Focused on the traditional methods of feature selection for brain functional connectivity matrix derived from Resting-state functional Magnetic Resonance Imaging (R-fMRI) have feature redundancy, cannot determine the final feature dimension and other problems, a new feature selection algorithm was proposed. The algorithm combined Random Forest (RF) algorithm in statistical method, and applied it in the identification experiment of schizophrenic and normal patients, according to the features are obtained by the classification results of out of bag data. The experimental results show that compared to the traditional Principal Component Analysis (PCA), the proposed algorithm can effectively retain important features to improve recognition accuracy, which have good medical explanation.

The traditional classification algorithms are mostly based on balanced datasets. But when the sample is not balanced, the performance of these learning algorithms are often significantly decreased. For the classification of imbalanced data, a optimized Support Vector Machine (SVM) ensemble classifier model was proposed. Firstly, the model used KSMOTE and Bootstrap to preprocess the imbalanced data and paralleled to generate the corresponding SVM models. And then these SVM models' parameters were optimized by using complex method. At last the optimized SVM ensemble classifier model was generated by the above parameters and produce the final result by voting mechanism. Through the experiment on 5 groups of UCI standard data set, the experimental results show that the optimized SVM ensemble classifier model has higher classification accuracy than SVM model, optimized SVM model and so on. And the results also verify the effect of different bootNum values on the optimized SVM ensemble classifier.