{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T17:45:54Z","timestamp":1789667154280,"version":"4.0.1"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T00:00:00Z","timestamp":1706572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>As an interactive method gaining popularity, brain-computer interfaces (BCIs) aim to facilitate communication between the brain and external devices. Among the various research topics in BCIs, the classification of motor imagery using electroencephalography (EEG) signals has the potential to greatly improve the quality of life for people with disabilities.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>This technology assists them in controlling computers or other devices like prosthetic limbs, wheelchairs, and drones. However, the current performance of EEG signal decoding is not sufficient for real-world applications based on Motor Imagery EEG (MI-EEG). To address this issue, this study proposes an attention-based bidirectional feature pyramid temporal convolutional network model for the classification task of MI-EEG. The model incorporates a multi-head self-attention mechanism to weigh significant features in the MI-EEG signals. It also utilizes a temporal convolution network (TCN) to separate high-level temporal features. The signals are enhanced using the sliding-window technique, and channel and time-domain information of the MI-EEG signals is extracted through convolution.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Additionally, a bidirectional feature pyramid structure is employed to implement attention mechanisms across different scales and multiple frequency bands of the MI-EEG signals. The performance of our model is evaluated on the BCI Competition IV-2a dataset and the BCI Competition IV-2b dataset, and the results showed that our model outperformed the state-of-the-art baseline model, with an accuracy of 87.5 and 86.3% for the subject-dependent, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>In conclusion, the BFATCNet model offers a novel approach for EEG-based motor imagery classification in BCIs, effectively capturing relevant features through attention mechanisms and temporal convolutional networks. Its superior performance on the BCI Competition IV-2a and IV-2b datasets highlights its potential for real-world applications. However, its performance on other datasets may vary, necessitating further research on data augmentation techniques and integration with multiple modalities to enhance interpretability and generalization. Additionally, reducing computational complexity for real-time applications is an important area for future work.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fnbot.2024.1343249","type":"journal-article","created":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T04:31:54Z","timestamp":1706589114000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Bidirectional feature pyramid attention-based temporal convolutional network model for motor imagery electroencephalogram classification"],"prefix":"10.3389","volume":"18","author":[{"given":"Xinghe","family":"Xie","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liyan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shujia","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fusheng","family":"Zha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinggang","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,1,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"5737","DOI":"10.1109\/JIOT.2019.2951365","article-title":"Exploring deep learning models for overhead view multiple object detection","volume":"7","author":"Ahmed","year":"2019","journal-title":"IEEE Internet Things J"},{"key":"B2","doi-asserted-by":"publisher","first-page":"5031","DOI":"10.1109\/TII.2022.3146552","article-title":"From artificial intelligence to explainable artificial intelligence in industry 4.0 a survey on what, how, and where","volume":"18","author":"Ahmed","year":"2022","journal-title":"IEEE Trans. Ind. Inform"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2623","DOI":"10.1145\/3292500.3330701","article-title":"\u201cOptuna: a next-generation hyperparameter optimization framework,","author":"Akiba","year":"2019"},{"key":"B4","doi-asserted-by":"publisher","first-page":"117115","DOI":"10.1109\/ACCESS.2019.2936536","article-title":"Date fruit classification for robotic harvesting in a natural environment using deep learning","volume":"7","author":"Altaheri","year":"2019","journal-title":"IEEE Access"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2249","DOI":"10.1109\/TII.2022.3197419","article-title":"Physics-informed attention temporal convolutional network for EEG-based motor imagery classification","volume":"19","author":"Altaheri","year":"2022","journal-title":"IEEE Trans. Ind. Inform"},{"key":"B6","doi-asserted-by":"publisher","first-page":"14681","DOI":"10.1007\/s00521-021-06352-5","article-title":"Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: a review","volume":"35","author":"Altaheri","year":"2023","journal-title":"Neural Comput. Appl"},{"key":"B7","doi-asserted-by":"publisher","first-page":"995","DOI":"10.3390\/diagnostics12040995","article-title":"A multi-branch convolutional neural network with squeeze-and-excitation attention blocks for EEG-based motor imagery signals classification","volume":"12","author":"Altuwaijri","year":"2022","journal-title":"Diagnostics"},{"key":"B8","doi-asserted-by":"publisher","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":"Amin","year":"2019","journal-title":"Future Gener. Comput. Syst"},{"key":"B9","first-page":"2390","article-title":"\u201cFilter bank common spatial pattern (FBCSP) in brain-computer interface,\u201d","volume-title":"2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","author":"Ang","year":"2008"},{"key":"B10","doi-asserted-by":"publisher","first-page":"39","DOI":"10.3389\/fnins.2012.00039","article-title":"Filter bank common spatial pattern algorithm on BCI competition iv datasets 2a and 2b","volume":"6","author":"Ang","year":"2012","journal-title":"Front. Neurosci"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.01271","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018","journal-title":"arXiv"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1220","DOI":"10.1016\/j.clinph.2003.12.015","article-title":"Optimization of an independent component analysis approach for artifact identification and removal in magnetoencephalographic signals","volume":"115","author":"Barbati","year":"2004","journal-title":"Clin. Neurophysiol"},{"key":"B13","first-page":"1","article-title":"\u201cBCI competition 2008-graz data set a,\u201d","author":"Brunner","year":"2008"},{"key":"B14","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A coefficient of agreement for nominal scales","volume":"20","author":"Cohen","year":"1960","journal-title":"Educ. Psychol. Meas"},{"key":"B15","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.jneumeth.2003.10.009","article-title":"Eeglab: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis","volume":"134","author":"Delorme","year":"2004","journal-title":"J. Neurosci. Methods"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3051996","article-title":"A sliding window common spatial pattern for enhancing motor imagery classification in EEG-BCI","volume":"70","author":"Gaur","year":"2021","journal-title":"IEEE Trans. Instrum. Meas"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-642-02091-9","article-title":"\u201cBrain-computer interfaces: a gentle introduction,\u201d","author":"Graimann","year":"2010"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e12494","DOI":"10.1111\/exsy.12494","article-title":"A novel end-to-end deep learning scheme for classifying multi-class motor imagery electroencephalography signals","volume":"36","author":"Hassanpour","year":"2019","journal-title":"Expert Syst"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1690","DOI":"10.23919\/EUSIPCO.2018.8553378","article-title":"\u201cFast and accurate multiclass inference for MI-BCIS using large multiscale temporal and spectral features,\u201d","author":"Hersche","year":"2018"},{"key":"B20","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1109\/TNSRE.2021.3059166","article-title":"Dynamic joint domain adaptation network for motor imagery classification","volume":"29","author":"Hong","year":"2021","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1109\/TII.2018.2875149","article-title":"Automatic fruit classification using deep learning for industrial applications","volume":"15","author":"Hossain","year":"2018","journal-title":"IEEE Trans. Ind. Inform"},{"key":"B22","doi-asserted-by":"publisher","first-page":"7132","DOI":"10.1109\/CVPR.2018.00745","article-title":"\u201cSqueeze-and-excitation networks,\u201d","author":"Hu","year":"2018"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.3389\/fnins.2019.01243","article-title":"An EEG-\/EOG-based hybrid brain-computer interface: application on controlling an integrated wheelchair robotic arm system","volume":"13","author":"Huang","year":"2019","journal-title":"Front. Neurosci"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2958","DOI":"10.1109\/SMC42975.2020.9283028","article-title":"\u201cEEG-TCNeT: an accurate temporal convolutional network for embedded motor-imagery brain-machine interfaces,\u201d","author":"Ingolfsson","year":"2020"},{"key":"B25","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1109\/LSP.2009.2022557","article-title":"Composite common spatial pattern for subject-to-subject transfer","volume":"16","author":"Kang","year":"2009","journal-title":"IEEE Signal Process. Lett"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e375","DOI":"10.7717\/peerj-cs.375","article-title":"Optical+: a frequency-based deep learning scheme for recognizing brain wave signals","volume":"7","author":"Kumar","year":"2021","journal-title":"Peerj Comput. Sci"},{"key":"B27","doi-asserted-by":"publisher","first-page":"056013","DOI":"10.1088\/1741-2552\/aace8c","article-title":"EEGNET: a compact convolutional neural network for EEG-based brain-computer interfaces","volume":"15","author":"Lawhern","year":"2018","journal-title":"J. Neural Eng"},{"key":"B28","first-page":"1","author":"Leeb","year":"2008","journal-title":"BCI Competition 2008-Graz Data Set b"},{"key":"B29","doi-asserted-by":"publisher","first-page":"2615","DOI":"10.1109\/TNSRE.2020.3037326","article-title":"A multi-scale fusion convolutional neural network based on attention mechanism for the visualization analysis of EEG signals decoding","volume":"28","author":"Li","year":"2020","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng"},{"key":"B30","doi-asserted-by":"publisher","first-page":"197","DOI":"10.3390\/brainsci11020197","article-title":"A densely connected multi-branch 3D convolutional neural network for motor imagery EEG decoding","volume":"11","author":"Liu","year":"2021","journal-title":"Brain Sci"},{"key":"B31","volume-title":"A BCI Challenge for the Signal Processing Community: Considering the User in the Loop","author":"Lotte","year":"2018"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12859-018-2365-1","article-title":"Exploring spatial-frequency-sequential relationships for motor imagery classification with recurrent neural network","volume":"19","author":"Luo","year":"2018","journal-title":"BMC Bioinform"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1508.04025","article-title":"Effective approaches to attention-based neural machine translation","author":"Luong","year":"2015","journal-title":"arXiv"},{"key":"B34","doi-asserted-by":"publisher","first-page":"102826","DOI":"10.1016\/j.bspc.2021.102826","article-title":"Electroencephalography-based motor imagery classification using temporal convolutional network fusion","volume":"69","author":"Musallam","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"B35","doi-asserted-by":"publisher","first-page":"57255","DOI":"10.1109\/ACCESS.2022.3178100","article-title":"Deep adversarial domain adaptation with few-shot learning for motor-imagery brain-computer interface","volume":"10","author":"Phunruangsakao","year":"2022","journal-title":"IEEE Access"},{"key":"B36","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.neuroimage.2014.10.049","article-title":"Removing speech artifacts from electroencephalographic recordings during overt picture naming","volume":"105","author":"Porcaro","year":"2015","journal-title":"Neuroimage"},{"key":"B37","doi-asserted-by":"publisher","first-page":"62719","DOI":"10.1109\/ACCESS.2021.3073786","article-title":"Digital audio forensics: microphone and environment classification using deep learning","volume":"9","author":"Qamhan","year":"2021","journal-title":"IEEE Access"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10916-018-1106-3","article-title":"An automatic channel selection approach for ica-based motor imagery brain computer interface","volume":"42","author":"Ruan","year":"2018","journal-title":"J. Med. Syst"},{"key":"B39","doi-asserted-by":"publisher","first-page":"5391","DOI":"10.1002\/hbm.23730","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"38","author":"Schirrmeister","year":"2017","journal-title":"Hum. Brain Mapp"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TNSRE.2023.3241846","article-title":"Improved domain adaptation network based on Wasserstein distance for motor imagery EEG classification","volume":"31","author":"She","year":"2023","journal-title":"IEEE Trans Neural Syst. Rehabil. Eng"},{"key":"B41","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.neuroscience.2023.07.020","article-title":"Classification algorithm for electroencephalogram-based motor imagery using hybrid neural network with spatio-temporal convolution and multi-head attention mechanism","volume":"527","author":"Shi","year":"2023","journal-title":"Neuroscience"},{"key":"B42","doi-asserted-by":"publisher","first-page":"2767","DOI":"10.1109\/TNSRE.2023.3285309","article-title":"Global adaptive transformer for cross-subject enhanced EEG classification","volume":"31","author":"Song","year":"2023","journal-title":"IEEE Trans. Neural Sys. Rehabil. Eng"},{"key":"B43","doi-asserted-by":"publisher","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":"Tang","year":"2020","journal-title":"Expert Syst. Appl"},{"key":"B44","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1109\/ACCT.2015.72","article-title":"\u201cEEG signal analysis for BCI interface: a review,\u201d","author":"Vaid","year":"2015"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B46","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","article-title":"\u201cCBAM: convolutional block attention module,\u201d","author":"Woo","year":"2018"},{"key":"B47","doi-asserted-by":"publisher","first-page":"6084","DOI":"10.1109\/ACCESS.2018.2889093","article-title":"Wavelet transform time-frequency image and convolutional network-based motor imagery EEG classification","volume":"7","author":"Xu","year":"2018","journal-title":"IEEE Access"},{"key":"B48","doi-asserted-by":"publisher","first-page":"3496","DOI":"10.3390\/s20123496","article-title":"Recognition of EEG signal motor imagery intention based on deep multi-view feature learning","volume":"20","author":"Xu","year":"2020","journal-title":"Sensors"},{"key":"B49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TNNLS.2023.3329525.","article-title":"Effective surrogate gradient learning with high-order information bottleneck for spike-based machine intelligence","author":"Yang","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B50","doi-asserted-by":"publisher","first-page":"126240","DOI":"10.1016\/j.neucom.2023.126240","article-title":"Spike-driven multi-scale learning with hybrid mechanisms of spiking dendrites","volume":"542","author":"Yang","year":"2023","journal-title":"Neurocomputing"},{"key":"B51","doi-asserted-by":"publisher","first-page":"455","DOI":"10.3390\/e24040455","article-title":"Robust spike-based continual meta-learning improved by restricted minimum error entropy criterion","volume":"24","author":"Yang","year":"2022","journal-title":"Entropy"},{"key":"B52","doi-asserted-by":"publisher","first-page":"2570","DOI":"10.1109\/JBHI.2020.2967128","article-title":"Motor imagery classification via temporal attention cues of graph embedded EEG signals","volume":"24","author":"Zhang","year":"2020","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"B53","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1109\/TNNLS.2020.3010780","article-title":"Deep representation-based domain adaptation for nonstationary EEG classification","volume":"32","author":"Zhao","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1343249\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,30]],"date-time":"2024-01-30T04:31:59Z","timestamp":1706589119000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2024.1343249\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,30]]},"references-count":53,"alternative-id":["10.3389\/fnbot.2024.1343249"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2024.1343249","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,30]]},"article-number":"1343249"}}