Constructing a Personalized Cross-Day EEG-Based Emotion-Classification Model Using Transfer Learning

• Published in: IEEE journal of biomedical and health informatics Vol. 24; no. 5; pp. 1255 - 1264
• Main Author: Lin, Yuan-Pin
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.05.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Affective computing; Arousal; Brain modeling; Classification; Data collection; Data models; Datasets; EEG; EEG non-stationarity; EEG-based emotion classification; Electroencephalography; Electroencephalography - methods; Emotional responses; Emotions; Emotions - classification; Female; Humans; Learning; Machine Learning; Male; Oscillators; Principal Component Analysis; Principal components analysis; Signal Processing, Computer-Assisted; Sparse matrices; Transfer learning

State-of-the-art electroencephalogram (EEG)-based emotion-classification works indicate that a personalized model may not be well exploited until sufficient labeled data are available, given a substantial EEG non-stationarity over days. However, it is impractical to impose a labor-intensive, time-co...