Learning a common dictionary for subject-transfer decoding with resting calibration

• Published in: NeuroImage (Orlando, Fla.) Vol. 111; pp. 167 - 178
• Main Authors: Morioka, Hiroshi, Kanemura, Atsunori, Hirayama, Jun-ichiro, Shikauchi, Manabu, Ogawa, Takeshi, Ikeda, Shigeyuki, Kawanabe, Motoaki, Ishii, Shin
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 01.05.2015; Elsevier Limited
• Subjects: Adult; Brain; Brain - physiology; Brain-Computer Interfaces; Brain–machine interface (BMI); Calibration; Dictionary learning and sparse coding; Electroencephalography; Electroencephalography (EEG); Electroencephalography - methods; Functional Neuroimaging - methods; Humans; Multi-subject–session analysis; Neurosciences; Signal processing; Signal Processing, Computer-Assisted; Spatial attention; Studies; Subject-transfer decoding; Dictionary learning and sparse coding; Subject-transfer decoding; Brain–machine interface (BMI); Electroencephalography (EEG); Spatial attention; Multi-subject–session analysis
• ISSN: 1053-8119; 1095-9572; 1095-9572
• DOI: 10.1016/j.neuroimage.2015.02.015

Brain signals measured over a series of experiments have inherent variability because of different physical and mental conditions among multiple subjects and sessions. Such variability complicates the analysis of data from multiple subjects and sessions in a consistent way, and degrades the performance of subject-transfer decoding in a brain–machine interface (BMI). To accommodate the variability in brain signals, we propose 1) a method for extracting spatial bases (or a dictionary) shared by multiple subjects, by employing a signal-processing technique of dictionary learning modified to compensate for variations between subjects and sessions, and 2) an approach to subject-transfer decoding that uses the resting-state activity of a previously unseen target subject as calibration data for compensating for variations, eliminating the need for a standard calibration based on task sessions. Applying our methodology to a dataset of electroencephalography (EEG) recordings during a selective visual–spatial attention task from multiple subjects and sessions, where the variability compensation was essential for reducing the redundancy of the dictionary, we found that the extracted common brain activities were reasonable in the light of neuroscience knowledge. The applicability to subject-transfer decoding was confirmed by improved performance over existing decoding methods. These results suggest that analyzing multisubject brain activities on common bases by the proposed method enables information sharing across subjects with low-burden resting calibration, and is effective for practical use of BMI in variable environments. •Novel method for extracting spatial bases of brain signals shared by multisubjects.•Subject-transfer decoding using activities on the common spatial bases.•Calibration of the decoders for target subjects using resting-state recordings.•Robust EEG analysis results based on a dataset of more than forty subjects.•Better subject-transfer decoding performance than existing methods.