GlobalSIP 2017:

Symposium on Signal Processing & Machine Learning in Large Medical Datasets

[Download the PDF Call for Papers]

IEEE GlobalSIP 2017 Symposium on signal processing and machine learning in large medical datasets will focus on advances in signal processing and machine learning methods with applications involving large medical datasets acquired for clinical decision support. Today, a huge amount of medical data is being generated from different modalities including imaging modalities (e.g., magnetic resonance imaging, ultrasound) and other signal acquisition modalities for acquiring physiological signals. To make and support an accurate clinical decision, one typically needs a variety of signal processing and machine learning algorithms to pre-process and classify such data. This symposium is aimed at addressing these two broad issues.

Distinguished Symposium Talk

Tiago H. Falk

Institut National de la Recherche Scientifique (INRS)

Is signal processing still important in the era of (deep) learning of big biomedical data?

Abstract:
Over the last decade, the (re)emergence of deep learning and deep neural networks has revolutionized fields, such as, computer vision, speech recognition and natural language processing. A great part of this success has been due to increased computational power, access to (cheap) abundant (labeled) data, and some key enabling algorithmic innovations, such as dropout. Within the biomedical field, however, advances in "deep" applications have been more modest, perhaps due to the high cost in obtaining large amounts of human biomedical data, the importance of expert domain knowledge for e.g., diagnostics, patient privacy, and the quality of data being collected by anyone at anytime, anywhere (after all, bigger data is not always better data). In fact, recent concerns raised over so-called adversarial sample attacks on deep neural networks may further hamper progress within the field. In this talk, I will try to convince you that signal processing still plays a crucial role in big biomedical data analytics and show examples in which signal processing and machine learning can come together to help advance the field.

Biography
Prof. Tiago H. Falk received the BSc degree from the Federal University of Pernambuco, Brazil, in 2002, and the MSc and PhD degrees from Queen’s University, Canada, in 2005 and 2008, respectively, all in electrical engineering. In 2007, he was a visiting Research Fellow at the Sound and Image Processing Lab, Royal Institute of Technology (KTH), Sweden, and in 2008 at the Quality and Usability Lab, Deutsche Telekom/TU Berlin, Germany. From 2009-2010 he was an NSERC Postdoctoral Fellow at Holland-Bloorview Kids Rehabilitation Hospital, affiliated with the University of Toronto. He joined the Institut National de la Recherche Scientifique (INRS) in Montreal, Canada in Dec. 2010 and is now an Associate Professor and Director of the Multimedia/Multimodal Signal Analysis and Enhancement (MuSAE) Laboratory.

Prof. Falk is a Senior Member of the IEEE, an elected member of the Global Young Academy (GYA), a member of the Sigma Xi Research Society, and Academic Chair of the Canadian Biomedical and Biological Engineering Society (CMBES). His research interests lie at the crossroads of telecommunications and biomedical engineering with particular focus on the development of affective human-machine interfaces and anthropomorphic, human-inspired technologies. Together with his research team, he has published over 190 journal and conference papers, book chapters and patents in these domains, including an upcoming edited book on signal processing and machine learning for big biomedical data. Prof. Falk's work has resulted in numerous awards, most recently the EURASIP Best Paper Award (Speech Communication, 2017), the Sigma Xi Young Investigator Award (2016), the Prix Rayonnement Bell (2015), and the CMBES Early Career Achievement Award (2015).

Schedule

Submissions are welcome on topics including:

• Big data approaches to physiological datasets
• Machine learning algorithms for data mining patient charts
• Multimodal neuroimaging data analysis and fusion
• Dynamic and non-linear time-series analysis
• Statistical inference, dictionary learning, sparse recovery, blind source separation methods applied to large medical datasets
• Advanced machine learning approaches to brain data analysis including network building, parcellation, and brain state decoding
• Statistical machine learning
• Medical data analysis using signal processing on graphs
• Distributed signal processing on networks/graphs in medical data
• Structured data recovery, e.g., sparse + low-rank matrix factorization, robust PCA, compressive sensing, structured sparsity
• Higher order data analysis, e.g. tensor-based approaches to medical data analysis
• Functional/effective connectivity of evolving networks in medical imaging data
• Anatomical imaging and structural connectivity

Paper Submission

Prospective authors are invited to submit full-length papers (up to 4 pages for technical content, an optional 5th page containing only references) and extended abstracts (up to 2 pages, for paperless industry presentations and Ongoing Work presentations). Manuscripts should be original (not submitted/published anywhere else) and written in accordance with the standard IEEE double-column paper template. Accepted full-length papers will be indexed on IEEE Xplore. Accepted abstracts will not be indexed in IEEE Xplore, however the abstracts and/or the presentations will be included in the IEEE SPS SigPort. Accepted papers and abstracts will be scheduled in lecture and poster sessions. Submission is through the GlobalSIP website at http://2017.ieeeglobalsip.org/Papers.asp.

Notice: The IEEE Signal Processing Society enforces a “no-show” policy. Any accepted paper included in the final program is expected to have at least one author or qualified proxy attend and present the paper at the conference. Authors of the accepted papers included in the final program who do not attend the conference will be subscribed to a “No-Show List”, compiled by the Society. The “no-show” papers will not be published by IEEE on IEEEXplore or other public access forums, but these papers will be distributed as part of the on-site electronic proceedings and the copyright of these papers will belong to the IEEE.

Organizing Committee

General Co-Chairs

Ervin Sejdić, University of Pittsburgh
Murat Akcakaya, University of Pittsburgh

Technical Co-Chairs

Sarah Ostadabbas, Northeastern University
Alessio Medda, Georgia Tech