Enhancing Motor Imagery Classification with Deep Learning: A Focus on Dimensionality Reduction and Temporal Features
Keywords:
Brain computer interface (BCI), Deep Neural network, Feature extraction, Long short term Memory (LSTM), Gated Recurrent Unit (GRU) and Independent component Analysis( ICA).Abstract
The Brain-Computer Interface (BCI) system empowers users to communicate with their environment solely through intent, eliminating the need for muscle reactions. However, Electroencephalography (EEG) datasets are typically small and complex due to cumbersome recording processes. This research aims to provide communication capabilities to individuals with complete paralysis, brain stroke disorders, or those who rely on wheelchairs. EEG signal acquisition often includes common artifacts, introducing noise. To tackle these challenges, this study employs Independent Component Analysis (ICA) and various deep learning algorithms within the BCI system. The dataset is sourced from BCI competition III, featuring signals related to the imagined movement of the tongue and the left small finger, from 278 instances. The research introduces a classification method that involves extracting essential components using ICA and experimenting with diverse deep learning architectures to identify the most effective model. The novelty of this research lies in the process of identifying critical components and integrating them into the deep learning network. A comparative analysis is conducted to contrast classification outcomes with and without dimensionality reduction through ICA. Different deep learning models, including Long Short-Term Memory, Gated Recurrent Unit, and Convolutional Neural Network, are employed to enhance EEG signal processing and classification accuracy compared to traditional classification methods. Experimental results indicate that the Convolutional Neural Network combined with ICA achieves the highest accuracy at 89% with the decrease in hidden layers.
Downloads
References
Jonathan R. Wolpaw, NielsBirbaumer, Dennis J. McFarland, GertPfurtscheller, Theresa M. Vaughan,”Brain-computer nterface for communication and control”,Clinical Neurophysiology (113),(2002), pp767–791.DOI: 10.1016/s1388-2457(02)00057-3.
H.H. Alwasiti, I. Aris, & A. Jantan, “Brain Computer Interface Design and Applications: Challenges and Future,” World Applied Sciences Journal,11(7)(2010),pp.819-825.
RajdeepChatterjee,AnkitaDatta,Debarshi Kumar Sanyal, Swati Banerjee,“Temporal Window based Feature Extraction Technique for Motor-Imagery EEG Signal Classification”,Malaysian Journal of Computer Science, March22, 2021.
Hamidreza Abbaspou,Nasser Mehrshad,Seyyed Mohammad Razavi “Identifying motor imagery activities in brain computer interfaces based on the intelligent selection of most informative timeframe”, Springer Nature Applied journal ,January18,2020.doi.10.1007/s42452-0202020-0.
XiaozhongzGeng,DezhiLi,HanlinChen,PingYu,HuiYan, MengzheYue, “An improved feature extraction algorithm of EEG signals based on motor imagery brain-computer interface”,AlexandriaEngineeringJournal,November1,2021.DOI: 10.7507/10015515.201812049.
Jing-Shan Huang , Yang Li , Bin-Qiang Chen, Chuang Lin and Bin Yao “An Intelligent EEG Classification Methodology Based on Sparse Representation Enhanced Deep Learning Networks”, brief research report rticle,September30,2022.https://doi.org/10.3389/fnins.2020.00808
SihengGao , Jun Yang, Tao Shen and Wen Jiang “A Parallel Feature Fusion Network Combining GRU and CNN for Motor Imagery EEG Decoding”,Brain Science Article,September 13,2022. DOI: 10.3390/brainsci12091233.
Swati Gawhale , Dr.Dhananjay E. Upasani , LeenaChaudhari , Dr.Dhananjay V. Khankal , Jambi Ratna Raja Kumar , Vidyabhushan A. Upadhye , “EEG Signal Processing for the Identification of Sleeping Disorder Using Hybrid Deep Learning with Ensemble Machine Learning Classifier”, International Journal of Intelligent Systems and Applications In Engineering, july 2023,pp 113-129.
Staudemeyer, Ralf & Morris, Eric. “Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks”, September 23, 2019,pp 1-42.
Tian, Juan & Zhang, Zhaochen. (2017). “Research on Algorithm for Feature Extraction and Classification of Motor Imagery EEG Signals”. BIO Web of Conferences. 8. 02013. 10.1051/bioconf/20170802013.
Shubhangigupta, jaipreetkaurbha “Pre-Processing, Feature Extraction And Classification Of EEG Signals For Brain Computer Interface”,journal of emerging technologies and innovative research JETIR 2017, volume 4, issue 05,pp 161-166.
E.Elavarasan, Dr.K.Mani “A Survey on Feature Extraction Techniques” International Journal of Innovative Research in Computer and Communication Engineering, January 2011, volume 3, issue 01, pp 52-55.
M.Kanimozhi, R.Roselin, “A Statistical Approach for Feature Extraction in Brain Computer Interface”, IOSR Journal of Engineering, 2018, pp 90-95.
M.Kanimozhi, R.Roselin, “Statistical Feature Extraction and Classification using Machine Learning Techniques in Brain-Computer Interface”, International Journal of Innovative Technology and Exploring Engineering,January 2020,pp – 1754-1758.
S. Manthandi Periannasamy, Chitra Thangavel, Sahukar Latha, G Vinoda Reddy, S Ramani, Pooja Vitthalrao Phad, S Ravi Chandline, S Gopalakrishnan, “Analysis of Artificial Intelligence Enabled Intelligent Sixth Generation (6G) Wireless Communication Networks”, IEEE International Conference on Data Science and Information System (ICDSIS), pp. 1-8, 2022.
Roma Fayaz, G Vinoda Reddy, M Sujaritha, N Soundiraraj, W Gracy Theresa, Dharmendra Kumar Roy, J Jeffin Gracewell, S Gopalakrishnan, "An Intelligent Harris Hawks Optimization (IHHO) based Pivotal Decision Tree (PDT) Machine Learning Model for Diabetes Prediction", International Journal of Intelligent Systems and Applications in Engineering, Vol. 10, pp 415–423, 2022.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
