Title :
A new multiple-kernel-learning weighting method for localizing human brain magnetic activity
Author :
Takiguchi, T. ; Imada, T. ; Takashima, R. ; Ariki, Y. ; Lin, J. -F L ; Kuhl, P.K. ; Kawakatsu, M. ; Kotani, M.
Author_Institution :
Grad. Sch. of Syst. Inf., Kobe Univ., Kobe, Japan
Abstract :
This paper shows that pattern classification based on machine learning is a powerful tool to analyze human brain activity data obtained by magnetoencephalography (MEG). We propose a new weighting method using a multiple kernel learning (MKL) algorithm to localize the brain area contributing to the accurate vowel discrimination. Our MKL simultaneously estimates both the classification boundary and the weight of each MEG sensor; MEG amplitude obtained from each pair of sensors is an element of the feature vector. The estimated weight indicates how the corresponding sensor is useful for classifying the MEG response patterns. Our results show both the large-weight MEG sensors mainly in a language area of the brain and the high classification accuracy (73.0%) in the 100 ~ 200 ms latency range.
Keywords :
feature extraction; learning (artificial intelligence); magnetoencephalography; medical signal processing; pattern classification; signal classification; MEG amplitude; MEG response patterns; classification boundary; feature vector; human brain magnetic activity localization; large-weight MEG sensors; machine learning; magnetoencephalography; multiple kernel learning weighting method; pattern classification; vowel discrimination; Accuracy; Brain; Educational institutions; Kernel; Speech; Support vector machines; Vectors; brain activity; brain area; kernel learning; magnetoencephalography; weighting;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2012 IEEE International Conference on
Conference_Location :
Kyoto
Print_ISBN :
978-1-4673-0045-2
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2012.6287995