Unifying Genetic Algorithm and Clustering Method for Recognizing Activated fMRI Time Series
In order to get more reliable activation detection result in functional MRI data, we attempt to bring together the advantages of the genetic algorithm, which is deterministic and able to escape from the local optimal solution, and the K-means clustering, which is fast. Thus a novel clustering approach, namely the genetic K-means algorithm, is proposed to detect fMRI activation. It 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 experimental results show that the proposed method recognizes fMRI activation regions with higher accuracy than ordinary K-means clustering.
KeywordsfMRI Data Independent Component Analysis Cluster Centroid fMRI Time Series Empty Cluster
Unable to display preview. Download preview PDF.
- 5.Lu, Y., Lu, S., Fotouhi, F., Deng, Y., Brown, S.: Fast genetic k-means algorithm and its application in gene expression data analysis. Technical Report TR-DB-06-2003 (2003), http://www.cs.wayne.edu/~luyi/publication/tr0603.pdf