When & Where
- Tuesday, Oct. 25, 2016
- 10:30 a.m.
- 105 EEB
Keshab K. Parhi
Dept. of Electrical & Computer Engineering
University of Minnesota, Minneapolis
“Brain, Biomedical, and Biomolecular Informatics: Convergence of Signal Processing, Machine Learning and Computing”
Abstract: I will describe ongoing interdisciplinary research in my group at the boundaries of neurology, neuroscience and psychiatry using established and emerging theory from the fields of signal processing and machine learning that can not only help us in discovery of biomarkers for neuropsychiatric disorders, such as epilepsy, schizophrenia, borderline personality disorder and obsessive compulsive disorder, from different imaging modalities such as electroencephalogram, magnetoencephalogram and functional magnetic resonance imaging, but also expand our understanding of the functioning of the human brain. I will describe applications of machine learning in ophthalmology to grade the severity of diabetic retinopathy from fundus images and to segment cysts in optical coherence tomography images. I will then address some aspects of energy-efficient architecture design for computing systems for these physical systems. I will describe some approaches to reducing energy consumption in feature selection, feature extraction and machine learning classifiers. I will conclude the talk with emerging biomolecular computing paradigms for computing signal processing and machine learning functions using DNA followed by future research directions on these topics.
Bio: Keshab K. Parhi received the B.Tech. degree from the Indian Institute of Technology (IIT), Kharagpur, in 1982, the M.S.E.E. degree from the University of Pennsylvania, Philadelphia, in 1984, and the Ph.D. degree from the University of California, Berkeley, in 1988. He has been with the University of Minnesota, Minneapolis, since 1988, where he is currently Distinguished McKnight University Professor and Edgar F. Johnson Professor in the Department of Electrical and Computer Engineering. He has published 600 papers, is inventor of 29 patents, and has authored the textbook VLSI Digital Signal Processing Systems (Wiley, 1999). Dr. Parhi is widely recognized for his work on high-level transformations of iterative data-flow computations, for developing a formal theory of computing for design of digital signal processing systems, and for his contributions to multi-gigabit Ethernet systems on copper and fiber and for backplanes. His current research addresses VLSI architecture design of signal processing, communications and biomedical systems, stochastic computing, hardware security, and molecular computing. He is also currently working on intelligent classification of biomedical signals and images, for applications such as seizure prediction and detection, schizophrenia classification, biomarkers for mental disorders, brain connectivity, and diabetic retinopathy screening. Dr. Parhi is the recipient of numerous awards including the 2012 Charles A. Desoer Technical Achievement award from the IEEE Circuits and Systems Society, the 2004 F. E. Terman award from the American Society of Engineering Education, the 2003 IEEE Kiyo Tomiyasu Technical Field Award, the 2001 IEEE W. R. G. Baker prize paper award, and a Golden Jubilee medal from the IEEE Circuits and Systems Society in 2000. He was elected a Fellow of IEEE in 1996. He served as the Editor-in-Chief of the IEEE Trans. Circuits and Systems, Part I during 2004-2005 and as an elected member of the Board of Governors of the IEEE Circuits and Systems society from 2005 to 2007.