IEEE JSTSP Special Issue on Learning-Based Signal Processing for Integrated Sensing and Communications

Manuscript Due: 10 July 2023
Publication Date: May 2024

Learning theory has seen success in speech recognition, computer vision, natural language processing and business analytics. Lately, learning and data-driven approaches are increasingly considered as key enablers for next-generation intelligent communications and radar systems. For example, to manage the design complexities, capacity, connectivity, and reliability of next-generation wireless communications, novel design methodologies are moving beyond the causal model-based signal processing to use learning paradigms leveraging on large-scale databases, full of context and information. A similar trend in seen in radar where applications of machine learning are no longer limited to merely target classification but increasingly applied to other aspects of radar design and signal processing. In this context, the recent integrated sensing and communications (ISAC) paradigm. which offers an integrated solution to spectrum sharing between the radar and communications while meeting the individual requirements, has emerged as an active applied area for learning theory and techniques. An integrated approach renders the ISAC design even more difficult because it incorporates different requirements and technical nuances of both systems. Further, rapid growth in ISAC applications brings forward an inevitable need for more intelligent processing, operation, and optimization of future systems. To realize this vision of intelligent processing and operation, there is a need to integrate learning techniques into the design, management, and optimization of ISAC systems. Modern learning techniques provide several opportunities to enable intelligent ISAC designs while addressing various problems ranging from signal processing, detection, classification, and recovery to spectrum access, channel modeling, security, resource management, waveform selection/design, deployment in new scenarios, and application/user behavior analysis. Sensing the fast-paced development of ISAC and the imminent design issues for large scaled systems, this Special Issue aims to offer the audience of IEEE Journal of Selected Topic in Signal Processing a compendium of latest research articles on application of learning-based signal processing for ISAC systems, hitherto not made available. Topics of interest include but are not limited to: 

• Learning for ISAC waveform design, channel estimation, receive processing
• New learning paradigms for ISAC: deep, adversarial, tensorial, dropout, transfer learning
• Learning for spectrum access, control, and optimization
• Cognition, inverse cognition, metacognition for ISAC
• Learning for distributed, collaborative, and multi-agent ISAC
• Reinforcement learning applications for ISAC, including resource allocation
• Bandit algorithms for ISAC Quickest change detection for ISAC
• Game theoretic approaches for ISAC ISAC applications of generative models
• Learning for ISAC signal classification, retrieval, and decoding
• Novel optimization applications, including stochastic optimization, to facilitate learning in ISAC
• Unfolding/unrolling, hybrid model-free and model-based learning for ISAC applications
• Graph neural networks for ISAC applications
• Active sensing for ISAC
• Hardware-algorithm co-design for ISAC

In addition to technical research results, we invite high-quality submissions of a tutorial or overview nature; we also welcome creative papers outside the areas listed here but related to the overall scope of the special issue. Prospective authors can contact the Guest Editors to ascertain interest on topics that are not listed and should visit JSTSP page for information on paper submission. Manuscripts should be submitted using the Manuscript Central system and will be peer-reviewed according to the standard IEEE process.

Important Dates

• Submissions Due: July 10, 2023 (Extended)
• First Review: 1 November 2023
• Revised Manuscript: 1 December 2023
• Second Review: 1 February 2024
• Final Decision: 1 March 2024
• Publication Date: May 2024

Guest Editors

• Kumar Vijay Mishra (Lead Editor), Army Research Laboratory, USA
• M. R. Bhavani Shankar, University of Luxembourg
• Nuria González-Prelcic, North Carolina State University, USA
• Mikko Valkama, Tampere University, Finland
• Wei Yu, University of Toronto, Canada
• Björn Ottersten, KTH Sweden