Multi-Class Classification Methods for EEG Signals of Lower-Limb Rehabilitation Movements

Brain–Computer Interfaces (BCIs) enable direct communication between the brain and external devices by decoding motor intentions from EEG signals. However, the existing multi-class classification methods for motor imagery EEG (MI-EEG) signals are hindered by low signal quality and limited accuracy,...

Full description

Saved in:
Bibliographic Details
Main Authors: Shuangling Ma, Zijie Situ, Xiaobo Peng, Zhangyang Li, Ying Huang
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Biomimetics
Subjects:
Online Access:https://www.mdpi.com/2313-7673/10/7/452
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849303505673650176
author Shuangling Ma
Zijie Situ
Xiaobo Peng
Zhangyang Li
Ying Huang
author_facet Shuangling Ma
Zijie Situ
Xiaobo Peng
Zhangyang Li
Ying Huang
author_sort Shuangling Ma
collection DOAJ
description Brain–Computer Interfaces (BCIs) enable direct communication between the brain and external devices by decoding motor intentions from EEG signals. However, the existing multi-class classification methods for motor imagery EEG (MI-EEG) signals are hindered by low signal quality and limited accuracy, restricting their practical application. This study focuses on rehabilitation training scenarios, aiming to capture the motor intentions of patients with partial or complete motor impairments (such as stroke survivors) and provide feedforward control commands for exoskeletons. This study developed an EEG acquisition protocol specifically for use with lower-limb rehabilitation motor imagery (MI). It systematically explored preprocessing techniques, feature extraction strategies, and multi-classification algorithms for multi-task MI-EEG signals. A novel 3D EEG convolutional neural network (3D EEG-CNN) that integrates time/frequency features is proposed. Evaluations on a self-collected dataset demonstrated that the proposed model achieved a peak classification accuracy of 66.32%, substantially outperforming conventional approaches and demonstrating notable progress in the multi-class classification of lower-limb motor imagery tasks.
format Article
id doaj-art-7df102ff6d524f74b1fe2207063ebd30
institution Kabale University
issn 2313-7673
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Biomimetics
spelling doaj-art-7df102ff6d524f74b1fe2207063ebd302025-08-20T03:58:26ZengMDPI AGBiomimetics2313-76732025-07-0110745210.3390/biomimetics10070452Multi-Class Classification Methods for EEG Signals of Lower-Limb Rehabilitation MovementsShuangling Ma0Zijie Situ1Xiaobo Peng2Zhangyang Li3Ying Huang4College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaShenzhen Key Laboratory of Marine Bioresources and Ecology, College of Life Sciences and Oceanography, Shenzhen University, Shenzhen 518060, ChinaBrain–Computer Interfaces (BCIs) enable direct communication between the brain and external devices by decoding motor intentions from EEG signals. However, the existing multi-class classification methods for motor imagery EEG (MI-EEG) signals are hindered by low signal quality and limited accuracy, restricting their practical application. This study focuses on rehabilitation training scenarios, aiming to capture the motor intentions of patients with partial or complete motor impairments (such as stroke survivors) and provide feedforward control commands for exoskeletons. This study developed an EEG acquisition protocol specifically for use with lower-limb rehabilitation motor imagery (MI). It systematically explored preprocessing techniques, feature extraction strategies, and multi-classification algorithms for multi-task MI-EEG signals. A novel 3D EEG convolutional neural network (3D EEG-CNN) that integrates time/frequency features is proposed. Evaluations on a self-collected dataset demonstrated that the proposed model achieved a peak classification accuracy of 66.32%, substantially outperforming conventional approaches and demonstrating notable progress in the multi-class classification of lower-limb motor imagery tasks.https://www.mdpi.com/2313-7673/10/7/452MI-EEG signalsfour-class classificationcommon spatial patternconvolutional neural network3D EEG-CNN
spellingShingle Shuangling Ma
Zijie Situ
Xiaobo Peng
Zhangyang Li
Ying Huang
Multi-Class Classification Methods for EEG Signals of Lower-Limb Rehabilitation Movements
Biomimetics
MI-EEG signals
four-class classification
common spatial pattern
convolutional neural network
3D EEG-CNN
title Multi-Class Classification Methods for EEG Signals of Lower-Limb Rehabilitation Movements
title_full Multi-Class Classification Methods for EEG Signals of Lower-Limb Rehabilitation Movements
title_fullStr Multi-Class Classification Methods for EEG Signals of Lower-Limb Rehabilitation Movements
title_full_unstemmed Multi-Class Classification Methods for EEG Signals of Lower-Limb Rehabilitation Movements
title_short Multi-Class Classification Methods for EEG Signals of Lower-Limb Rehabilitation Movements
title_sort multi class classification methods for eeg signals of lower limb rehabilitation movements
topic MI-EEG signals
four-class classification
common spatial pattern
convolutional neural network
3D EEG-CNN
url https://www.mdpi.com/2313-7673/10/7/452
work_keys_str_mv AT shuanglingma multiclassclassificationmethodsforeegsignalsoflowerlimbrehabilitationmovements
AT zijiesitu multiclassclassificationmethodsforeegsignalsoflowerlimbrehabilitationmovements
AT xiaobopeng multiclassclassificationmethodsforeegsignalsoflowerlimbrehabilitationmovements
AT zhangyangli multiclassclassificationmethodsforeegsignalsoflowerlimbrehabilitationmovements
AT yinghuang multiclassclassificationmethodsforeegsignalsoflowerlimbrehabilitationmovements