摘要：Depression is a severe mental illness with an unknown pathogenesis. Clinical diagnosis is based primarily on symptoms and does not include objective biological markers. Finding objective markers for diagnosis and treatment from imaging, on the contrary, is becoming increasingly important. The SOM (self-organizing feature mapping) model was used to identify the depression tendency of users in order to investigate the emotional experience and psychological intervention of patients with depression. On this foundation, the concept of depression index is developed further, and the relationship between depression index and the severity of depression in patients is thoroughly investigated. The system can accurately and quickly identify the depression state by applying it directly to the original EEG signals, without any preprocessing or feature extraction. When combined with traditional classifiers, the analysis and comparison results show that SOM can not only effectively select features but also improve the accuracy of depression classification. This research proposes a new research direction for deep learning in the context of large-scale big data analysis.
