Comparison of Supervised Classification Methods with Various Data Preprocessing Procedures for Activation Detection in fMRI Data
In this study we compare five classification methods for detecting activation in fMRI data: Fisher linear discriminant, support vector machine, Gaussian nave Bayes, correlation analysis and k-nearest neighbor classifier. In order to enhance classifiers performance a variety of data preprocessing steps were employed. The results show that although kNN and linear SVM can classify active and nonactive voxels with less than 1.2% error, careful preprocessing of the data, including dimensionality reduction, outlier elimination, and denoising are important factors in overall classification.
KeywordsSupport Vector Machine Linear Discriminant Analysis Classification Error fMRI Data Independent Component Analysis
- 1.Franc, V., Hlavác, V. Statistical pattern recognition toolbox for matlab. Center for Machine Perception, Czech Technical University, Prague, Czech (2004)Google Scholar
- 2.Group, T.F.M. Spm5 manual. (2005)Google Scholar
- 5.Mitchell, T., Hutchinson, R., Just, M.A., Niculescu, R.S., Pereira, F., Wang, X. Classifying instantaneous cognitive states from fmri data. In: Americal Medical Informatics Association Annual Symposium, Washington DC 469 (2003)Google Scholar
- 7.Theodoridis, S., Koutroumbas, K. Pattern Recognition. Academic Press, San Diego, CA (2006)Google Scholar