Compressive Sensing for Biomedical Applications: Is this a Hammer Looking for Nails?

Abstract: Compressive Sensing (CS) has emerged in the last two decades as a transformative technique capable of revolutionizing the way data is acquired, processed, and reconstructed. CS exploits the inherent sparsity or compressibility of signals, allowing accurate reconstruction from a small number of non-traditional measurements. This principle is particularly relevant in the biomedical field, where acquiring high-quality data can be resource-intensive and time-consuming. To apply CS, the signals must be acquired in an incoherent way with respect to the sparsity basis, which is classically obtained in practice by acquiring the signal through projection on a random PAM signal with i.i.d. symbols. Performance improvement, in terms of acquisition time/energy reduction, has been obtained using several optimizations directions. This exploits the fact that, while sparsity is not under a system designer’s control, incoherence is. Hence when signals are localized (i.e they preferentially occupy a given subspace, as it is for biosignals) acquisition sequences can be statistically designed to maximize their capability to collect the energy of the samples during the acquisition with the goal of either improving reconstruction accuracy or further compressing the data. The design of innovative acquisition systems is another important aspect of this field: several architecture for CS based systems have been proposed starting from general purpose implementation of Analog-to-Information Converters for signal acquisition from biosensors, to the design of CS-based MRI systems with faster imaging acquisition. In addition, the development of advanced (also Deep Neural Network Based) decoders has also been investigated to improve the reconstruction quality from the compressed measurements. Aim is this talk is give first an overview of all the elements presented above and to determine which of them have truly caused a breakthrough in the respective area of application, arriving also to commercial products. We will also highlight areas in which this has not been the case, and try understand why the initial promises have not been maintained, especially in terms of ultra-low-power acquisition. Finally, we will show other less known characteristics of CS, such as its ability to eliminate the necessity for pre- or post-acquisition filtering stages or its ability to guarantee some level of privacy in information transmission, which makes the CS signal acquisition paradigm more suitable for applications in the area of biosignal acquisition. Biography: Gianluca Setti received a Dr. Eng. degree (honors) and a Ph.D. degree in Electronic Engineering from the University of Bologna, in 1992 and in 1997. From 1997 to 2017 he was with the Department of Engineering, University of Ferrara, Italy, as an Assistant- (1998-2000), Associate- (2001-2008) and as a Professor (2009-2017) of Circuit Theory and Analog Electronics. From 2017 to 2022, he was Professor of Electronics, Signal and Data Processing at the Department of Electronics and Telecommunications (DET) of Politecnico di Torino, Italy. He is currently Dean of the Computer, Electrical, Mathematical Science and Engineering at KAUST, Saudi Arabia, where is also a Professor of Electrical and Computer Engineering. Dr. Setti has held various visiting positions, most recently at the University of Washington, at IBM T. J. Watson Laboratories, and at EPFL (Lausanne). His research interests include nonlinear circuits, recurrent neural networks, statistical signal processing, electromagnetic compatibility, compressive sensing and statistical signal processing, biomedical circuits and systems, power electronics, design and implementation of IoT nodes, circuits and systems for machine learning. He is the recipient of numerous awards, including the 2004 IEEE Circuits and Systems (CAS) Society Darlington Award, the 2013 IEEE CASS Guellemin-Cauer Award, the 2013 IEEE CASS Meritorious Service Award and the 2019 IEEE Transactions on Biomedical Circuits and Systems Best Paper Award. He was a Distinguished Lecturer of the IEEE CAS Society (2004-2005 and 2013-2014) of the same Society, a member of the CASS Board of Governors (2005-2008), and served as the 2010 CAS Society President, as well as the 2018 General Chair of the IEEE International Symposium on Circuits and Systems (ISCAS) in Florence, Italy. In 2012, he was the Chair of the IEEE Strategic Planning Committee of the Publication Services and Products Board (PSPB-SPC) and in 2013-2014 he was the first non North-American Vice President of the IEEE for Publication Services and Products. He is currently serving as the Editor-in-chief of the Proceedings of the IEEE.