Content Gazette - May 2017 - 24

CALL FOR PAPERS
IEEE Journal of Selected Topics in Signal Processing: Special Issue on
Machine Learning for Cognition in Radio Communications and Radar (ML-CR 2 )
While machine learning is achieving ground breaking success in speech recognition, computer vision, natural language processing and business
analytics, its impact on radio communications, and on the associated problem area in signal processing, has been less pronounced mainly due to
the lack of 'big data' and big applications. However, in the era of the Fifth Generation (5G) cellular systems and Internet-of-Things (IoT), some
significant changes are under way. For example, as 5G cellular systems demand huge capacity, massive connectivity, high reliability and low
latency, acquiring adequate resources to operate such systems is difficult and novel models and algorithms are needed to help improve spectrum
utilization by leveraging large-scale databases, full of context and information. These databases can be sourced from handheld devices, network
infrastructure, and the environment, such as typical user trajectories provided by vehicular traffic management systems. In addition, government
agencies are now willing to share their spectrum with commercial users. The 3550-3650 MHz band is identified for spectrum sharing between
military radars and communication systems. This requires cognition both in communication systems and radars. There is also a general trend
toward cognitive radars as the next generation of environment-adaptive radars with unprecedented spectral and behavioral agility. A natural
approach to handling all this is the development of efficient machine learning algorithms, which, combined with traditional signal processing
methods, will allow for the automation of cognitive functionality both in radars and radio communication networks. There are nontrivial challenges
and open questions in the application of machine learning to RF environments starting with the fact that, as opposed to speech recognition and
computer vision where the output of machine cognition can be readily compared and verified against human auditory and visual perception, no
such option is available for radio signals. The main goal of this Special Issue is to raise awareness of this emerging interdisciplinary research area,
and to showcase the existing state-of-the-art and its current and future challenges. Topics of interest include (but are not limited to):
- Machine learning for blind channel and signal
characterization
- Machine learning for source separation
- Deep learning for RF signal classification
- Machine learning for channel decoding
- Machine learning for RF-based geolocation and signal
association
- Distributed multi-agent learning in collaborative radio
networks
- Machine learning-based antenna selection

- Joint optimization and learning of spectrum usage dynamics and
spectrum access control
- Privacy-preserving machine learning for cognitive radio
- Machine learning for cognitive technologies in 5G cellular networks
- Non-parametric Bayesian machine learning for temporal clustering
of spectral activity
- Machine learning for activity recognition of partially observable
wireless network nodes
- Machine learning in cognitive radars for spectrum sharing with
communication devices
- Machine learning for passive radars

- Reinforcement Learning in wireless networks
- Machine learning of the topology and structural
properties of radio networks

- Machine learning for Bayesian target characterization
- Machine learning for cognitive radar characterization and for radar
waveform design

Prospective authors should follow the instructions given on the IEEE JSTSP webpages:

https://signalprocessingsociety.org/publications-resources/ieee-journal-selected-topics-signal-processing and submit their
manuscript with the web submission system at: https://mc.manuscriptcentral.com/jstsp-ieee.
Dates:

Guest Editors (ge.ml.crcr@gmail.com):

Manuscript submission: June 30, 2017

Maria Sabrina Greco, University of Pisa

First review completed: August 15, 2017

Silvija Kokalj-Filipovic, U.S. Naval Research Laboratory

Revised Manuscript Due: September 15, 2017

H. Vincent Poor, Princeton University

Second Review Completed: October 31, 2017

George Stantchev, U. S. Naval Research Laboratory

Final Manuscript Due: December 15, 2017

Liang Xiao, Xiamen University

Publication: February 2018

www.signalprocessingsociety.org

[24]

MAY 2017
https://www.signalprocessingsociety.org/publications-resources/ieee-journal-selected-topics-signal-processing https://mc.manuscriptcentral.com/jstsp-ieee http://www.signalprocessingsociety.org
Table of Contents for the Digital Edition of Content Gazette - May 2017
