EEG-Based Motion Intention Detection for Robotic Rehabilitation: Evaluating Classification and Regression Algorithms

Rehabilitation robots have shown significant efficacy in restoring lost motor functions in stroke survivors by providing compliant assistance during rehabilitation tasks. However, accurately understanding the desired motion intention (DMI) of the subjects is a significant challenge in providing effe...

Full description

Saved in:
Bibliographic Details
Published in:SN computer science Vol. 5; no. 8; p. 1057
Main Authors: Khan, Abdul Manan, Khan, Fatima, Dwivedi, Anshu Kumar, Semwal, Vijay Bhaskar, Martha, Sheshikala, Bijalwan, Vishwanath
Format: Journal Article
Language:English
Published: Singapore Springer Nature Singapore 01.12.2024
Springer Nature B.V
Subjects:
Accuracy
Algorithms
Classification
Compliance
Computer Imaging
Computer Science
Computer Systems Organization and Communication Networks
Data Structures and Information Theory
Decision trees
Deep learning
Discriminant analysis
Effectiveness
Electroencephalography
Information Systems and Communication Service
Machine learning
Methods
Motion perception
Neural networks
Original Research
Pattern Recognition and Graphics
Real time
Recovery (Medical)
Regression
Rehabilitation
Rehabilitation robots
Research Advancements in Intelligent Computing
Robot dynamics
Robot learning
Robotics
Robots
Software Engineering/Programming and Operating Systems
Support vector machines
Vision
Deep learning
EEG signals
Rehabilitation
Desired motion intention
C-RNN
Machine learning
ISSN:2661-8907, 2662-995X, 2661-8907
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Rehabilitation robots have shown significant efficacy in restoring lost motor functions in stroke survivors by providing compliant assistance during rehabilitation tasks. However, accurately understanding the desired motion intention (DMI) of the subjects is a significant challenge in providing effective robotic assistance. This work aims to determine the desired motion intention (DMI) for compliant robotic assistance through the analysis of upper limb motions using electroencephalography (EEG) signals. A group of fifteen individuals who were in good health carried out six distinct exercises. These movements were categorized using decision trees, random forest, and deep learning algorithms. Using deep learning, we achieved the highest accuracy rates, reaching 82% for movement-to-movement classification and 90% for movement-to-rest classification. The random forest method achieved superior performance compared to the other algorithms in regression tests, with an accuracy rate of 83%. The results demonstrate the effectiveness of our proposed EEG-based classification and regression techniques in detecting DMI for robotic help in rehabilitation.The study was conducted with a small sample size, exclusively involving healthy subjects, which is a critical factor to consider. This may limit the generalizability of the results, particularly when populations with motor impairments are taken into account. However, the study offers valuable insights into the potential of the EEG-based models for real-time rehabilitation applications despite this limitation.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2661-8907
2662-995X
2661-8907
DOI:10.1007/s42979-024-03419-7