Dynamic Distribution Alignment With Dual-Subspace Mapping for Cross-Subject Driver Mental State Detection

• Published in: IEEE transactions on cognitive and developmental systems Vol. 14; no. 4; pp. 1705 - 1716
• Main Authors: Cui, Jin, Jin, Xuanyu, Hu, Hua, Zhu, Li, Ozawa, Kenji, Pan, Gang, Kong, Wanzeng
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.12.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Alignment; Conditional probability; Covariance matrices; Domain adaptation; Domains; driver mental state detection; electroencephalogram (EEG); Electroencephalography; Handheld computers; Mapping; Matrix decomposition; Probability distribution; Subspaces; Task analysis; transfer learning; Visualization
• ISSN: 2379-8920; 2379-8939
• DOI: 10.1109/TCDS.2021.3137530

For the detection of electroencephalogram-based driving mental states, it is important to utilize transfer learning to overcome individual and period differences. However, there are two challenges in existing unsupervised domain adaptation methods: 1) they ignore the geometric divergence of the source and target domains with single subspace mapping and 2) they usually employ a fixed weight distribution to align the marginal and conditional probability distributions. In this article, we propose a dynamic distribution alignment with dual-subspace mapping (DDADSM) method for cross-subject driver mental state detection. Initially, DDADSM explores two optimally aligned subspaces for the source and target domains, which can significantly reduce the geometric shifting. Subsequently, the dynamic probability distribution alignment method is introduced to acquire the adaptive weight between the marginal and conditional distributions, which adapts to domains with wide variations. Through our experiments based on the driving mental state detection task, DDADSM demonstrated superior performance compared with state-of-the-art models.