Adaptive transfer learning-based multiscale feature fused deep convolutional neural network for EEG MI multiclassification in brain–computer interface. (November 2022)

• Record Type: Journal Article
• Authors: Roy, Arunabha M.
• Is Part Of: Engineering applications of artificial intelligence. Volume 116(2022)
• Publication Date: 2022-11
• Subjects: Brain–computer interfaces (BCIs) -- Transfer learning (TL) -- Motor imagery (MI) -- Electroencephalogram (EEG) signal classification -- Convolutional neural network (CNN) -- Deep learning (DL); Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2022.105347
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Objective: Deep learning (DL)-based brain–computer interface (BCI) in motor imagery (MI) has emerged as a powerful method for establishing direct communication between the brain and external electronic devices. However, due to inter-subject variability, inherent complex properties, and low signal-to-noise ratio (SNR) in electroencephalogram (EEG) signals are major challenges that significantly hinder the accuracy of the MI classifier. Approach: To overcome this, the present work proposes an efficient transfer learning (TL)-based multi-scale feature fused CNN (MSFFCNN) which can capture the distinguishable features of various non-overlapping canonical frequency bands of EEG signals from different convolutional scales for multi-class MI classification. Significance: In order to account for inter-subject variability from different subjects, the current work presents 4 different model variants including subject-independent and subject-adaptive classification models considering different adaptation configurations to exploit the full learning capacity of the classifier. Each adaptation configuration has been fine-tuned in an extensively trained pre-trained model and the performance of the classifier has been studied for a vast range of learning rates and degrees of adaptation which illustrates the advantages of using an adaptive transfer learning-based model. Results: The model achieves an average classification accuracy of 94.06% ( ± 0 . 70 % ) and the kappa value of 0.88 outperforming several baseline and current state-of-the-art EEG-based MI classification models with fewer training samples. The present research provides an effective and efficient transfer learning-based end-to-end MI classification framework for designing a high-performance robust MI-BCI system. Highlights: An efficient TL-based MSFFCNN has been proposed that demonstrates superior performance for EEG-based MI classification in BCIs. The MS-CNN block enhances the overall model performance from multiple scales. The OVR-FBCSP CNN block can efficiently extract the discriminative spatiotemporal CSP features of ERD/ERS. Proposed model achieves average classification accuracy of 94.06% outperforming several SOAT models with fewer training samples.