Skip to Main Content
We propose a novel clustering approach to fMRI activation detection using a genetic K-means algorithm, which is more likely to find a global optimal solution to the K-means clustering, and is independent of the initial assignments of the cluster centroids. The experiments show that the proposed method solves fMRI activation detection problem with higher accuracy than ordinary K-means clustering.
Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on (Volume:3 )
Date of Conference: 18-21 Aug. 2005