{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T06:00:42Z","timestamp":1785477642448,"version":"3.56.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376044"],"award-info":[{"award-number":["62376044"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Fatigue is a critical factor contributing to operational errors, traffic accidents, and psychological disorders. A major challenge in current fatigue detection lies in the difficulty of clearly identifying fatigue-related neural channels in the brain, which hinders the accurate extraction of effective features from high-dimensional electroencephalography (EEG) signals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study proposes the AXELLSTM fatigue detection framework, an EEG-based cross-subject fatigue detection framework that integrates interpretable feature selection with efficient temporal modeling. Specifically, a nested leave-one-subject-out (LOSO) validation strategy was adopted to evaluate cross-subject generalization and reduce potential data leakage during feature and channel selection. Within each LOSO fold, ANOVA and XGBoost were first used to identify discriminative fatigue-related features, followed by an L1-regularized sparse selection model to estimate channel importance. Furthermore, an EfficientLSTM model was designed by integrating a feature compression module, bidirectional long short-term memory network, channel attention, and temporal attention mechanisms to capture sequence-level EEG temporal representations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The results showed that eight features, including mean, RMS, zero-crossing rate, gamma power, beta power, standard deviation, variance, and peak-to-peak value, were consistently selected across all LOSO folds. In addition, 18 EEG channels, including F8, AF8, TP8, F2, Fp1, F4, FT10, F6, Fz, P7, FT9, O1, C5, FT8, CP4, F3, FC6, and P3, were stably retained, suggesting that fatigue-related EEG information is distributed across frontal, frontopolar, frontotemporal, parietal, and occipital regions. Under the LOSO protocol, EfficientLSTM achieved an accuracy of 0.7454 \u00b1 0.2147, balanced accuracy of 0.7436 \u00b1 0.2139, and Macro-F1 of 0.7143 \u00b1 0.2452, with 0.1959 M parameters, a model size of 0.7474 MB, and 3.7069 M FLOPs. Compared with the baseline models, EfficientLSTM obtained the highest average Macro-F1 and showed a favorable balance between cross-subject recognition performance, model complexity, and temporal modeling capability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings indicate that the proposed AXELLSTM framework provides an interpretable and computationally efficient solution for EEG-based fatigue detection and offers potential support for the development of portable fatigue monitoring systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnins.2026.1903252","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T05:37:46Z","timestamp":1785476266000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An EEG-based fatigue detection framework integrating interpretable feature selection and efficient temporal modeling"],"prefix":"10.3389","volume":"20","author":[{"given":"Xiaohong","family":"Jiang","sequence":"first","affiliation":[{"name":"College of Traffic and Transportation, Chongqing Jiaotong University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Chongqing Jiaotong University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Chongqing University of Posts and Telecommunications","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyang","family":"Chu","sequence":"additional","affiliation":[{"name":"School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Wu","sequence":"additional","affiliation":[{"name":"The First Affiliated Hospital of Chongqing Medical University","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinbo","family":"Gao","sequence":"additional","affiliation":[{"name":"Xidian University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"790292","DOI":"10.3389\/fphys.2021.790292","article-title":"Fatigue monitoring through wearables: A state-of-the-art review.","volume":"12","author":"Ad\u00e3o Martins","year":"2021","journal-title":"Front. Physiol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"19743","DOI":"10.1109\/TITS.2021.3134222","article-title":"Intelligent driver drowsiness detection for traffic safety based on multi CNN deep model and facial subsampling.","volume":"23","author":"Ahmed","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"B3","doi-asserted-by":"publisher","first-page":"29","DOI":"10.3109\/00207459008994241","article-title":"\u2018Subjective and objective sleepiness in the active individual\u2019.","volume":"52","author":"\u00c5kerstedt","year":"1990","journal-title":"Int. J. Neurosci."},{"key":"B4","unstructured":"Germany BP actiCHamp 64-Channel EEG Acquisition System.\n          \n          2023"},{"key":"B5","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1007\/s10115-012-0487-8","article-title":"A review of feature selection methods on synthetic data.","volume":"34","author":"Bol\u00f3n-Canedo","year":"2013","journal-title":"Knowl. Inf. Syst."},{"key":"B6","doi-asserted-by":"publisher","first-page":"109284","DOI":"10.1016\/j.bspc.2025.109284","article-title":"Brain power mapping with optimized deep learning for EEG-based pilot fatigue detection.","volume":"114","author":"Chen","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"B7","first-page":"785","article-title":"XGBoost: A scalable tree boosting system","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)","author":"Chen","year":"2016"},{"key":"B8","doi-asserted-by":"crossref","first-page":"1724","DOI":"10.3115\/v1\/D14-1179","article-title":"Learning phrase representations using RNN encoder-decoder for statistical machine translation","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Cho","year":"2014"},{"key":"B9","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks.","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"B10","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1109\/TCDS.2019.2963476","article-title":"Detecting fatigue status of pilots based on deep learning network using EEG signals.","volume":"13","author":"Deng","year":"2020","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"B11","first-page":"253","article-title":"Sustained attention performance during sleep deprivation: Evidence of state instability.","volume":"139","author":"Doran","year":"2001","journal-title":"Arch. Italiennes Biol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"4624","DOI":"10.1038\/s41598-024-55399-6","article-title":"When temporal attention interacts with expectation.","volume":"14","author":"Duyar","year":"2024","journal-title":"Sci. Rep."},{"key":"B13","doi-asserted-by":"publisher","first-page":"2755","DOI":"10.1109\/TNNLS.2018.2886414","article-title":"EEG-based spatio-temporal convolutional neural network for driver fatigue evaluation.","volume":"30","author":"Gao","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"B14","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/s12559-026-10585-8","article-title":"EmoDLNet: End-to-end multi-scale spatio-temporal deep learning for EEG-based emotion recognition in affective human-computer interaction.","volume":"18","author":"Geda","year":"2026","journal-title":"Cogn. Comput."},{"key":"B15","doi-asserted-by":"publisher","first-page":"33226","DOI":"10.1038\/s41598-025-18554-1","article-title":"An improved feature extraction algorithm for EEG-based driving fatigue recognition.","volume":"15","author":"Geng","year":"2025","journal-title":"Sci. Rep."},{"key":"B16","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1007\/978-3-642-24797-2_4","article-title":"Long short-term memory","volume-title":"Supervised Sequence Labelling with Recurrent Neural Networks","author":"Graves","year":"2012"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1621638","DOI":"10.3389\/fnins.2025.1621638","article-title":"Assessment of flight fatigue using heart rate variability and machine learning approaches.","volume":"19","author":"Guo","year":"2025","journal-title":"Front. Neurosci."},{"key":"B18","doi-asserted-by":"publisher","first-page":"2139","DOI":"10.1038\/s41598-025-86234-1","article-title":"A hybrid critical channels and optimal feature subset selection framework for EEG fatigue recognition.","volume":"15","author":"Guo","year":"2025","journal-title":"Sci. Rep."},{"key":"B19","first-page":"7132","article-title":"Squeeze-and-excitation networks","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Hu","year":"2018"},{"key":"B20","doi-asserted-by":"publisher","first-page":"17","DOI":"10.31083\/JIN-170033","article-title":"Functional brain dynamic analysis of ADHD and control children using nonlinear dynamical features of EEG signals.","volume":"17","author":"Khoshnoud","year":"2018","journal-title":"J. Integr. Neurosci."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1121","DOI":"10.1001\/archneur.1989.00520460115022","article-title":"The fatigue severity scale: Application to patients with multiple sclerosis and systemic lupus erythematosus.","volume":"46","author":"Krupp","year":"1989","journal-title":"Arch. Neurol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"56013","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":"B23","doi-asserted-by":"publisher","first-page":"106685","DOI":"10.1016\/j.bspc.2024.106685","article-title":"CWSTR-Net: A channel-weighted spatial-temporal residual network based on nonsmooth nonnegative matrix factorization for fatigue detection using EEG signals.","volume":"97","author":"Li","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1748","DOI":"10.1016\/j.ijforecast.2021.03.012","article-title":"Temporal fusion transformers for interpretable multi-horizon time series forecasting.","volume":"37","author":"Lim","year":"2021","journal-title":"Int. J. Forecast."},{"key":"B25","doi-asserted-by":"publisher","first-page":"5723","DOI":"10.1109\/JSEN.2024.3514094","article-title":"EEG emotion recognition via a lightweight 1DCNN-BiLSTM model in resource-limited environments.","volume":"25","author":"Liu","year":"2024","journal-title":"IEEE Sens. J."},{"key":"B26","doi-asserted-by":"publisher","first-page":"457","DOI":"10.3390\/e23040457","article-title":"Research on channel selection and multi-feature fusion of EEG signals for mental fatigue detection.","volume":"23","author":"Liu","year":"2021","journal-title":"Entropy"},{"key":"B27","doi-asserted-by":"publisher","first-page":"44003","DOI":"10.1088\/1361-6579\/abf336","article-title":"Toward practical driving fatigue detection using three frontal EEG channels: A proof-of-concept study.","volume":"42","author":"Liu","year":"2021","journal-title":"Physiol. Meas."},{"key":"B28","doi-asserted-by":"publisher","first-page":"101157","DOI":"10.1016\/j.aei.2020.101157","article-title":"Inter-subject transfer learning for EEG-based mental fatigue recognition.","volume":"46","author":"Liu","year":"2020","journal-title":"Adv. Eng. Informatics"},{"key":"B29","first-page":"4765","article-title":"A unified approach to interpreting model predictions.","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B30","doi-asserted-by":"publisher","first-page":"1788","DOI":"10.1109\/TBME.2021.3135622","article-title":"Real-time patient-specific ECG classification by 1D self-operational neural networks.","volume":"69","author":"Malik","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B31","doi-asserted-by":"publisher","first-page":"1079","DOI":"10.18280\/ts.390406","article-title":"Dual-layer ranking feature selection method based on statistical formula for driver fatigue detection of EMG signals.","volume":"39","author":"Naim","year":"2022","journal-title":"Trait. Signal"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.47852\/bonviewJDSIS3202983","article-title":"3D-STCNN: Spatiotemporal convolutional neural network based on EEG 3D features for detecting driving fatigue.","volume":"2","author":"Peng","year":"2024","journal-title":"J. Data Sci. Intell. Syst."},{"key":"B33","volume-title":"Learning Internal Representations by Error Propagation. Technical Report ICS8506.","author":"Rumelhart","year":"1985"},{"key":"B34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2025.3550242","article-title":"SGL-Net: An ultra-lightweight fatigue detection network in fast deployment scenarios.","volume":"74","author":"Sun","year":"2025","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"B35","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.brainres.2014.03.009","article-title":"Neural effects of mental fatigue caused by continuous attention load: A magnetoencephalography study.","volume":"1561","author":"Tanaka","year":"2014","journal-title":"Brain Res."},{"key":"B36","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.ijpsycho.2013.04.008","article-title":"Machine learning approach for classification of ADHD adults.","volume":"93","author":"Tenev","year":"2014","journal-title":"Int. J. Psychophysiol."},{"key":"B37","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1111\/j.1467-9868.2011.00771.x","article-title":"Regression shrinkage and selection via the lasso: A retrospective.","volume":"73","author":"Tibshirani","year":"2011","journal-title":"J. R. Stat. Soc. Series B"},{"key":"B38","doi-asserted-by":"publisher","first-page":"2550","DOI":"10.1109\/JBHI.2020.2980056","article-title":"Prediction of reaction time and vigilance variability from spatio-spectral features of resting-state EEG in a long sustained attention task.","volume":"24","author":"Torkamani-Azar","year":"2020","journal-title":"IEEE J. Biomed. Health Informatics"},{"key":"B39","doi-asserted-by":"publisher","first-page":"103838","DOI":"10.1016\/j.apergo.2022.103838","article-title":"Aviation and neurophysiology: A systematic review.","volume":"105","author":"van Weelden","year":"2022","journal-title":"Appl. Ergon."},{"key":"B40","doi-asserted-by":"publisher","first-page":"104657","DOI":"10.1016\/j.bspc.2023.104657","article-title":"Eye blink artifact detection based on multi-dimensional EEG feature fusion and optimization.","volume":"83","author":"Wang","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B41","doi-asserted-by":"publisher","first-page":"1567146","DOI":"10.3389\/fnins.2025.1567146","article-title":"Multiple entropy fusion predicts driver fatigue using forehead EEG.","volume":"19","author":"Yang","year":"2025","journal-title":"Front. Neurosci."},{"key":"B42","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1080\/0952813X.2014.924585","article-title":"ABC-based distance-weighted kNN algorithm.","volume":"27","author":"Yigit","year":"2015","journal-title":"J. Exp. Theor. Artif. Intell."},{"key":"B43","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1016\/j.neucom.2017.12.062","article-title":"Task-generic mental fatigue recognition based on neurophysiological signals and dynamical deep extreme learning machine.","volume":"283","author":"Yin","year":"2018","journal-title":"Neurocomputing"},{"key":"B44","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.ijrobp.2021.08.007","article-title":"Logistic regression in clinical studies.","volume":"112","author":"Zabor","year":"2022","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"B45","doi-asserted-by":"publisher","first-page":"104237","DOI":"10.1016\/j.bspc.2022.104237","article-title":"Recognising drivers\u2019 mental fatigue based on EEG multi-dimensional feature selection and fusion.","volume":"79","author":"Zhang","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B46","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1049\/bme2.12108","article-title":"Optimal feature-algorithm combination research for EEG fatigue driving detection based on functional brain network.","volume":"12","author":"Zhou","year":"2023","journal-title":"IET Biom."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1903252\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T05:37:49Z","timestamp":1785476269000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1903252\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":46,"alternative-id":["10.3389\/fnins.2026.1903252"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2026.1903252","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]},"article-number":"1903252"}}