Brain State Recognition Using Fuzzy C-Means (FCM) Clustering with Near Infrared Spectroscopy (NIRS)

Authors:
Syoji Kobashi;Yutaka Hata;Yuri Kitamura;Toshiaki Hayakata;Toshio Yanagida
Affiliations:
-;-;-;-;-
Venue:
Proceedings of the International Conference, 7th Fuzzy Days on Computational Intelligence, Theory and Applications
Year:
2001

Citing 2
Cited 1

Pattern Recognition with Fuzzy Objective Function Algorithms

Pattern Recognition with Fuzzy Objective Function Algorithms
Automatic segmentation of non-enhancing brain tumors in magnetic resonance images

Artificial Intelligence in Medicine

A new segmentation system for brain MR images based on fuzzy techniques

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Near-infrared spectroscopy (NIRS) is a recently developed method, which can investigate the human brain function with noninvasive, high time resolution, and high portability. However, there are few discussions on post-processing of time series data taken by the NIRS because of the difficulty of understanding the obtained data and the complexity of the human higher-order brain function. This paper discusses on an analysis of such a time series. The analysis method is based on fuzzy c-means (FCM) clustering and wavelet transform, and it divides the time series of a measurement point into some clusters with respect to wavelet coefficients. To evaluate the performance of the method, it has been applied to four healthy volunteers, and three brain-dead patients. The results showed that the proposed method could segment the NIRS time series into some clusters that may represent brain states, and could estimate the number of clusters.