Enhanced EEG signal classification in brain computer interfaces using hybrid deep learning models

Abstract Brain-computer interfaces (BCIs) establish a communication pathway between the human brain and external devices by decoding neural signals. This study focuses on enhancing the classification of Motor Imagery (MI) within BCI systems by leveraging advanced machine learning and deep learning t...

Full description

Saved in:
Bibliographic Details
Main Authors: Abir Das, Saurabh Singh, Jaejeung Kim, Tariq Ahamed Ahanger, Anil Audumbar Pise
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-07427-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849344302463844352
author Abir Das
Saurabh Singh
Jaejeung Kim
Tariq Ahamed Ahanger
Anil Audumbar Pise
author_facet Abir Das
Saurabh Singh
Jaejeung Kim
Tariq Ahamed Ahanger
Anil Audumbar Pise
author_sort Abir Das
collection DOAJ
description Abstract Brain-computer interfaces (BCIs) establish a communication pathway between the human brain and external devices by decoding neural signals. This study focuses on enhancing the classification of Motor Imagery (MI) within BCI systems by leveraging advanced machine learning and deep learning techniques. The accurate classification of electroencephalogram (EEG) data is crucial for enhancing BCI performance. The BCI architecture processes electroencephalography signals through three critical stages: data pre-processing, feature extraction, and classification. The research evaluates the performance of five traditional machine learning classifiers- K-Nearest Neighbors (KNN), Support Vector Classifier (SVC), Logistic Regression (LR), Random Forest (RF), and Naive Bayes (NB)-using the “PhysioNet EEG Motor Movement/Imagery Dataset”. This dataset encompasses EEG data from various motor tasks, including both actual and imagined movements. Among the traditional classifiers, Random Forest achieved the highest accuracy of 91%, underscoring its efficacy in motor imagery classification within BCI systems. In addition to conventional approaches, the study also explores deep learning techniques, with Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks yielding accuracies of 88.18% and 16.13%, respectively. However, the proposed hybrid model, which synergistically combines CNN and LSTM, significantly surpasses both traditional machine learning and individual deep learning methods, achieving an exceptional accuracy of 96.06%. This substantial improvement highlights the potential of hybrid deep learning models to advance the state of the art in BCI systems, offering a more robust and precise approach to motor imagery classification.
format Article
id doaj-art-dfde7e732a6c429f99418ff3e1dae1e4
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-dfde7e732a6c429f99418ff3e1dae1e42025-08-20T03:42:41ZengNature PortfolioScientific Reports2045-23222025-07-0115112010.1038/s41598-025-07427-2Enhanced EEG signal classification in brain computer interfaces using hybrid deep learning modelsAbir Das0Saurabh Singh1Jaejeung Kim2Tariq Ahamed Ahanger3Anil Audumbar Pise4JCFS, Endicott College, Woosong UniversityAI and Big Data, Endicott College Woosong UniversityDepartment of Computer Science and Engineering, Chungnam National UniversityDepartment of Management Information Systems, College of Business Administration, Prince Sattam Bin Abdulaziz UniversityDepartment of Computer Science, Cumulus SolutionsAbstract Brain-computer interfaces (BCIs) establish a communication pathway between the human brain and external devices by decoding neural signals. This study focuses on enhancing the classification of Motor Imagery (MI) within BCI systems by leveraging advanced machine learning and deep learning techniques. The accurate classification of electroencephalogram (EEG) data is crucial for enhancing BCI performance. The BCI architecture processes electroencephalography signals through three critical stages: data pre-processing, feature extraction, and classification. The research evaluates the performance of five traditional machine learning classifiers- K-Nearest Neighbors (KNN), Support Vector Classifier (SVC), Logistic Regression (LR), Random Forest (RF), and Naive Bayes (NB)-using the “PhysioNet EEG Motor Movement/Imagery Dataset”. This dataset encompasses EEG data from various motor tasks, including both actual and imagined movements. Among the traditional classifiers, Random Forest achieved the highest accuracy of 91%, underscoring its efficacy in motor imagery classification within BCI systems. In addition to conventional approaches, the study also explores deep learning techniques, with Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks yielding accuracies of 88.18% and 16.13%, respectively. However, the proposed hybrid model, which synergistically combines CNN and LSTM, significantly surpasses both traditional machine learning and individual deep learning methods, achieving an exceptional accuracy of 96.06%. This substantial improvement highlights the potential of hybrid deep learning models to advance the state of the art in BCI systems, offering a more robust and precise approach to motor imagery classification.https://doi.org/10.1038/s41598-025-07427-2BCIClassificationEEGMachine learningDeep learningMotor imagery
spellingShingle Abir Das
Saurabh Singh
Jaejeung Kim
Tariq Ahamed Ahanger
Anil Audumbar Pise
Enhanced EEG signal classification in brain computer interfaces using hybrid deep learning models
Scientific Reports
BCI
Classification
EEG
Machine learning
Deep learning
Motor imagery
title Enhanced EEG signal classification in brain computer interfaces using hybrid deep learning models
title_full Enhanced EEG signal classification in brain computer interfaces using hybrid deep learning models
title_fullStr Enhanced EEG signal classification in brain computer interfaces using hybrid deep learning models
title_full_unstemmed Enhanced EEG signal classification in brain computer interfaces using hybrid deep learning models
title_short Enhanced EEG signal classification in brain computer interfaces using hybrid deep learning models
title_sort enhanced eeg signal classification in brain computer interfaces using hybrid deep learning models
topic BCI
Classification
EEG
Machine learning
Deep learning
Motor imagery
url https://doi.org/10.1038/s41598-025-07427-2
work_keys_str_mv AT abirdas enhancedeegsignalclassificationinbraincomputerinterfacesusinghybriddeeplearningmodels
AT saurabhsingh enhancedeegsignalclassificationinbraincomputerinterfacesusinghybriddeeplearningmodels
AT jaejeungkim enhancedeegsignalclassificationinbraincomputerinterfacesusinghybriddeeplearningmodels
AT tariqahamedahanger enhancedeegsignalclassificationinbraincomputerinterfacesusinghybriddeeplearningmodels
AT anilaudumbarpise enhancedeegsignalclassificationinbraincomputerinterfacesusinghybriddeeplearningmodels