EEG-Channel-Temporal-Spectral-Attention Correlation for Motor Imagery EEG Classification

被引:23
|
作者
Hsu, Wei-Yen [1 ]
Cheng, Ya-Wen [2 ]
机构
[1] Natl Chung Cheng Univ, Adv Inst Mfg High Tech Innovat, Ctr Innovat Res Aging Soc CIRAS, Dept Informat Management, Chiayi 62102, Taiwan
[2] Natl Chung Cheng Univ, Dept Informat Management, Chiayi 62102, Taiwan
关键词
Feature extraction; Electroencephalography; Time-frequency analysis; Task analysis; Convolution; Data mining; Correlation coefficient; Brain--computer interface (BCI); motor-imagery electroencephalography (MI EEG); EEG-channel attention; temporal-spectral attention; wavelet transform; correlation coefficient; BRAIN-COMPUTER-INTERFACE; ACTIVE SEGMENT SELECTION; FEATURE-EXTRACTION; FEATURE FUSION; NETWORK; FEATURES;
D O I
10.1109/TNSRE.2023.3255233
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
In brain-computer interface (BCI) work, how correctly identifying various features and their corresponding actions from complex Electroencephalography (EEG) signals is a challenging technology. However, most current methods do not consider EEG feature information in spatial, temporal and spectral domains, and the structure of these models cannot effectively extract discriminative features, resulting in limited classification performance. To address this issue, we propose a novel text motor-imagery EEG discrimination method, namely wavelet-based temporal-spectral-attention correlation coefficient (WTS-CC), to simultaneously consider the features and their weighting in spatial, EEG-channel, temporal and spectral domains in this study. The initial Temporal Feature Extraction (iTFE) module extracts the initial important temporal features of MI EEG signals. The Deep EEG-Channel-attention (DEC) module is then proposed to automatically adjust the weight of each EEG channel according to its importance, thereby effectively enhancing more important EEG channels and suppressing less important EEG channels. Next, the Wavelet-based Temporal-Spectral-attention (WTS) module is proposed to obtain more significant discriminative features between different MI tasks by weighting features on two-dimensional time-frequency maps. Finally, a simple discrimination module is used for MI EEG discrimination. The experimental results indicate that the proposed text WTS-CC method can achieve promising discrimination performance that outperforms the state-of-the-art methods in terms of classification accuracy, Kappa coefficient, F1 score, and AUC on three public datasets.
引用
收藏
页码:1659 / 1669
页数:11
相关论文
共 50 条
  • [21] Spatial and Spectral Features Fusion for EEG Classification during Motor Imagery in BCI
    Tan, Chuanqi
    Sun, Fuchun
    Zhang, Wenchang
    Liu, Shaobo
    Liu, Chunfang
    2017 IEEE EMBS INTERNATIONAL CONFERENCE ON BIOMEDICAL & HEALTH INFORMATICS (BHI), 2017, : 309 - 312
  • [22] MOTOR IMAGERY CLASSIFICATION USING EEG SPECTROGRAMS
    Khan, Saadat Ullah
    Majid, Muhammad
    Anwar, Syed Muhammad
    2023 IEEE 20TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING, ISBI, 2023,
  • [23] Relevant Feature Selection from a Combination of Spectral-Temporal and Spatial Features for Classification of Motor Imagery EEG
    Jyoti Singh Kirar
    R. K. Agrawal
    Journal of Medical Systems, 2018, 42
  • [24] Relevant Feature Selection from a Combination of Spectral-Temporal and Spatial Features for Classification of Motor Imagery EEG
    Kirar, Jyoti Singh
    Agrawal, R. K.
    JOURNAL OF MEDICAL SYSTEMS, 2018, 42 (05)
  • [25] SSTMNet: Spectral-Spatio-Temporal and Multiscale Deep Network for EEG-Based Motor Imagery Classification
    Alotaibi, Albandari
    Hussain, Muhammad
    Aboalsamh, Hatim
    MATHEMATICS, 2025, 13 (04)
  • [26] Classification of EEG Motor imagery multi class signals based on Cross Correlation
    Krishna, D. Hari
    Pasha, I. A.
    Savithri, T. Satya
    INTERNATIONAL CONFERENCE ON COMPUTATIONAL MODELLING AND SECURITY (CMS 2016), 2016, 85 : 490 - 495
  • [27] EEG Channel Selection Based on Correlation Coefficient for Motor Imagery Classification: A Study on Healthy Subjects and ALS Patient
    Yang, Tao
    Ang, Kai Keng
    Phua, Kok Soon
    Yu, Juanhong
    Toh, Valerie
    Ng, Wai Hoe
    So, Rosa Q.
    2018 40TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2018, : 1996 - 1999
  • [28] FBATCNet: A Temporal Convolutional Network With Frequency Band Attention for Decoding Motor Imagery EEG
    Ma, Shuaishuai
    Lv, Jidong
    Li, Wenjie
    Liu, Yan
    Zou, Ling
    Dai, Yakang
    IEEE ACCESS, 2025, 13 : 11265 - 11279
  • [29] A CHANNEL ATTENTION BASED MLP-MIXER NETWORK FOR MOTOR IMAGERY DECODING WITH EEG
    He, Yanbin
    Lu, Zhiyang
    Wang, Jun
    Shi, Jun
    2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, : 1291 - 1295
  • [30] Correlation between Forehead EEG and Sensorimotor Area EEG in Motor Imagery Task
    Li, Kuangda
    Sun, Gufei
    Zhang, Bofeng
    Wu, Shaochun
    Wu, Gengfeng
    EIGHTH IEEE INTERNATIONAL CONFERENCE ON DEPENDABLE, AUTONOMIC AND SECURE COMPUTING, PROCEEDINGS, 2009, : 430 - 435