Transfer Learning for P300 Brain-Computer Interfaces by Joint Alignment of Feature Vectors

• Published in: IEEE journal of biomedical and health informatics Vol. 27; no. 10; pp. 1 - 11
• Main Authors: Altindis, Fatih, Banerjee, Antara, Phlypo, Ronald, Yilmaz, Bulent, Congedo, Marco
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Algorithms; Alignment; Brain; Brain modeling; Brain-computer interface (BCI); Classification; Computational neuroscience; Computer applications; Computer Science; Covariance matrices; domain adaptation; Electroencephalography; electroencephalography (EEG); Engineering Sciences; Expression vectors; Human-computer interface; Implants; Linear transformations; Machine learning; Manifolds; Riemannian geometry; Training; Transfer learning; Approximate Joint Diagonalization AJD; Transfer learning TL; P300 classification; Brain-Computer Interface BCI; Riemannian Geometry; Tangent Space
• ISSN: 2168-2194; 2168-2208; 2168-2208
• DOI: 10.1109/JBHI.2023.3299837

This paper presents a new transfer learning method named group learning, that jointly aligns multiple domains (many-to-many) and an extension named fast alignment that aligns any further domain to previously aligned group of domains (many-to-one). The proposed group alignment algorithm (GALIA) is evaluated on brain-computer interface (BCI) data and optimal hyper-parameter values of the algorithm are studied for classification performance and computational cost. Six publicly available P300 databases comprising 333 sessions from 177 subjects are used. As compared to the conventional subject-specific train/test pipeline, both group learning and fast alignment significantly improve the classification accuracy except for the database with clinical subjects (average improvement: 2.12±1.88%). GALIA utilizes cyclic approximate joint diagonalization (AJD) to find a set of linear transformations, one for each domain, jointly aligning the feature vectors of all domains. Group learning achieves a many-to-many transfer learning without compromising the classification performance on non-clinical BCI data. Fast alignment further extends the group learning for any unseen domains, allowing a many-to-one transfer learning with the same properties. The former method creates a single machine learning model using data from previous subjects and/or sessions, whereas the latter exploits the trained model for an unseen domain requiring no further training of the classifier.