A Jackknife-Inspired Deep Learning Approach to Subject-Independent Classification of EEG

被引:0
|
作者
Dolzhikova, Irina [1 ]
Abibullaev, Berdakh [2 ]
Zollanvari, Amin [1 ]
机构
[1] Nazarbayev Univ, Dept Elect & Comp Engn, Astana, Kazakhstan
[2] Nazarbayev Univ, Dept Robot & Mechatron, Astana, Kazakhstan
关键词
Convolutional neural network; Delete-a-Subject-Jackknife; Deep learning; Subject-independent; CONVOLUTIONAL NEURAL-NETWORKS; BRAIN-COMPUTER INTERFACES; MODEL; CONFIDENCE; BIAS;
D O I
10.1016/j.patrec.2023.10.011
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
One of the significant challenges in Brain-Computer Interface (BCI) is to develop a classifier that can decode users' mental states based on electroencephalogram (EEG) data collected from independent subjects. The focus of such subject-independent (SI) classification is justified because it can lead to BCIs that do not require a user-specific calibration process. In recent years, the emergence of deep neural networks (DNNs) has significantly improved the performance of EEG classification. Among various deep learning techniques, the training efficiency and the performance of Convolutional Neural Networks (CNNs), in particular, have led to several state-of-the-art architectures for accurate classification of EEG. Not surprisingly, the efforts to improve the performance of these architectures for EEG classification have been ramped up in recent years. In this regard, a trivial approach is to train and tune a large number of architectures and hyperparameters and hope to improve upon the existing results. In contrast with this ad hoc approach, here we put forward a systematic method inspired by the jackknife estimation to improve the performance of existing CNN architectures. Using EEGNet and ShallowConvNet as archetypical, our empirical results show that the proposed "Delete-a-Subject Jackknife"(DASJ) technique can potentially improve the performance of existing CNN architectures for SI classification of EEG.
引用
收藏
页码:28 / 33
页数:6
相关论文
共 50 条
  • [41] Deep Learning Models for Subject-Independent ERP-based Brain-Computer Interfaces
    Tuleuov, Adilet
    Abibullaev, Berdakh
    2019 9TH INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING (NER), 2019, : 945 - 948
  • [42] Subject-Independent Emotion Recognition During Music Listening Based on EEG Using Deep Convolutional Neural Networks
    Keelawat, Panayu
    Thammasan, Nattapong
    Kijsirikul, Boonserm
    Numao, Masayuki
    2019 IEEE 15TH INTERNATIONAL COLLOQUIUM ON SIGNAL PROCESSING & ITS APPLICATIONS (CSPA 2019), 2019, : 21 - 26
  • [43] Automated detection and classification of leukemia on a subject-independent test dataset using deep transfer learning supported by Grad-CAM visualization
    Abhishek, Arjun
    Jha, Rajib Kumar
    Sinha, Ruchi
    Jha, Kamlesh
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2023, 83
  • [44] Subject-Independent Diver Gesture Classification Using Upper Limb Movement
    Ghader, Bilal
    Dune, Claire
    Watelain, Eric
    Hugel, Vincent
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2024, 9 (11): : 9311 - 9318
  • [45] Interpretable Convolutional Neural Networks for Subject-Independent Motor Imagery Classification
    Bang, Ji-Seon
    Lee, Seong-Whan
    10TH INTERNATIONAL WINTER CONFERENCE ON BRAIN-COMPUTER INTERFACE (BCI2022), 2022,
  • [46] Subject-Independent Odor Pleasantness Classification Using Brain and Peripheral Signals
    Kroupi, Eleni
    Vesin, Jean-Marc
    Ebrahimi, Touradj
    IEEE TRANSACTIONS ON AFFECTIVE COMPUTING, 2016, 7 (04) : 422 - 434
  • [47] A Deep-Learning Model for Subject-Independent Human Emotion Recognition Using Electrodermal Activity Sensors
    Al Machot, Fadi
    Elmachot, Ali
    Ali, Mouhannad
    Al Machot, Elyan
    Kyamakya, Kyandoghere
    SENSORS, 2019, 19 (07)
  • [48] Subject-Independent, Biological Hip Moment Estimation During Multimodal Overground Ambulation Using Deep Learning
    Molinaro, Dean D.
    Kang, Inseung
    Camargo, Jonathan
    Gombolay, Matthew C.
    Young, Aaron J.
    IEEE TRANSACTIONS ON MEDICAL ROBOTICS AND BIONICS, 2022, 4 (01): : 219 - 229
  • [49] Subject-Dependent and Subject-Independent Emotion Classification Using Unimodal and Multimodal Physiological Signals
    Jatupaiboon, Noppadon
    Pan-Ngum, Setha
    Israsena, Pasin
    JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, 2015, 5 (05) : 1020 - 1027
  • [50] Transferrable Subject-Independent Feature Representation for Discriminating EEG-Based Brain Signals
    Haowei Lou
    Zesheng Ye
    Lina Yao
    Guidance,Navigation and Control, 2024, (03) : 45 - 69