A data-driven machine learning approach for brain-computer interfaces targeting lower limb neuroprosthetics

被引:5
|
作者
Dillen, Arnau [1 ,2 ,3 ]
Lathouwers, Elke [1 ,2 ]
Miladinovic, Aleksandar [4 ,5 ,6 ]
Marusic, Uros [4 ,7 ]
Ghaffari, Fakhreddine [3 ]
Romain, Olivier [3 ]
Meeusen, Romain [1 ,2 ]
De Pauw, Kevin [1 ,2 ]
机构
[1] Vrije Univ Brussel, Human Physiol & Sports Physiotherapy Res Grp, Brussels, Belgium
[2] Vrije Univ Brussel, Brussels Human Robot Res Ctr, Brussels, Belgium
[3] CY Cergy Paris Univ, Equipes Traitement Informat & Syst, Cergy, France
[4] Inst Kinesiol Res Sci & Res Ctr Koper, Koper, Slovenia
[5] IRCCS Burlo Garofolo, Inst Maternal & Child Hlth, Trieste, Italy
[6] Univ Trieste, Dept Engn & Architecture, Trieste, Italy
[7] Alma Mater Europaea ECM, Dept Hlth Sci, Maribor, Slovenia
来源
FRONTIERS IN HUMAN NEUROSCIENCE | 2022年 / 16卷
基金
欧盟地平线“2020”;
关键词
neuroprosthetics; brain-computer interface; machine learning; electroencephalography; data-driven learning; lower limb amputation; MOTOR; PATTERN; COMPONENTS; REJECTION; SIGNALS; ABILITY; KERNEL; CORTEX; KNEE;
D O I
10.3389/fnhum.2022.949224
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
Prosthetic devices that replace a lost limb have become increasingly performant in recent years. Recent advances in both software and hardware allow for the decoding of electroencephalogram (EEG) signals to improve the control of active prostheses with brain-computer interfaces (BCI). Most BCI research is focused on the upper body. Although BCI research for the lower extremities has increased in recent years, there are still gaps in our knowledge of the neural patterns associated with lower limb movement. Therefore, the main objective of this study is to show the feasibility of decoding lower limb movements from EEG data recordings. The second aim is to investigate whether well-known neuroplastic adaptations in individuals with an amputation have an influence on decoding performance. To address this, we collected data from multiple individuals with lower limb amputation and a matched able-bodied control group. Using these data, we trained and evaluated common BCI methods that have already been proven effective for upper limb BCI. With an average test decoding accuracy of 84% for both groups, our results show that it is possible to discriminate different lower extremity movements using EEG data with good accuracy. There are no significant differences (p = 0.99) in the decoding performance of these movements between healthy subjects and subjects with lower extremity amputation. These results show the feasibility of using BCI for lower limb prosthesis control and indicate that decoding performance is not influenced by neuroplasticity-induced differences between the two groups.
引用
收藏
页数:15
相关论文
共 50 条
  • [31] The Prediction of Flight Delay: Big Data-driven Machine Learning Approach
    Huo, Jiage
    Keung, K. L.
    Lee, C. K. M.
    Ng, Kam K. H.
    Li, K. C.
    2020 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL ENGINEERING AND ENGINEERING MANAGEMENT (IEEE IEEM), 2020, : 190 - 194
  • [32] A data-driven approach to predicting diabetes and cardiovascular disease with machine learning
    An Dinh
    Stacey Miertschin
    Amber Young
    Somya D. Mohanty
    BMC Medical Informatics and Decision Making, 19
  • [33] Channel reflection: Knowledge-driven data augmentation for EEG-based brain-computer interfaces
    Wang, Ziwei
    Li, Siyang
    Luo, Jingwei
    Liu, Jiajing
    Wu, Dongrui
    NEURAL NETWORKS, 2024, 176
  • [34] Data-driven machine learning models for decoding speech categorization from evoked brain responses
    Mahmud, Md Sultan
    Yeasin, Mohammed
    Bidelman, Gavin M.
    JOURNAL OF NEURAL ENGINEERING, 2021, 18 (04)
  • [35] Deep learning and deep knowledge representation in Spiking Neural Networks for Brain-Computer Interfaces
    Kumarasinghe, Kaushalya
    Kasabov, Nikola
    Taylor, Denise
    NEURAL NETWORKS, 2020, 121 (121) : 169 - 185
  • [36] A ML-based Approach to Enhance Metrological Performance of Wearable Brain-Computer Interfaces
    Angrisani, Leopoldo
    Apicella, Andrea
    Arpaia, Pasquale
    De Benedetto, Egidio
    Donato, Nicola
    Duraccio, Luigi
    Giugliano, Salvatore
    Prevete, Roberto
    2022 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE (I2MTC 2022), 2022,
  • [37] Learning Discriminative Spatiospectral Features of ERPs for Accurate Brain-Computer Interfaces
    Abibullaev, Berdakh
    Zollanvari, Amin
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2019, 23 (05) : 2009 - 2020
  • [38] Transfer learning for motor imagery based brain-computer interfaces: A tutorial
    Wu, Dongrui
    Jiang, Xue
    Peng, Ruimin
    NEURAL NETWORKS, 2022, 153 : 235 - 253
  • [39] Riemannian Geometric Instance Filtering for Transfer Learning in Brain-Computer Interfaces
    Hui, Qianxin
    Liu, Xiaolin
    Li, Yang
    Xu, Susu
    Zhang, Shuailei
    Sun, Ying
    Wang, Shuai
    Chen, Xinlei
    Zheng, Dezhi
    PROCEEDINGS OF THE TWENTIETH ACM CONFERENCE ON EMBEDDED NETWORKED SENSOR SYSTEMS, SENSYS 2022, 2022, : 1162 - 1167
  • [40] Multiview Contrastive Learning for Unsupervised Domain Adaptation in Brain-Computer Interfaces
    Asgarian, Sepehr
    Wang, Ze
    Wan, Feng
    Wong, Chi Man
    Liu, Feng
    Mohsenzadeh, Yalda
    Wang, Boyu
    Ling, Charles X.
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2024, 73 : 1 - 10