Deep and Wide Transfer Learning with Kernel Matching for Pooling Data from Electroencephalography and Psychological Questionnaires

• Published in: Sensors (Basel, Switzerland) Vol. 21; no. 15; p. 5105
• Main Authors: Collazos-Huertas, Diego Fabian, Velasquez-Martinez, Luisa Fernanda, Perez-Nastar, Hernan Dario, Alvarez-Meza, Andres Marino, Castellanos-Dominguez, German
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 28.07.2021; MDPI
• Subjects: Accuracy; Brain research; Classification; Deep and Wide network; Deep learning; Electroencephalography; Illiteracy; kernel-embedding; motor imagery; Neural networks; Questionnaires; Topography; transfer learning; Wavelet transforms
• DOI: 10.3390/s21155105
• ISSN: 1424-8220

Motor imagery (MI) promotes motor learning and encourages brain–computer interface systems that entail electroencephalogram (EEG) decoding. However, a long period of training is required to master brain rhythms’ self-regulation, resulting in users with MI inefficiency. We introduce a parameter-based approach of cross-subject transfer-learning to improve the performances of poor-performing individuals in MI-based BCI systems, pooling data from labeled EEG measurements and psychological questionnaires via kernel-embedding. To this end, a Deep and Wide neural network for MI classification is implemented to pre-train the network from the source domain. Then, the parameter layers are transferred to initialize the target network within a fine-tuning procedure to recompute the Multilayer Perceptron-based accuracy. To perform data-fusion combining categorical features with the real-valued features, we implement stepwise kernel-matching via Gaussian-embedding. Finally, the paired source–target sets are selected for evaluation purposes according to the inefficiency-based clustering by subjects to consider their influence on BCI motor skills, exploring two choosing strategies of the best-performing subjects (source space): single-subject and multiple-subjects. Validation results achieved for discriminant MI tasks demonstrate that the introduced Deep and Wide neural network presents competitive performance of accuracy even after the inclusion of questionnaire data.