EEG-based depression recognition using feature selection method with fuzzy label

Depression diagnosis is easily affected by subjective consciousness. It is of great significance to study objective and accurate identification methods. Electroencephalogram (EEG) can reflect brain activity and working state. Therefore, this paper aims to explore features with significant differences based on brain functional connectivity to improve the accuracy of depression recognition. We propose a Functional Connection Feature Selection based on Fuzzy Label (FLFCFS), it calculates the correlation between electrode pairs through the phase lag index (PLI), constructing a functional connection matrix. The cluster center is initialized with the same number as the actual category, and the local distance from the sample to the cluster center is calculated to determine its membership degree, serving as the fuzzy label. And a sparse regression model is employed to select the most related features associated with the fuzzy label. Finally, the top ranked feature subset is selected and input into support vector machine (SVM) for depression recognition. The experimental results show that FLFCFS effectively improves the recognition accuracy, reaching 92.59%, and obtains the highest classification performance. Our method makes full use of the semantic information implied in category markers, it effectively guides feature selection to obtain discriminant feature subsets, enhancing the accuracy of depression recognition.