MLDA: Multi-Loss Domain Adaptor for Cross-Session and Cross-Emotion EEG-Based Individual Identification

• Published in: IEEE journal of biomedical and health informatics Vol. 27; no. 12; pp. 5767 - 5778
• Main Authors: Miao, Yifan, Jiang, Wanqing, Su, Nuo, Shan, Jun, Jiang, Tianzi, Zuo, Nianming
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.12.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: across mental states; across time; Adaptation; Adapters; Adaptor proteins; Algorithms; Artificial neural networks; biometric; Biometric recognition systems; Brain modeling; Cognitive science; Data privacy; Deep learning; domain adaptation; EEG; Electroencephalography; Electroencephalography - methods; Emotions; Feature extraction; Fingerprint recognition; Fingerprint verification; Humans; Identification methods; Identification of persons; Labels; Machine learning; Mental health; Neural networks; Neural Networks, Computer; Pattern recognition; Recording; Software; Support vector machines; Task analysis

Traditional individual identification methods, such as face and fingerprint recognition, carry the risk of personal information leakage. The uniqueness and privacy of electroencephalograms (EEG) and the popularization of EEG acquisition devices have intensified research on EEG-based individual ident...