Can EEG features combined with machine learning classifiers accurately identify multiple anxiety levels in healthy college students?
EEG features, particularly linear features in the beta band and frontal lobe, combined with SVM can classify four anxiety levels with approximately 62.56% accuracy.
Anxiety is a complex emotional state that has a great impact on people's physical and mental health. Effectively identifying different anxiety states is very important. By inducing various anxiety states of 12 healthy college students with electroencephalograph (EEG) recording, comprehensive EEG features, including not only commonly used frequency domain features but also the time domain, statistical and nonlinear features were extracted from different EEG bands and brain locations. Next, correlation analysis was performed between various features and anxiety level changes that were predetermined at each stage of the experiment using a 5-point Likert scale, and the most relevant features were collected. Then, different classifiers were applied to classify four anxiety levels using different features alone or together to explore their anxiety recognition ability. Based on our dataset, the highest accuracy of identifying four anxiety states reached approximately 62.56 percent using the Support Vector Machine (SVM), which improved the classification accuracy compared with previous studies. The results also revealed the importance of EEG linear features (especially for features including total power, mean square and variance) in anxiety recognition. Furthermore, it suggested that EEG features in the beta band and the frontal lobe contributed to anxiety recognition more than the features in the other bands or other brain locations. In short, this study improves the accuracy of multi-level anxiety recognition and helps in choosing better features for anxiety recognition, which lay the foundation for the detection of continuous anxiety changes.
Li et al. (Thu,) studied this question.