DMSACNN: Deep Multiscale Attentional Convolutional Neural Network for EEG-Based Motor Decoding

Objective: Accurate decoding of electroencephalogram (EEG) signals has become more significant for the brain-computer interface (BCI). Specifically, motor imagery and motor execution (MI/ME) tasks enable the control of external devices by decoding EEG signals during imagined or real movements. However, accurately decoding MI/ME signals remains a challenge due to the limited utilization of temporal information and ineffective feature selection methods. Methods: This paper introduces DMSACNN, an end-to-end deep multiscale attention convolutional neural network for MI/ME-EEG decoding. DMSACNN incorporates a deep multiscale temporal feature extraction module to capture temporal features at various levels. These features are then processed by a spatial convolutional module to extract spatial features. Finally, a local and global feature fusion attention module is utilized to combine local and global information and extract the most discriminative spatiotemporal features. Main results: DMSACNN achieves impressive accuracies of 78. 20%, 96. 34% and 70. 90% for hold-out analysis on the BCI-IV-2a, High Gamma and OpenBMI datasets, respectively, outperforming most of the state-of-the-art methods. Conclusion and significance: These results highlight the potential of DMSACNN in robust BCI applications. Our proposed method provides a valuable solution to improve the accuracy of the MI/ME-EEG decoding, which can pave the way for more efficient and reliable BCI systems.

Authors

• Ke Liu Zhejiang University
• Xin Xing
• Tao Yang Sun Yat-sen University
• Zhuliang Yu Institute for Super Robotics (Huangpu) Shien-Ming Wu School of Intelligent Engineering, South China University of Technology School of Automation Science and Engineering, South China University of Technology
• Bin Xiao
• Guoyin Wang National Center for Applied Mathematics in Chongqing, Chongqing Normal University, Chongqing 401331, China
• Wei Wu

Keywords

• Feature extraction
• Decoding
• Electroencephalography
• Brain modeling
• Accuracy
• Data mining
• Convolutional neural networks
• Convolutional Neural Network
• Deep Neural Network
• Local Information
• Spatial Features
• Global Features
• Temporal Features
• Temporal Information
• Global Information
• Discriminative Features
• EEG Signals
• Feature Fusion
• Control Devices
• Motor Execution
• Motor Imagery
• High Gamma
• Decoding Accuracy
• Brain-computer Interface System
• Classification Accuracy
• Superior Performance
• Artificial Neural Network
• Motor Imagery Tasks
• Feature Maps
• Convolution Kernel
• Multi-scale Architecture
• Decoding Performance
• Attention Mechanism
• Global Average Pooling
• Common Spatial Pattern
• Multiple Scales
• Number Of Filters
• Brain-computer interface
• deep mixed-scale convolution
• Humans
• Brain-Computer Interfaces
• Neural Networks, Computer
• Signal Processing, Computer-Assisted
• Imagination