{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T22:52:18Z","timestamp":1787611938713,"version":"build-2736575974"},"reference-count":61,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T00:00:00Z","timestamp":1736985600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>In recent years, the utilization of motor imagery (MI) signals derived from electroencephalography (EEG) has shown promising applications in controlling various devices such as wheelchairs, assistive technologies, and driverless vehicles. However, decoding EEG signals poses significant challenges due to their complexity, dynamic nature, and low signal-to-noise ratio (SNR). Traditional EEG pattern recognition algorithms typically involve two key steps: feature extraction and feature classification, both crucial for accurate operation. In this work, we propose a novel method that addresses these challenges by employing empirical mode decomposition (EMD) for feature extraction and a parallel convolutional neural network (PCNN) for feature classification. This approach aims to mitigate non-stationary issues, improve performance speed, and enhance classification accuracy. We validate the effectiveness of our proposed method using datasets from the BCI competition IV, specifically datasets 2a and 2b, which contain motor imagery EEG signals. Our method focuses on identifying two- and four-class motor imagery EEG signal classifications. Additionally, we introduce a transfer learning technique to fine-tune the model for individual subjects, leveraging important features extracted from a group dataset. Our results demonstrate that the proposed EMD-PCNN method outperforms existing approaches in terms of classification accuracy. We conduct both qualitative and quantitative analyses to evaluate our method. Qualitatively, we employ confusion matrices and various performance metrics such as specificity, sensitivity, precision, accuracy, recall, and f1-score. Quantitatively, we compare the classification accuracies of our method with those of existing approaches. Our findings highlight the superiority of the proposed EMD-PCNN method in accurately classifying motor imagery EEG signals. The enhanced performance and robustness of our method underscore its potential for broader applicability in real-world scenarios.<\/jats:p>","DOI":"10.1371\/journal.pone.0311942","type":"journal-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T13:53:43Z","timestamp":1737035623000},"page":"e0311942","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":10,"title":["Parallel convolutional neural network and empirical mode decomposition for high accuracy in motor imagery EEG signal classification"],"prefix":"10.1371","volume":"20","author":[{"given":"Jaipriya","family":"D.","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6755-6631","authenticated-orcid":true,"given":"Sriharipriya","family":"K. C.","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,1,16]]},"reference":[{"key":"pone.0311942.ref001","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/S0278-2626(03)00036-8","article-title":"\"Learning to control brain activity: A review of the production and control of EEG components for driving brain\u2013computer interface (BCI) systems.\"","volume":"3","author":"Eleanor A. Curran","year":"2003","journal-title":"Brain and cognition 51,"},{"key":"pone.0311942.ref002","first-page":"1","article-title":"Efficacy of motor imagery in post-stroke rehabilitation: a systematic review","volume":"1","author":"Andrea Zimmermann-Schlatter","year":"2008","journal-title":"Journal of neuroengineering and rehabilitation 5, no"},{"key":"pone.0311942.ref003","doi-asserted-by":"crossref","first-page":"364","DOI":"10.14336\/AD.2016.1012","article-title":"Motor imagery-based rehabilitation: potential neural correlates and clinical application for functional recovery of motor deficits after stroke","volume":"3","author":"Yanna Tong","year":"2017","journal-title":"Aging and disease 8"},{"key":"pone.0311942.ref004","article-title":"Motor imagery training on muscle strength and gait performance in ambulant stroke subjects-a randomized clinical trial","volume":"3","author":"Kumar","year":"2016","journal-title":"Journal of clinical and diagnostic research: JCDR 10"},{"key":"pone.0311942.ref005","doi-asserted-by":"crossref","first-page":"2161","DOI":"10.3390\/app12042161","article-title":"The application of integration of EEG signals for authorial classification algorithms in implementation for a mobile robot control using movement imagery\u2014Pilot study","volume":"4","author":"Dawid Pawu\u015b","year":"2022","journal-title":"Applied Sciences 12"},{"key":"pone.0311942.ref006","first-page":"2620","article-title":"On the use of convolutional neural networks and augmented CSP features for multi-class motor imagery of EEG signals classification","author":"Huijuan Yang","year":"2015","journal-title":"2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC),"},{"key":"pone.0311942.ref007","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1109\/ICCCA49541.2020.9250907","article-title":"A novel deep learning approach for classification of COVID-19 images","author":"Malaya Kumar Nath","year":"2020","journal-title":"In 2020 IEEE 5th international conference on computing communication and automation (ICCCA),"},{"key":"pone.0311942.ref008","doi-asserted-by":"crossref","first-page":"1010770","DOI":"10.3389\/fncom.2022.1010770","article-title":"A comparative analysis of masking empirical mode decomposition and a neural network with feed-forward and back propagation along with masking empirical mode decomposition to improve the classification performance for a reliable brain-computer interface","volume":"16","author":"D. Jaipriya","year":"2022","journal-title":"Frontiers in Computational Neuroscience"},{"key":"pone.0311942.ref009","doi-asserted-by":"crossref","first-page":"4485","DOI":"10.3390\/s20164485","article-title":"Data augmentation for motor imagery signal classification based on a hybrid neural network","volume":"16","author":"Kai Zhang","year":"2020","journal-title":"Sensors 20"},{"key":"pone.0311942.ref010","doi-asserted-by":"crossref","first-page":"148","DOI":"10.1016\/j.bspc.2018.02.021","article-title":"Automatic ocular artifacts removal in EEG using deep learning","volume":"43","author":"Banghua Yang","year":"2018","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0311942.ref011","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1080\/10447318.2021.1921482","article-title":"Efficient quadcopter flight control using hybrid SSVEP+ P300 visual brain computer interface","volume":"1","author":"Deepak Kapgate","year":"2022","journal-title":"International Journal of Human\u2013Computer Interaction 38"},{"key":"pone.0311942.ref012","doi-asserted-by":"crossref","first-page":"15945","DOI":"10.1109\/ACCESS.2019.2895133","article-title":"A novel deep learning approach with data augmentation to classify motor imagery signals","volume":"7","author":"Zhiwen Zhang","year":"2019","journal-title":"IEEE Access"},{"key":"pone.0311942.ref013","doi-asserted-by":"crossref","first-page":"645952","DOI":"10.3389\/fnhum.2021.645952","article-title":"Data augmentation: using channel-level recombination to improve classification performance for motor imagery EEG","volume":"15","author":"Yu Pei","year":"2021","journal-title":"Frontiers in Human Neuroscience"},{"key":"pone.0311942.ref014","doi-asserted-by":"crossref","first-page":"100003","DOI":"10.1016\/j.array.2019.100003","article-title":"Signal processing techniques for motor imagery brain computer interface: A review","volume":"1","author":"Swati Aggarwal","year":"2019","journal-title":"Array"},{"key":"pone.0311942.ref015","doi-asserted-by":"crossref","first-page":"2936","DOI":"10.1109\/TBME.2010.2082540","article-title":"Regularized common spatial pattern with aggregation for EEG classification in small-sample setting","volume":"12","author":"Haiping Lu","year":"2010","journal-title":"IEEE transactions on Biomedical Engineering 57,"},{"key":"pone.0311942.ref016","doi-asserted-by":"crossref","first-page":"8659","DOI":"10.1016\/j.eswa.2010.06.065","article-title":"EEG signal classification using PCA, ICA, LDA and support vector machines","volume":"12","author":"Abdulhamit Subasi","year":"2010","journal-title":"Expert systems with applications 37, no"},{"key":"pone.0311942.ref017","first-page":"2256","article-title":"Sparse Bayesian classification of EEG for brain\u2013computer interface","volume":"11","author":"Yu Zhang","year":"2015","journal-title":"IEEE transactions on neural networks and learning systems 27,"},{"issue":"5","key":"pone.0311942.ref018","first-page":"1","article-title":"Relevant feature selection from a combination of spectral-temporal and spatial features for classification of motor imagery EEG","volume":"42","author":"Jyoti Singh Kirar","year":"2018","journal-title":"Journal of medical systems"},{"key":"pone.0311942.ref019","first-page":"1","article-title":"An empirical mode decomposition-based filtering method for classification of motor-imagery EEG signals for enhancing brain-computer interface","author":"Pramod Gaur","year":"2015","journal-title":"2015 International Joint Conference on Neural Networks (IJCNN),"},{"key":"pone.0311942.ref020","first-page":"2","article-title":"Improving motor imagery classification with a new BCI design using neuro-fuzzy S-dFasArt","volume":"1","author":"Jose-Manuel Cano-Izquierdo","year":"2011","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering 20,"},{"key":"pone.0311942.ref021","first-page":"938","article-title":"EEG feature extraction and classification in multiclass multiuser motor imagery brain computer interface u sing Bayesian Network and ANN","author":"G. S. Sagee","year":"2017","journal-title":"In 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT),"},{"key":"pone.0311942.ref022","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1109\/TENCONSpring.2014.6863026","article-title":"Neural network-based three-class motor imagery classification using time-domain features for BCI applications","author":"Mahyar Hamedi","year":"2014","journal-title":"In 2014 IEEE Region 10 Symposium"},{"key":"pone.0311942.ref023","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1016\/j.neucom.2015.03.041","article-title":"Classification of mental tasks from EEG data using backtracking search optimization based neural classifier","volume":"166","author":"Saurabh Kumar Agarwal","year":"2015","journal-title":"Neurocomputing"},{"issue":"2019","key":"pone.0311942.ref024","first-page":"3197","article-title":"A novel MI-EEG imaging with the location information of electrodes","volume":"8","author":"Ming-Ai Li","journal-title":"IEEE Access"},{"key":"pone.0311942.ref025","first-page":"1","article-title":"Deep convolutional neural network for decoding motor imagery-based brain computer interface","author":"Jin Zhang","year":"2017","journal-title":"2017 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)"},{"key":"pone.0311942.ref026","doi-asserted-by":"crossref","first-page":"2736","DOI":"10.1109\/EUSIPCO.2015.7362882","article-title":"Parallel convolutional-linear neural snetwork for motor imagery classification","author":"Siavash Sakhavi","year":"2015","journal-title":"2015 23rd European Signal Processing Conference (EUSIPCO),"},{"key":"pone.0311942.ref027","first-page":"1","article-title":"Deep recurrent spatio-temporal neural network for motor imagery based BCI","author":"Wonjun Ko","year":"2018","journal-title":"In 2018 6th International Conference on Brain-Computer Interface (BCI),"},{"key":"pone.0311942.ref028","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1038\/nn947","article-title":"Connecting cortex to machines: recent advances in brain interfaces","volume":"11","author":"John P. Donoghue","year":"2002","journal-title":"Nature neuroscience 5,"},{"key":"pone.0311942.ref029","first-page":"14","article-title":"Brain-machine interface: Instant neural control of a movement signal","volume":"416","author":"J. P. Donoghue","year":"2002","journal-title":"Nature"},{"issue":"2012","key":"pone.0311942.ref030","first-page":"53","article-title":"Applying evolution strategies to preprocessing EEG signals for brain\u2013computer interfaces","volume":"215","author":"Ricardo Aler","journal-title":"Information Sciences"},{"key":"pone.0311942.ref031","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1177\/107385849900500211","article-title":"Slow cortical potentials: plasticity, operant control, and behavioral effects","volume":"2","author":"Niels Birbaumer","year":"1999","journal-title":"The Neuroscientist 5"},{"key":"pone.0311942.ref032","article-title":"Features extraction techniques of EEG signal for BCI applications","author":"Suleiman","year":"2007","journal-title":"Faculty of Computer and Information Engineering Department College of Electronics Engineering, University of Mosul, Iraq"},{"key":"pone.0311942.ref033","article-title":"Computational EEG Analysis","author":"Chang-Hwan Im","year":"2018","journal-title":"Springer Singapore"},{"key":"pone.0311942.ref034","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1007\/s42600-023-00321-8","article-title":"Predicting the tasks of disabled persons using deep learning-based motor imagery model in BCI applications","volume":"4","author":"Nayak","year":"2023","journal-title":"Research on Biomedical Engineering 39"},{"key":"pone.0311942.ref035","first-page":"158","article-title":"Deep convolutional neural networks and power spectral density features for motor imagery classification of EEG signals","volume":"15\u201320","author":"A. F. P\u00e9rez-Zapata","year":"2018","journal-title":"Augmented Cognition: Intelligent Technologies: 12th International Conference, AC 2018, Held as Part of HCI International 2018, Las Vegas, NV, USA,"},{"key":"pone.0311942.ref036","first-page":"6084","article-title":"Wavelet transform time-frequency image and convolutional network-based motor imagery EEG classification","volume":"7","author":"Baoguo Xu","year":"2018","journal-title":"Ieee Access"},{"key":"pone.0311942.ref037","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1016\/j.neunet.2019.09.037","article-title":"Spiking Neural Networks applied to the classification of motor tasks in EEG signals","volume":"122","author":"G.CD.A Virgilio","year":"2019","journal-title":"Neural Networks: the Official Journal of the International Neural Network Society"},{"key":"pone.0311942.ref038","first-page":"1","article-title":"Brain Computer Interface-Based Signal Processing Techniques for Feature Extraction and Classification of Motor Imagery Using EEG: A Literature Review","author":"D. Jaipriya","year":"2023","journal-title":"Biomedical Materials & Devices"},{"key":"pone.0311942.ref039","first-page":"1023","article-title":"Multi-scale feature fusion convolutional neural network for concurrent segmentation of left ventricle and myocardium in cardiac mr images","volume":"5","author":"Lin Qi","year":"2020","journal-title":"Journal of Medical Imaging and Health Informatics 10"},{"key":"pone.0311942.ref040","first-page":"2022","article-title":"A multi-scale fusion CNN model based on adaptive transfer learning for multi-class MI-classification in BCI system","author":"Arunabha M. Roy","year":"2022","journal-title":"BioRxiv"},{"key":"pone.0311942.ref041","doi-asserted-by":"crossref","first-page":"4156","DOI":"10.3390\/s22114156","article-title":"Unsupervised domain adaptive 1D-CNN for fault diagnosis of bearing","volume":"11","author":"Xiaorui Shao","year":"2022","journal-title":"Sensors 22"},{"key":"pone.0311942.ref042","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1109\/TNSRE.2011.2116805","article-title":"Time-frequency analysis of EEG asymmetry using bivariate empirical mode decomposition","volume":"4","author":"Cheolsoo Park","year":"2011","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering 19"},{"key":"pone.0311942.ref043","first-page":"1457","article-title":"Classification of motor imagery movements using multivariate empirical mode decomposition and short time Fourier transform based hybrid method","volume":"3","author":"Syed Khairul Bashar","year":"2016","journal-title":"Engineering science and technologyan international journal 19,"},{"key":"pone.0311942.ref044","doi-asserted-by":"crossref","first-page":"113285","DOI":"10.1016\/j.eswa.2020.113285","article-title":"Motor imagery EEG recognition based on conditional optimization empirical mode decomposition and multi-scale convolutional neural network","volume":"149","author":"Xianlun Tang","year":"2020","journal-title":"Expert Systems with Applications"},{"key":"pone.0311942.ref045","doi-asserted-by":"crossref","first-page":"1477","DOI":"10.1016\/j.neucom.2014.10.038","article-title":"Extracting features from phase space of EEG signals in brain\u2013computer interfaces","volume":"151","author":"Yonghui Fang","year":"2015","journal-title":"Neurocomputing"},{"key":"pone.0311942.ref046","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1016\/j.future.2019.06.027","article-title":"Deep Learning for EEG motor imagery classification based on multi-layer CNNs feature fusion","volume":"101","author":"Syed Umar Amin","year":"2019","journal-title":"Future Generation computer systems"},{"key":"pone.0311942.ref047","first-page":"016025","article-title":"HS-CNN: a CNN with hybrid convolution scale for EEG motor imagery classification","volume":"1","author":"Guanghai Dai","year":"2020","journal-title":"Journal of neural engineering 17"},{"key":"pone.0311942.ref048","first-page":"016073","article-title":"DWT and CNN based multi-class motor imagery electroencephalographic signal recognition","volume":"1","author":"Xunguang Ma","year":"2020","journal-title":"Journal of neural engineering 17,"},{"key":"pone.0311942.ref049","doi-asserted-by":"crossref","first-page":"066004","DOI":"10.1088\/1741-2552\/ab3471","article-title":"A novel hybrid deep learning scheme for four-class motor imagery classification","volume":"6","author":"Ruilong Zhang","year":"2019","journal-title":"Journal of neural engineering 16"},{"key":"pone.0311942.ref050","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1109\/86.712230","article-title":"Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters","volume":"3","author":"Gert Pfurtscheller","year":"1998","journal-title":"IEEE transactions on Rehabilitation Engineering 6,"},{"key":"pone.0311942.ref051","first-page":"39","article-title":"Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b","volume":"6","author":"Kai Keng Ang","year":"2012","journal-title":"Frontiers in neuroscience"},{"key":"pone.0311942.ref052","first-page":"016003","article-title":"A novel deep learning approach for classification of EEG motor imagery signals","volume":"1","author":"Yousef Rezaei Tabar","year":"2016","journal-title":"Journal of neural engineering 14"},{"key":"pone.0311942.ref053","doi-asserted-by":"crossref","first-page":"056013","DOI":"10.1088\/1741-2552\/aace8c","article-title":"EEGNet: a compact convolutional neural network for EEG-based brain\u2013computer interfaces","volume":"5","author":"Vernon J. Lawhern","year":"2018","journal-title":"Journal of neural engineering 15,"},{"key":"pone.0311942.ref054","doi-asserted-by":"crossref","first-page":"5391","DOI":"10.1002\/hbm.23730","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"11","author":"Robin Tibor Schirrmeister","year":"2017","journal-title":"Human brain mapping 38,"},{"key":"pone.0311942.ref055","doi-asserted-by":"crossref","first-page":"5619","DOI":"10.1109\/TNNLS.2018.2789927","article-title":"Learning temporal information for brain-computer interface using convolutional neural networks","volume":"11","author":"Siavash Sakhavi","year":"2018","journal-title":"IEEE transactions on neural networks and learning systems 29, no"},{"key":"pone.0311942.ref056","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1016\/j.bspc.2016.09.007","article-title":"Comparison of signal decomposition methods in classification of EEG signals for motor-imagery BCI system","volume":"31","author":"Jasmin Kevric","year":"2017","journal-title":"Biomedical Signal Processing and Control"},{"issue":"2021","key":"pone.0311942.ref057","first-page":"145","article-title":"Optimization of parameters for improving the performance of EEG-based BCI system","volume":"7","author":"Mandeep Kaur Ghumman","journal-title":"Journal of Reliable Intelligent Environments"},{"key":"pone.0311942.ref058","doi-asserted-by":"crossref","first-page":"103101","DOI":"10.1016\/j.bspc.2021.103101","article-title":"Motor imagery classification in brain-machine interface with machine learning algorithms: Classical approach to multi-layer perceptron model","volume":"71","author":"Rahul Sharma","year":"2022","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0311942.ref059","doi-asserted-by":"crossref","first-page":"103496","DOI":"10.1016\/j.bspc.2022.103496","article-title":"An efficient multi-scale CNN model with intrinsic feature integration for motor imagery EEG subject classification in brain-machine interfaces","volume":"74","author":"Arunabha M. Roy","year":"2022","journal-title":"Biomedical Signal Processing and Control"},{"key":"pone.0311942.ref060","doi-asserted-by":"crossref","first-page":"105347","DOI":"10.1016\/j.engappai.2022.105347","article-title":"Adaptive transfer learning-based multiscale feature fused deep convolutional neural network for EEG MI multiclassification in brain\u2013computer interface","volume":"116","author":"Arunabha M. Roy","year":"2022","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"pone.0311942.ref061","doi-asserted-by":"crossref","first-page":"1932","DOI":"10.3390\/s23041932","article-title":"Classification of Motor Imagery EEG Signals Based on Data Augmentation and Convolutional Neural Networks","volume":"4","author":"Yu Xie","year":"2023","journal-title":"Sensors 23"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0311942","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T13:54:07Z","timestamp":1737035647000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0311942"}},"subtitle":[],"editor":[{"given":"Saeed","family":"Mian Qaisar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,1,16]]},"references-count":61,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1,16]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0311942","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,16]]}}}