Multi-Source Domain Adaptation and Its Application to Early Detection of Fatigue¶
Jieping Ye
Associate Professor
Arizona State University
Abstract:
We consider the characterization of muscle fatigue through noninvasive sensing mechanism such as surface electromyography (SEMG). One major challenge in the modeling and classification of SEMG signals lies in the variation in SEMG parameters from subject to subject which creates differences in the data distribution. In this talk, we present a transfer learning framework based on the multi-source domain adaptation methodology for detecting different stages of fatigue using SEMG signals, that addresses the distribution differences. In the proposed framework, the SEMG data of a subject represent a domain; data from multiple subjects in the training set form the multiple source domains and the test subject data form the target domain. SEMG signals are predominantly different in conditional probability distribution across subjects. The key feature of the proposed framework is a novel weighing scheme that addresses the conditional probability distribution differences across multiple domains (subjects). Finally, we present an extension based on a two-stage weighting framework and provide a theoretical analysis on the generalization performance using the weighted Rademacher complexity measure.
Bio:
Jieping Ye is an Associate Professor of the Department of Computer Science and Engineering at Arizona State University. He received his Ph.D. in Computer Science from University of Minnesota, Twin Cities in 2005. His research interests include machine learning, data mining, and biomedical informatics. He won the outstanding student paper award at ICML in 2004, the SCI Young Investigator of the Year Award at ASU in 2007, the SCI Researcher of the Year Award at ASU in 2009, the NSF CAREER Award in 2010, the KDD best research paper award honorable mention in 2010, and the KDD best research paper nomination in 2011.