Smoothing of Spatial Patterns of EEG by Graph Spectral AnalysisDate: 2015-05-13 Add to Google Calendar
Time: 4:30pm - 5:30pm
Location: Holmes Hall 389
Speaker: Prof. Toshihisa Tanaka, Tokyo University of Agriculture and Technology (TUAT)
Spatial filtering is useful for extracting features from multichannel electroencephalography (EEG) recordings. In order to enhance robustness of the spatial filter against low SNR and a small sample set, this talk introduces a smoothing method for the spatial filter using spectral graph theory. This method is based on an assumption that the electrodes installed in nearby locations observe the electrical activities of the same source. Therefore the spatial filter coefficients corresponding to the nearby electrodes are supposed to exhibit similar values, that is, the coefficients should be spatially smooth. To introduce the smoothness, a graph whose edge weights represent the physical distances between the electrodes is introduced. The spatially smoothed spatial filter is found out in the subspace spanned by the smooth basis induced from the graph Laplacian. We evaluate the method with artificial signals and a dataset of motor imagery brain computer interface. The smoothness of the spatial filter given by the method provides robustness of the spatial filter in the condition that the small amount of the samples is available. The smoothness of the spatial filter given by the method provides robustness of the spatial filter in the condition that the small amount of the samples is available.
Bio: His research interests include image and signal processing, statistical signal processing and machine learning, brain and biomedical signal processing, and adaptive systems. He is a co-editor of Signal Processing Techniques for Knowledge Extraction and Information Fusion (with Mandic, Springer), 2008. He served as a guest editor of special issues in journals including Neurocomputing. He served as an associate editor of IEICE Transactions on Fundamentals. He was a chair of the Technical Committee on Biomedical Signal Processing, APSIPA. He is a senior member of IEEE, and a member of IEICE and APSIPA.