Biosignal Informatics and Processing
I am advocating this new concept of research area called biosignal informatics. This novel area aims at unifying various concepts concerning biomedical signal processing, machine learning, neuroscience, mathematical engineering, etc.
Graph signal processing for electroencephalogram (EEG) with application to brain-computer interfaces
Introducing a graph structure to electrode location and the use of graph Fourier transform lead to effective feature extraction from EEG.
T. Tanaka, T. Uehara and Y. Tanaka, "Dimensionality reduction of sample covariance matrices by graph Fourier transform for motor imagery brain-machine interface," 2016 IEEE Statistical Signal Processing Workshop (SSP), Palma de Mallorca, 2016, pp. 1-5.
H. Higashi, T. M. Rutkowski, T. Tanaka, and Y. Tanaka, ``Multilinear discriminant analysis with subspace constraints for single-trial classification of event-related potentials,'' IEEE Journal of Selected Topics in Signal Processing, vol. 10, no. 7, pp. 1295-1305, 2016.
Active data selection of trials for motor-imagery brain computer interfaces
A novel sparse signal processing / machine learning methods for selecting useful trials from a dataset of multiple trials.
Tomida, N.; Tanaka, T.; Ono, S.; Yamagishi, M.; Higashi, H., "Active Data Selection for Motor Imagery EEG Classification," Biomedical Engineering, IEEE Transactions on , vol.62, no.2, pp.458,467, Feb. 2015
Digital communication through the brain with steady-state visually evoked potentials (SSVEP)
Kimura, Y.; Tanaka, T.; Higashi, H.; Morikawa, N., "SSVEP-Based Brain–Computer Interfaces Using FSK-Modulated Visual Stimuli," in Biomedical Engineering, IEEE Transactions on , vol.60, no.10, pp.2831-2838, Oct. 2013
Mining of active frequency bands during motor imagery
Higashi, H.; Tanaka, T., "Simultaneous Design of FIR Filter Banks and Spatial Patterns for EEG Signal Classification," in Biomedical Engineering, IEEE Transactions on , vol.60, no.4, pp.1100-1110, April 2013
Machine Learning and Signal Processing