Imagen de Portada

Optimization of EEG-based wheelchair control: machine learning, feature selection, outlier management, and explainable AI

Guardado en:
Publicado en:Journal of Big Data vol. 12, no. 1 (Jul 2025), p. 175
Autor principal: Hamed, Amr M.
Otros Autores: Attia, Abdel-Fattah, El-Behery, Heba
Publicado:
Springer Nature B.V.
Materias:
Recall
Accuracy
Outliers (statistics)
Machine learning
Deep learning
Datasets
Classification
Wavelet transforms
Wheelchairs
Human-computer interface
Fourier transforms
Brain research
Optimization
Signal processing
Adaptive technology
Feature selection
Electroencephalography
Correlation analysis
Algorithms
Explainable artificial intelligence
Ensemble learning
Artificial intelligence
Big Data
Interfaces
Recursion
Brain
Models
Navigation
Control systems
Elimination
Public relations
Thresholds
Trees
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:Classifying Electroencephalogram (EEG) signals for wheelchair navigation presents significant challenges due to high dimensionality, noise, outliers, and class imbalances. This study proposes an optimized classification framework that evaluates ten machine learning (ML) models, emphasizing ensemble methods, feature selection (FS), and outlier utilization. The dataset, comprising 2869 samples and 141 features, was processed using Recursive Feature Elimination (RFE) and correlation thresholds (CTs), achieving a peak accuracy of 69% with Extra Trees after FS. Notably, training on outlier-only data yielded even higher accuracy (Extra Trees: 82%), underscoring the value of outliers in enhancing class separability. Receiver Operating Characteristic–Precision Recall (ROC-PR) curve analysis confirmed that Extra Trees achieved a ROC AUC (Area Under Curve) of 0.92 and PR AUC of 0.82 for the best-classified movement command, while other models exhibited lower precision-recall (PR) balance. This approach, complemented by explainability techniques, offers a robust solution for EEG-based wheelchair control systems and paves the way for interpretable brain-computer interfaces (BCIs).
ISSN:2196-1115
DOI:10.1186/s40537-025-01238-y
Fuente:ABI/INFORM Global