期刊Applied Sciences发表论文：基于分片池的一维卷积神经与双向循环注意力单元网络的高效运动想象识别
论文“Effective Human Motor Imagery Recognition via Segment Pool Based on One-Dimensional Convolutional Neural Network with Bidirectional Recurrent Attention Unit Network”被期刊Applied Sciences接收
时间：2023-08-11
关键词：脑机接口与智能机器人，文章接收
近日，硕士研究生胡华文在计算机科学领域期刊（Applied Sciences，IF = 2.7，JCR Q3）发表题为“Effective Human Motor Imagery Recognition via Segment Pool Based on One-Dimensional Convolutional Neural Network with Bidirectional Recurrent Attention Unit Network”的研究性文章，通讯作者为张枢教授。
Brain-computer interface (BCI) technology enables humans to interact with computers by collecting and decoding Electroencephalogram (EEG) from the brain. For practical BCIs based on EEG, accurate recognition is crucial. However, existing methods often struggle to achieve a balance between accuracy and complexity. To overcome these challenges, we propose 1D convolutional neural networks with bidirectional recurrent attention unit network (1DCNN-BiRAU) based on the random segment recombination strategy (segments pool, SegPool) which showed in 图1. It has three main contributions. First, SegPool is proposed to increase training data diversity and reduce the impact of a single splicing method on model performance across different tasks. Second, it employs multiple 1D CNNs, including local and global models, to extract channel information with simplicity and efficiency. Third, BiRAU is introduced to learn temporal information and identify key features in time series data, using forward-backward networks and an attention gate in RAU. The experiments show that our model is effective and robust, achieving accuracy of 99.47% and 91.21% on the binary classification of individual and group level, while 90.90% and 92.18% on the four-category classification. Our model demonstrates promising results for recognizing human motor imagery and has the potential to be applied in practical scenarios such as brain-computer interfaces and neurological disorder diagnosis.
参考文献
Hu Huawen, Chenxi Yue, Enze Shi, Sigang Yu, Yanqing Kang, Jinru Wu, Jiaqi Wang, and Shu Zhang. 2023. “Effective Human Motor Imagery Recognition via Segment Pool Based on One-Dimensional Convolutional Neural Network with Bidirectional Recurrent Attention Unit Network” Applied Sciences 13, no. 16: 9233. https://doi.org/10.3390/app13169233.