a talk on "Machine Learning for 5G and Beyond: Challenges, Opportunities and Promising Approaches" at the Workshop organized by Robert Bosch GmbH in Renningen, Germany.

The Robert Bosch GmbH Workshop will take place on March 21, 2019 in Renningen, Germany.

## Invited Talk at ITU Workshop on AI Enables Intelligent 5G Network - Shenzen, China, 6 March 2019

Dienstag, 26. Februar 2019

Prof. Dr.-Ing. Stanczak is invited to give a talk on "Machine Learning-Aware Communication Networks: A driver for Relevant Ecosystems" at the ITU Workshop on AI Enables Intelligent 5G Network.

The Workshop will take place in Shenzen, China on the 6th March 2019.

For further information regarding the Sessions and Speakers at the Workshop please click on the link attached: https://www.itu.int/en/ITU-T/Workshops-and-Seminars/201903/Pages/Programme.aspx

## A new DFG-Project for the conceptional realization of Full-Duplex transceivers has been authorized for the Institute of Telecommunications

Mittwoch, 21. November 2018

We are glad to announce that the German Research Foundation (DFG) authorized another project for the Institute of Telecommunications for a duration of three years. The new project focuses on the conceptual realization of Full-Duplex transceivers within the milimeter wave band for applications within wireless backhauls for small radio cells.

## Prof. Dr.-Ing. Slawomir Stanczak was appointed by the IEEE ComSoc as a 'Workshops, Tutorials, & Symposia Officer' of the Emerging Technology Initiative

Montag, 19. November 2018

The aim of this Emerging Technology Initiative (ETI) is to foster research and innovation surrounding the use of machine learning (ML) for the physical (PHY) and medium access control (MAC) layers for all types of communication systems, such as wireless, optical, satellite, and molecular. We provide a list of Best Readings in MLC for newcomers and organize conference workshops, tracks, sessions, industry symposia, tutorials, summer schools, data science competitions, as well as special issues in journals. We aim to establish common data sets and related benchmarks and invite authors to open-source their code for reproducible research. We maintain a blog where members can write articles, opinions, perspectives or present their research in an accessible way.

Slawomir Stanczak studied electrical engineering with specialization in control theory at the Wroclaw University of Technology and at the Technical University of Berlin (TU Berlin). He received the Dipl.-Ing. degree in 1998 and the Dr.-Ing. degree (summa cum laude) in electrical engineering in 2003, both from TU Berlin; the Habilitation degree (venialegendi) followed in 2006. Since 2015, he has been a Full Professor for network information theory with TU Berlin and the head of the Wireless Communications and Networks department. Prof. Stanczak is a co-author of two books and more than 200 peer-reviewed journal articles and conference papers in the area of information theory, wireless communications, signal processing and machine learning.He was an Associate Editor of the IEEE Transactions on Signal Processing between 2012 and 2015.

______________________________

## Session and demonstration on "Collaborative Compressive Inference for 5G" at the GTC Europe 2018 by Prof. Slawomir Stanczak, Steffen Limmer and Georg Hieronimus

Donnerstag, 01. November 2018

Prof. Salwomir Stanczak was invited to give a session on "Machine Learning enabled 5G Wireless Networks: GPU Convex Feasibility Solvers" at the GTC Europe which took place on 9-11 October 2018 in Munich.

As part of the GTC Europe the researchers Georg Hieronimus, Steffen Limmer and Prof. Slawomir Stanczak from TU Berlin and Franhofer Heinrich-Hertz-Institute presented also a demonstration on "Collaborative Compressive Interference". The presented system shows the advantages of the cooperation on several image recognition systems in practical use. The scene is recorded by several Nvidia Jetson Edge computers from different perspectives and used for individual decision-making.

NVIDIA’s GPU Technology Conference (GTC) Europe is part of the largest global series of events focused on artificial intelligence and its applications across many important fields.

______________________________

Organized by: NVIDIA

## Invited Talk at Future Industrial Communication Conference - Nationales Symposium BMBF-Forschungsinitiativen 5G

Dienstag, 02. Oktober 2018

Prof. Dr.-Ing. Slawomir Stanczak was very happy to give a talk on 5G research perspectives at the Future Industrial Communication Conference which took place in September in Berlin. Pictures of the event can be found here.

Organized by the Information Platform for 5G Industrial Internet, the Future Industrial Communication Conference is an annual cutting-edge forum for discussions on 5G technologies, including its application in industry.

## The manuscript 'A Neural Architecture for Bayesian Compressive Sensing over the Simplex via Laplace Techniques' has been accpected for publication in the IEEE Transactions on Signal Processing

Montag, 24. September 2018

The manuscript 'A Neural Architecture for Bayesian Compressive Sensing over the Simplex via Laplace Techniques' has been accepted for publication as a regular paper in the IEEE Transactions on Signal Processing.

The Authors of the manuscript are Steffen Limmer and Prof. Dr.-Ing. Slawomir Stanczak.

Link to the IEEE Explore Digital Library: https://ieeexplore.ieee.org/Xplore/home.jsp

## Invited Talk at Intel Corp.: "Machine Learning in 5G Radio Access Networks" by Prof.Slawomir Stanczak | 10.August 2018 | San Jose, CA

Montag, 06. August 2018

Title: Machine Learning in 5G Radio Access Networks

Abstract: Wireless communications poses some fundamental challenges to machine learning (ML). Due to high mobility, wireless links exhibit ephemeral and  highly dynamic nature; moreover, the links are corrupted by noise and are in general exposed to interference, while wireless resources (spectrum and energy) are scarce. All this may greatly limit the capacity of wireless networks. Since data (including measurement data) is not available at a single point but distributed among different locations, there is a strong need for distributed ML algorithms that efficiently use the scarce wireless resources in 5G networks. Moreover, the new ML methods need to provide robust results based on small data sets and under latency constraints.

In this talk, we will discuss why ML has the potential for substantially enhancing current radio access networks (RAN) solutions, and we will give an overview of promising techniques and algorithmic approaches for overcoming the above mentioned challenges in 5G networks.  We argue in favor of hybrid-driven methods that combine purely data-driven ML algorithms with classical model-based  approaches, while making use of the available expert knowledge. In particular, it is in general necessary to exploit structures in the wireless channel, transmission signals and various functions such as load maps. We will consider both kernel-based methods and deep neural networks.

Location & Date: Intel Corp. San Jose, California | 10.August 2018

## The manuscript "Compressive Rate Estimation with Applications to Device-to-Device Communications" has been ACCEPTED for publication

Freitag, 03. August 2018

The manuscript entitled "Compressive Rate Estimation with Applications to Device-to-Device Communications" is accepted in its current form for publication in the IEEE Transactions on Wireless Communications.

Abstract: We develop a framework that we call compressive rate estimation. We assume that the composite channel gain matrix (i.e. the matrix of all channel gains between all network nodes) is compressible which means it can be approximated by a sparse or low rank representation. We develop and study a novel sensing and reconstruction protocol for the estimation of achievable rates. We develop a sensing protocol that exploits the superposition principle of the wireless channel and enables the receiving nodes to obtain non-adaptive random measurements of columns of the composite channel matrix. The random measurements are fed back to a central controller that decodes the composite channel gain matrix (or parts of it) and estimates individual user rates. We analyze the rate loss for a linear and a non-linear decoder and find the scaling laws according to the number of non-adaptive measurements. In particular if we consider a system with <nobr>N</nobr> nodes and assume that each column of the composite channel matrix is <nobr>k</nobr> sparse, our findings can be summarized as follows. For a certain class of non-linear decoders we show that if the number of pilot signals <nobr>M</nobr> scales like <nobr>Mklog(N/k)</nobr>, then the rate loss compared to perfect channel state information remains bounded. For a certain class of linear decoders we show that the rate loss compared to perfect channel state information scales like <nobr>1/M‾√</nobr>

Authors: Jan Schreck and Peter Jung and Slawomir Stanczak.

Publisher: IEEE

## Invited Talk at GTC Europe 2018 - Session by Prof. Slawomir Stanczak on "Machine Learning Enabled 5G Wireless Networks: GPU Convex Feasibility Solvers" 11.October 2018 | Munich

Mittwoch, 01. August 2018

NVIDIA’s GPU Technology Conference (GTC) Europe is part of the largest global series of events focused on artificial intelligence and its applications across many important fields.

Choose from over a hundred sessions at GTC Europe 2018 where rising AI startups, innovative researchers, and leading enterprises present critical breakthroughs, industry-changing technologies, and successful implementations.

The GTC Europe 2018 takes place 9-11 October at the International Congress Centre in Munich, Germany.

Session by Prof. Slawomir Stanczak: Thursday, 11/10/2018 | 13:30 - 14:15 Room 14a  - "Machine Learning Enabled 5G Wireless Networks: GPU Convex Feasibility Solvers" - E8422 Talk

Registration: use the VIP code GMSP18 for a 20% discount on the price of your ticket!!!

______________________________

Organized by: NVIDIA

## Future Industrial Communication Conference - Nationales Symposium BMBF-Forschungsinitiativen 5G 11.-13.September 2018 | Berlin

Freitag, 27. Juli 2018

Organized by the Information Platform for 5G Industrial Internet, “Future Industrial Communication” is an annual cutting-edge forum for discussions on 5G technologies, including its application in industry. Join us in Berlin from September 11-13 for this exciting event!

Program:

• 11.09.2018 5G Nationales Symposium (This event will be held in German)

• Prof. Stanczak is invited to discuss with other representatives out of industry, research, equipment and the Federal Network Agency about the actual situation of the industrial and tactile communication in Germany. Which course has been set, and how can we shape it? - the panel discussion will take place from 4:30 to 5:30pm

• 12.09.2018 5G Research Perspectives (This event will be held in English)

• Prof. Stanczak will be giving a talk on behalf of the Fraunhofer HHI on "Enhancing 5G Radio Access Technologies with Machine Learning" - the talk will be held at 12:30am, Session 2: Seamless Communication System

• 13.09.2018 5G Projekte im Dialog (This event will be held in German)

Venue: Sofitel Kurfürstendamm, Augsburger Straße 41, 10789 Berlin, Germany

## Globecom 2018 - The Paper "Error Bounds for FDD Massive MIMO Channel Covariance Conversion with Set-Theoretic Methods" has been ACCEPTED.

Mittwoch, 18. Juli 2018

The paper 'Error Bounds for FDD Massive MIMO Channel Covariance Conversion with Set-Theoretic Methods' has been accpeted for presentation at the IEEE Globecom2018 WC and for publication in its proceedings. IEEE Globecom2018 WC received 2700 submissions and only high-quality papers with an acceptance rate of around 38% could be accepted.

The IEEE Globecom2018 will take place in Abu Dhabi, UAE from 9-13 December 2018.

The Authors of the Paper are Renato L.G. Cavalcante, Lorenzo Miretti and Slawomir Stanczak

## Generous Donation for Fundamental Research

Dienstag, 10. Juli 2018

The Chair of Network Information Theory received a donation of 50,000 euros from Nokia Bell Labs. We will use this money for basic research at the chair. This is not earmarked funding from Nokia Bell Labs, but we are keen to intensify our cooperation. We would like to thank Nokia Bell Labs for their generous support.

## We are glad to announce that the DFG Project "Joint design of compressed sensing and network coding for wireless meshed networks" goes into the next phase!

Montag, 09. Juli 2018

The DFG (German Research Foundation) announced that the funding of the project "Joint design of compressed sensing and network coding for wireless meshed networks - Phase 2" will be extended until the 31st December 2020. The project has been funded since 2015 by the DFG.

Abstract: Based on the impressive features that network coding and compressed sensing paradigms have brought separately the idea of bringing them together seems obvious. By combining them we can realize low latency communication for largescale sensing scenarios just by reducing the amount of data significantly. Our first phase proposal aimed to break with the agnostic combination of the two key techniques and replace it with a holistic approach for wireless meshed networks. We identified the relevant scenarios and applications in order to design a robust joint encoding/recoding/decoding and compression scheme. Currently we are deploying our joint approach in real-life for industrial IoT-devices for audio and video transmissions. We will deliver a full-fledge demonstrator by the end of the first
phase.
In the second phase of project we would like to continue our research work with novel ideas and concepts in order to achieve low-latency scalability and security for future communication systems. The main goals of phase two are i.) finite field compressed sensing ii.) joint coded computation iii.) adaptive learning strategies for optimal coding/compression decisions per node and iv.) group testing with user
activity detection.
While network coding already operates with finite fields the challenge is to change compressed sensing from real field to finite field computation. We expect that finitefield compressed sensing will overcome the drawback of costly computational complexity which has a direct impact on latency. Furthermore we would like to continue the work in combinatorial group testing and coded computation for user activation and secure wireless distributed storage. In this context we expect that joint network coding and compressed sensing design with our new ideas will enhance tremendously the built-in security and reliability of any future communication system. By bringing in machine learning and in particular learning based on deep neural networks we expect to considerably reduce the latency and complexity for real-time applications.

Duration of the Project: 01st October 2018 until 31st December 2020

## NecSys 2018 - The Paper "Exploiting the Superposition Property of Wireless Communication for Max-Consensus Problems in Multi-Agent Systems" has been ACCEPTED.

Freitag, 06. Juli 2018

The paper 'Exploiting the Superposition Property of Wireless Communication for Max-Consensus Problems in Multi-Agent Systems' which was submitted for inclusion in the program of the 7th IFAC Workshop on Distributed Estimation and Control in Networked Systems (NecSys 2018) has been accepted for presentation at the Workshop and for publication in the official Proceedings, which will be hosted on-line on the IFAC-PapersOnLine website. The 7th IFAC Workshop on Distributed Estimation and Control in Networked Systems will take place in Groningen, the Netherlands, on August 27-28, 2018.

The Authors of the Paper are Fabio Molinari, Slawomir Stanczak, Joerg Raisch

## Asilomar Conference 2018 - the paper "Distributed Machine Learning in the Context of Function Computation over Wireless Networks" has been ACCEPTED.

Donnerstag, 05. Juli 2018

The paper 'Distributed Machine Learning in the Context of Function Computation over Wireless Networks' has been selected for presentation at the 52nd Asilomar Conference on Signals, Systems and Computers, which will be held from October 28, 2018 - October 31, 2018 at the Asilomar Conference Grounds, Pacific Grove, California.

The Authors of the Paper are Miruna Raceala-Motoc, Steffen Limmer, Igor Bjelakovic, Slawomir Stanczak

## Asilomar Conference 2018 - the paper "Low-complexity distributed set-theoretic decoders for analog fountain codes" has been ACCEPTED.

Donnerstag, 05. Juli 2018

The paper 'Low-complexity distributed set-theoretic decoders for analog fountain codes' has been selected for presentation at the 52nd Asilomar Conference on Signals, Systems and Computers, which will be held from October 28, 2018 - October 31, 2018 at the Asilomar Conference Grounds, Pacific Grove, California.

The Authors of the Paper are Dr. Renato G. L. Cavalcante and Prof. Dr. Slawomir Stanczak

## ISWCS 2018 - Paper 'Scalable massive random access in C-RAN with fronthaul limitations' has been ACCEPTED.

Dienstag, 05. Juni 2018

The paper 'Scalable massive random access in C-RAN with fronthaul limitations' submitted to the 15th International Symposium on Wireless Communication Systems (ISWCS) 2018 - SS6 has been accepted for publication and presentation. The ISWCS 2018 will take place in Lisbon, Portugal from 28-31 August 2018.

Authors: Patrick Agostini, Zoran Utkovski, Slawomir Stanczak, Jens Pilz

## EUSIPCO 2018 - Paper 'Extrapolated Projection methods for PAPR Reduction' has been ACCEPTED.

Dienstag, 22. Mai 2018

The paper 'Extrapolated Projection methods for PAPR Reduction' has been ACCEPTED for presentation and publication in the proceedings at 26th European Signal Processing Conference (EUSIPCO 2018) in Rome, Italy, September 3-7.

Authors: Jochen Fink, Renato L.G. Cavalcante, Peter Jung, Slawomir Stanczak

## The Manuscript 'Towards Massive Connectivity Support for Scalable mMTC Communications in 5G networks' has been ACCEPTED.

Mittwoch, 16. Mai 2018

The Manuscript 'Towards Massive Connectivity Support for Scalable mMTC Communications in 5G networks' has been ACCEPTED for publication in the IEEE Access.

Abstract: The fifth generation of cellular communication systems is foreseen to enable a multitude of new applications and use cases with very different requirements. A new 5G multiservice air interface needs to enhance broadband performance as well as provide new levels of reliability, latency and supported number of users. In this paper we focus on the massive Machine Type Communications (mMTC) service within a multi-service air interface. Specifically, we present an overview of different physical and medium access techniques to address the problem of a massive number of access attempts in mMTC and discuss the protocol performance of these solutions in a common evaluation framework.

Authors: C. Bockelmann et al.

Date of Publication: 16 May 2018

Publisher: IEEE

## Invited Talk at TU Berlin: Advances in Information Theory, Coding, and Communications - 04. May 2018 - Berlin, Germany

Mittwoch, 11. April 2018

Matthias Frey, PhD student of the Network Information Theory Group, will be giving a talk on "The MAC Resolvability Region, Semantic Security and Its Operational Implications" at the 31. Plenary of the ITG-Group in Berlin.

Event: 31. Plenary of the ITG-Group for "Applied Information Theory" on the topic "Advances in Information Theory, Coding, and Communications"

Date and time: 04. May 2018, 09:00-17:30

Location: TU Berlin, Room H 3005, Hauptgebäude, 3.OG, Straße des 17. Juni 135, 10623 Berlin

Talk by Matthias Frey from 16:55-17:10 - "The MAC Resolvability Region, Semantic Security and Its Operational Implications"

______________________________

Organized by: ITG-Group University Bremen

## Invited Talk "Machine Learning for 5G and beyond" at ITU: Workshop on "Impact of AI on ICT Infrastructures"

Freitag, 20. April 2018

Prof. Dr.-Ing. habil. Slawomir Stanczak will attend the second meeting of Focus Group on Machine Learning for Future Networks including 5G and the workshop on "Impact of AI on ICT Infrastructures" which will be held in Xi'an, China on 25 April 2018.

Date and time: the second meeting of FG-ML5G will be held on 26.-27. April 2018 and the workshop on 25. April 2018

Location: Xi'an ZTE Hotel, NO.10 Tangyan South Road High Technology District,Xi’an, China

Title of the talk: "Machine Learning for 5G and beyond"- Concerns of the AI Enablers. What are the requirements and obstacles when deploying AI related platforms and Services? Sharing of best practices and Industry experiences.

______________________________

Organized by: This workshop is organized by CAICT in collaboration with ITU

## IEEE ICASSP 2018 - Paper 'FDD massive MIMO channel spatial covariance conversion using projection methods has been ACCEPTED.

Samstag, 31. März 2018

The paper 'FDD massive MIMO channel spatial covariance conversion using projection methods' has been ACCEPTED for presentation at the symposium and for publication in the proceedings at IEEE International Conference on Acoustics, Speech and Signal Processing 2018 in Calgary, Alberta, Canada, April 15-20.

Authors: Lorenzo Miretti and Renato L.G. Cavalcante and Slawomir Stanczak

## IEEE ICASSP 2018 - Paper 'A robust machine learning method for cell-load approximation in wireless networks' has been ACCEPTED.

Samstag, 31. März 2018

The paper 'A robust machine learning method for cell-load approximation in wireless networks' has been ACCEPTED for presentation at the symposium and for publication in the proceedings at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2018 in Calgary, Alberta, Canada, April 15-20.

Authors: Daniyal A. Awan and Renato L.G. Cavalcante and Slawomir Stanczak

Abstract: We propose a learning algorithm for cell-load approximation in wireless networks. The proposed algorithm is robust in the sense that it is designed to cope with the uncertainty arising from a small number of training samples. This scenario is highly relevant in wireless networks where training has to be performed on short time scales because of a fast time-varying communication environment. The first part of this work studies the set of feasible rates and shows that this set is compact. We then prove that the mapping relating a feasible rate vector to the unique fixed point of the non-linear cell-load mapping is monotone and uniformly continuous. Utilizing these properties, we apply an approximation framework that achieves the best worst-case performance. Furthermore, the approximation preserves the monotonicity and continuity properties. Simulations show that the proposed method exhibits better robustness and accuracy for small training sets in comparison with standard approximation techniques for multivariate data.

## IEEE ICC 2018 - Paper 'Detection for 5G-NOMA: An online adaptive machine learning approach.' has been ACCEPTED.

Samstag, 31. März 2018

The paper 'Detection for 5G-NOMA: An online adaptive machine learning approach' has been ACCEPTED for presentation at the symposium and for publication in the proceedings at IEEE International Conference on Communications in Kansas City, MO, USA.

Authors: Daniyal A. Awan and Renato L.G. Cavalcante and Masahiro Yukawa Slawomir Stanczak

Abstract: Non-orthogonal multiple access (NOMA) has emerged as a promising radio access technique for enabling the performance enhancements promised by the fifth-generation (5G) networks in terms of connectivity, low latency, and high spectrum efficiency. In the NOMA uplink, successive interference cancellation (SIC) based detection with device clustering has been suggested. In the case of multiple receive antennas, SIC can be combined with the minimum mean-squared error (MMSE) beamforming. However, there exists a tradeoff between the NOMA cluster size and the incurred SIC error. Larger clusters lead to larger errors but they are desirable from the spectrum efficiency and connectivity point of view. We propose a novel online learning based detection for the NOMA uplink. In particular, we design an online adaptive filter in the sum space of linear and Gaussian reproducing kernel Hilbert spaces (RKHSs). Such a sum space design is robust against variations of a dynamic wireless network that can deteriorate the performance of a purely nonlinear adaptive filter. We demonstrate by simulations that the proposed method outperforms the MMSE-SIC based detection for large cluster sizes.

## IEEE ISIT 2018 - Paper 'Resolvability on Continuous Alphabets' has been ACCEPTED.

Samstag, 31. März 2018

The paper 'Resolvability on Continuous Alphabets' has been ACCEPTED for presentation at the Symposium and for publication in the proceedings at IEEE International Symposium on Information Theory (ISIT) 2018 in Vail, Colorado, USA.

Authors: Matthias Frey and Igor Bjelakovic and Slawomir Stanczak

Abstract: We characterize the resolvability region for a large class of point-to-point channels with continuous alphabets. In our direct result, we prove not only the existence of good resolvability codebooks, but adapt an approach based on the Chernoff-Hoeffding bound to the continuous case showing that the probability of drawing an unsuitable codebook is doubly exponentially small. For the converse part, we show that our previous elementary result carries over to the continuous case easily under some mild continuity assumption.

## Invited Talk at WSIS Forum 19-23 March 2018 - Geneva, Switzerland

Montag, 19. März 2018

Prof. Dr.-Ing. habil. Slawomir Stanczak will be giving a talk on Artificial Intelligence and Machine Learning for 5G at World Summit on the Information Society Forum (WSIS) in Geneva.

Event: WSIS Forum - Leveraging ICTs to Build Information and Knowledge Societies for Achieving the Sustainable Development Goals (SDGs)

Date and time: 19. March 2018

Location: Room M, ITU Montbrillant - Geneva, Switzerland (Webcast)

Title: Machine Learning for 5G

______________________________

Organizer: the Forum is co-organized by ITU, UNESCO, UNDP and UNCTAD

## Invited Talk at ITU: Workshop on "Machine Learning for 5G and beyond"

Montag, 29. Januar 2018

Prof. Dr.-Ing. habil. Slawomir Stanczak attended the workshop on "Machine Learning for 5G and beyond" to discuss requirements, expectations, challenges, research gaps and standardization needs for machine learning for 5G networks.

Date and time: 29. January 2018

Location: ITU Headquarters, Rue de Varembe, 2, Geneva, Switzerland

Title: Machine Learning for 5G and beyond

Workshop Abstract:

This workshop intended to offer a plattform for all involved stakeholders and aimed to discuss requirements, expectations, challenges, research gaps and standardization needs for machine learning for 5G networks.This workshop took place in conjunction with the inagural meeting of the new ITU-T Focus Group on Machine Learning for Future Networks including 5G (FG-ML5G) taking place from 30 January to 2 February 2018 in the same venue.

______________________________

Organized by: International Telecommunication Union (ITU)

## Tutorial at 8th FOKUS FUSECO Forum

Donnerstag, 09. November 2017

Dr. Renato Cavalcante and Prof. Dr.-Ing. habil. Slawomir Stanczak will be giving a tutorial on Machine Learning in 5G Radio Access Networks

Date and time: 9. November 2017

Location: Fraunhofer FOKUS, Kaiserin-Augusta-Allee 31, 10589 Berlin

Title: Machine Learning in 5G Radio Access Networks

Abstract:

1. Overview of machine learning methods for wireless networks
2. Potential applications of machine learning in wireless networks
Wireless computation for efficient machine learning
Efficient learning of sparse stochastic signals in communication systems
Optimal deep neural networks for sparse recovery
Projection methods in communication systems
Consensus algorithms
Kernel machines
Applications (e.g., radio maps in wireless networks)
Beyond projections

______________________________

Organizer: Prof. Dr. Thomas Magedanz

## Invited Talk at MIT - NSF Workshop on low-latency wireless random-access

Donnerstag, 02. November 2017

Prof. Dr.-Ing. habil. Slawomir Stanczak will be giving a talk at the NSF Workshop on low-latency wireless random-access.

Date and time: 2.-3. November 2017

Location: Massachusetts Institute of Technology (MIT), Grier Room, 34-401 (A & B), 50 Vassar Street, Cambridge, MA, 02139

Title: Harnessing Channel Collisions for Enabling Low-Latency Wireless Random Access: From Theory to Practice

Workshop Abstract:

This workshop brings together experts from industry and academia to discuss the challenges and solutionsfor the problem of multiple-access in wireless communication and Internet-of-Things. Current radio-access networks (RANs) are designed with the aim of maximizing data-stream throughput for a few active users. The next generation RANs will need to service massive numbers of infrequently communicating sensors (machine-type communication, MTC, or Internet-of-Things). Most present systems employ centralized resource allocation, thus orthogonalizing the access from different users. This solution is not acceptable for the MTC as it relies on a significant control-layer overhead and incurs severe latency. Presently, there is a strong demand for a new solution in both the unlicensed spectrum [low-power wide-area networks (LP-WANs)] and the licensed spectrum (5G). While the problem of multiple-access (MAC) is classic and a number of well-established solutions exist, the massive machine-type communications pose significant new challenges: (a) a gigantic number of idle (inactive) users; (b) a still large number (hundreds) of active users; (c) short packets; (d) focus on high energy-efficiency (low energy-per-bit). Consequently, the efficiency of the currently available solutions should be contrasted with the fundamental non-asymptotic fundamental limits and new solutions developed. Furthermore, the typical assumption of vanishing overhead of headers (control layers) in network analytic literature, and unbounded blocklength assumption in information theory evidently become grossly inadequate. As another example, the classical information-theoretic model of a K-user MAC fails to capture the random-access nature of the real-world applications, while network-theoretic collision models fail to capture the superposition nature of the real-world physics.

______________________________

Organizer: Yury Polyanskiy
Program committee: Yury Polyanskiy and Sergio Verdú

## Invited Talk at "Nokia Lectures: Maschinen entscheiden – Fortschritte beim maschinellen Lernen"

Dienstag, 24. Oktober 2017

Prof. Dr.-Ing. habil. Slawomir Stanczak will be giving a talk at "Nokia Lectures: Maschinen entscheiden – Fortschritte beim maschinellen Lernen"

Date: 24. Oktober 2017

Location: Universität Stuttgart, Campus Vaihingen

Title of the Talk: Machine Learning and Mobile Communications: A (Mis)match made in Heaven?

______________________________

Organizer:
Alcatel-Lucent Stiftung für Kommunikationsforschung, Stuttgart
Fakultät Informatik, Elektrotechnik und Informationstechnik, Universität Stuttgart
Internationales Zentrum für Kultur- und Technikforschung, Universität Stuttgart

## [IEEE CNS 2017 PLMWS] Paper MAC Resolvability: First And Second Order Results' has been ACCEPTED.

Donnerstag, 03. August 2017

The paper MAC Resolvability: First And Second Order Results' has been ACCEPTED to the 4th Workshop on Physical-Layer Methods for Wireless Security to be held at IEEE CNS 2017 in Las Vegas, NV.

## GlobalSIP 2017 Paper Submission Confirmation: 1366

Freitag, 04. August 2017

Note: The filename shown above has been modified from your original upload in order to ensure a unique filename. This file supercedes all previously uploaded files.

Remember to submit a signed e-copyright transfer form before the submission deadline. We are required to collect copyright forms before papers can be sent to reviewers. If the paper is not accepted into the technical program, the form becomes null and void.

Your uploaded file will now be inspected to ensure compliance with the formatting guidelines in the Paper Kit. Please allow 7-10 days from the official submission deadline for paper inspection to be completed. You will be notified by email if any problems are found with your submission.

You may revise your submission until the paper submission deadline date at:
https://2017.ieeeglobalsip.org//Papers/FindPaper.asp

Submission Timestamp: 8/4/2017 6:21:38 AM

Thank you for participating in GlobalSIP 2017.

## Coordinated User Scheduling and Spectrum Sharing: A Fractional Programming Approach

Dienstag, 22. November 2016

Abstract:

Interference management is a key challenge for both cellular and device-to-device (D2D) communication networks, in which multiple transmitter and receiver pairs may arbitrarily interfere with each other with full frequency reuse. In this talk, we introduce a distributed spectrum sharing strategy called FPLinQ to alleviate inter-link interference by coordinating link schedule decisions throughout the network. Scheduling in the general setting is a challenging combinatorial optimization problem. In this talk, we devise a fractional programming (FP) approach to derive a reformulation whereby the integer variables are determined analytically in each iterative step. The resulting FPLinQ algorithm enables an iterative and distributed optimization of link schedule with provable convergence. The proposed strategy can be extended to include joint link scheduling and power control. The proposed strategy can further be used for interference aware uplink scheduling and beamforming in cellular networks. As compared to the existing works such as FlashLinQ, ITLinQ and ITLinQ+, a main advantage of the proposed strategy is that it does not require tuning of design parameters; it further shows significant performance advantage as compared to the benchmarks in maximizing the sum rate and the network utility.

## Michael Peter successfully defended his PhD thesis 'Measurement, Characterization and Modeling of Millimeter-Wave Channels: From 60 GHz to 5G'

Dienstag, 18. Juli 2017

Michael Peter successfully defended his PhD thesis 'Measurement, Characterization and Modeling of Millimeter-Wave Channels: From 60 GHz to 5G' on July 18, 2017. Reviewers have been Prof. Dr.-Ing. Stanczak (TU Berlin), Prof. Dr.-Ing. Kürner (Technische Universität Braunschweig) and Prof. Salous, Ph.D. (Durham University, UK). The evaluation committee was chaired by Prof. Caire, Ph.D.

## Measurement, Characterization and Modeling of Millimeter-Wave Channels: From 60 GHz to 5G

Dienstag, 18. Juli 2017

Wissenschaftliche Aussprache von

Herrn Dipl.-Ing. Michael Peter

Dienstag, 18. Juli 2017 um 14:00 Uhr

Im Sitzungsraum der Fakultät IV

Raum MAR 6.004 – Marchstraße 23 in 10587 Berlin

(Dr.-Ing.)

Der Titel der Dissertation lautet:

Measurement, Characterization and Modeling of Millimeter-Wave Channels: From 60 GHz to 5G

Der Promotionsausschuss setzt sich wie folgt zusammen:

Vorsitz:            Prof. Caire, Ph.D.

Gutachter:        Prof. Dr.-Ing. Stanczak

Prof. Dr.-Ing. Kürner (Technische Universität Braunschweig)

Prof. Salous, Ph.D. (Durham University, UK)

## GlobalSIP 2017 Review Results for paper #1366

Montag, 17. Juli 2017

Paper ID: 1366
Title: 'The role of asymptotic functions in network optimization and feasibility studies'
Submitted to 2017 IEEE GlobalSIP Symposium on Distributed Optimization and Resource Management over Networks

The 2017 IEEE GlobalSIP Symposium on Distributed Optimization and Resource Management over Networks has completed the review process and we are pleased to inform you that the manuscript listed above has been ACCEPTED for presentation in a session at the conference. Congratulations! All papers are to be presented either orally or as posters. The Technical Program Committee for the Symposium on Distributed Optimization and Resource Management over Networks carefully selected reviewers for GlobalSIP 2017 and assigned reviewers papers in their areas of expertise.  Every paper received at least two reviews.

## IEEE Technical Seminar by Slawomir Stanczak

Freitag, 02. Juni 2017

Prof. Dr.-Ing. habil. Slawomir Stanczak will be giving an IEEE Technical Seminar for the IEEE joint VT/COM/IT Sweden Chapter Board. The slides can be found here.

Date and time: 2017-JUNE-02 14.30

Location: Address: Isafjordsgatan 14E, 164 80 Stockholm (Kista) – Ericsson Building 04,

Floor 1 (Ground floor) Titan (Official Room Number: SE KI 04 01 350 Titan)

(Please see a link to a map below), the building is marked as “04”)

TitleTowards Efficient and Robust Machine Learning in Wireless Communication Systems

Abstract:

In the first part of the talk we address the problem of  anomaly detection in wireless networks. Here „anomaly“ is to be understood as a significant deviation of a system state that is observed from the normal state which in general needs to be learned and tracked. Anomaly detection has numerous applications including fault detection, jamming detection and condition monitoring. This talk presents a general framework for online anomaly detection in wireless sensor networks based on projection methods and consensus algorithms. This includes our recent results on classification for anomaly detection by exploiting the broadcast property of the wireless channel. The second part of the talk deals with the problem of efficient nonlinear estimation of sparse stochastic signals in communication systems. In contrast to Gaussian models, sparse stochastic processes contain significant information in higher-order moments that must be assessed and considered for efficient algorithms in next generation communication systems. These algorithms must exploit sparse and low-rank structures arising e.g. due to physical propagation effects of multiple-antenna transmission at higher frequencies. In this talk, we introduce a model of sparse stochastic signals using distributions over lp-balls, that allows for a unified quantification of necessary higher-order statistics. To obtain real-time capable estimation algorithms for next generation wireless systems, we propose a class of neural-network inspired estimators that are magnitudes less complex than general iterative and convex optimization alternatives. By quantifying precisely the resulting estimation error, novel points at the performance/complexity frontier may be found.

Biography:

Prof. Dr.-Ing. habil. Slawomir Stanczak studied control theory at the Wroclaw University of Technology, Wroclaw, Poland, and at the Technical University of Berlin (TU Berlin), Berlin, Germany, where he received the Dipl.-Ing. degree and the Dr.-Ing. degree (summa cum laude) in electrical engineering in 1998 and 2003, respectively; the Habilitation degree (venialegendi) followed in 2006. Since 2015, he has been a Full Professor for network information theory with TU Berlin and the head of the Wireless Communications and Networks department. Prof. Stanczak has been involved in research and development activities in wireless communications since 1997. In 2004 and 2007, he was a Visiting Professor with RWTH Aachen University, Aachen, Germany, and in 2008, he was a Visiting Scientist with Stanford University, Stanford, CA, USA. He is a co-author of two books and more than 200 peer-reviewed journal articles and conference papers in the area of information theory and wireless communications and networking. Prof. Stanczak received research fellowships from the German Research Foundation and the Best Paper Award from the German Communication Engineering Society in 2014. He was a Co-chair of the 14th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC 2013). Between 2009 and 2011, he was an Associate Editor of the European Transactions for Telecommunications (information theory) and an Associate Editor of the IEEE Transactions on Signal Processing between 2012 and 2015.

Link to map of Ericsson in Kista, Building 04, Isafjordsgatan 14E:

## ITG Keynote Talk by Slawomir Stanczak

Donnerstag, 11. Mai 2017

Prof. Dr.-Ing. habil. Slawomir Stanczak will be giving a Keynote Talk at 18. ITG-Fachtagung
„Photonische Netze“.

Date and time: 11. May 2017, 10:40

Location: 18. ITG-Fachtagung „Photonische Netze“, Leipzig

Title: 5G Research: Objectives, Challenges and Current Trends

## Qi Liao successfully defended her PhD thesis 'Statistical Learning, Anomaly Detection, and Optimization in Self-Organizing Networks'

Montag, 21. November 2016

Qi Liao successfully defended her PhD thesis 'Statistical Learning, Anomaly Detection, and Optimization in Self-Organizing Networks' on November 21, 2016. Reviewers have been Prof. Dr.-Ing. Stanczak (TU Berlin), Prof. Yu, Ph.D. (University of Toronto, Kanada), Prof. Dr.-Ing. Kürner (TU Braunschweig) and Prof. Dr.-Ing. Giovanidis (Telecom ParisTech, Frankreich). The evaluation committee was chaired by Prof. Caire, Ph.D.

## Kim Mahler successfully defended his PhD thesis 'Wideband Propagation Channel in Vehicular Communication Scenarios'

Montag, 10. Oktober 2016

Kim Mahler successfully defended his PhD thesis 'Wideband Propagation Channel in Vehicular Communication Scenarios' on October 10, 2016. Reviewers have been Prof. Caire, Ph.D. (TU Berlin), Prof. Dr. Oestges (Ecole Polytechnique de Louvain, Belgien), Prof. Dr. Tufvesson (Lund University, Schweden) and PD Dr. Zemen (AIT Vienna, Österreich). The evaluation committee was chaired by Prof. Dr.-Ing. Stanczak.

## Richard Weiler successfully defended his PhD thesis 'Channel Investigation of Outdoor Millimeter-Wave Access Links'

Montag, 26. September 2016

Richard Weiler successfully defended his PhD thesis 'Channel Investigation of Outdoor Millimeter-Wave Access Links' on September 26, 2016. Reviewers have been Prof. Dr.-Ing. Stanczak (TU Berlin), Prof. Dr. Maltsev (Labochevsky State University of Nizhny Novgorod, Russland) and Prof. Dr. Ando (Tokyo Institute of Technology, Japan). The evaluation committee was chaired by Prof. Caire, Ph.D.

## Jafar Mohammadi successfully defended his PhD thesis 'Security by Similarity: Information-theoretic Secrecy and Decentralized Anomaly Detection for Wireless Networks'

Freitag, 12. August 2016

Jafar Mohammadi successfully defended his PhD thesis 'Security by Similarity: Information-theoretic Secrecy and Decentralized Anomaly Detection for Wireless Networks' on August 12, 2016. Reviewers have been Prof. Dr.-Ing. Stanczak (TU Berlin), Prof. Kiyavash, Ph.D. (University of Illinois, USA) and Prof. Dr.-Ing. Oechtering (KTH Stockholm, Sweden). The evaluation committee was chaired by Prof. Caire, Ph.D.

## Mario Goldenbaum received the Vodafone Förderpreis 2016

Mario Goldenbaum received the Vodafone Förderpreis 2016 for his work on efficient data transmission over the wireless channel. From 2010 to 2015, he was a Research and Teaching Assistant at the Fachgebiet für Informationstheorie und theoretische Informationstechnik and later at the Fachgebiet for Network Information Theory. Since October 2015, he is a Postdoctoral Research Fellow in the Department of Electrical Engineering at Princeton University. His doctoral thesis was entitlted "Computation of Real-Valued Functions Over the Channel in Wireless Sensor Networks".

## Zhe Ren successfully defended his PhD thesis 'Energy Savings in 5G Automotive Nomadic Relaying Networks'

Freitag, 01. April 2016

Zhe Ren successfully defended his PhD thesis 'Energy Savings in 5G Automotive Nomadic Relaying Networks' on April 1, 2016. Reviewers have been Prof. Dr.-Ing. Stanczak (TU Berlin), Prof. Dr. Popovski (University of Aalbord, Denmark) and PD Dr.-Ing Wunder. The evaluation committee was chaired by Prof. Caire, Ph.D.

## Martin Kasparick successfully defended his PhD thesis 'Towards Self-Organizing Wireless Networks: Adaptive Learning, Resource Allocation, and Network Control'

Montag, 21. Dezember 2015

Martin Kasparick successfully defended his PhD thesis 'Towards Self-Organizing Wireless Networks: Adaptive Learning, Resource Allocation, and Network Control' on December 21, 2015. Reviewers have been Prof. Dr.-Ing. Stanczak (TU Berlin), Prof. Dr. Mathar (RWTH Aachen) and PD Dr.-Ing. Wunder. The evaluation committee was chaired by Prof. Anja Feldmann, Ph.D.