{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T11:15:08Z","timestamp":1783422908342,"version":"3.54.6"},"reference-count":40,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Innovation Capacity Improvement Project for Technology-based SMEs in Shandong Province","award":["2023TSGC0449"],"award-info":[{"award-number":["2023TSGC0449"]}]},{"name":"Youth Innovation Team Development Plan for Universities in Shandong Province","award":["2021QCYY003"],"award-info":[{"award-number":["2021QCYY003"]}]},{"name":"College Students\u2019 Innovative Entrepreneurial Training Plan Program Project","award":["202510424091"],"award-info":[{"award-number":["202510424091"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Existing seizure detection methods cannot fully exploit the spatiotemporal features of multimodal signals. They also fail to capture deep associations among cross-modal features. This limits their ability to learn unified representations of spatiotemporal dependencies. This work proposes CMEpiNet (Complex-valued Multimodal Epilepsy detection Network model) to address this issue. CMEpiNet first uses complex-valued convolutions for feature extraction. It explicitly models phase synchronization, phase shifts, and cross-frequency coupling. Thus, EEG, ECG, and EMG features are represented in the complex-valued domain. During feature fusion, CMEpiNet uses a two-level semantic alignment-based fusion method. It applies cross-modal consistency constraints in a shared alignment space. It also performs distribution-level alignment in an epilepsy-related semantic latent space. These operations ensure the consistency of multimodal features in the global semantic structure. Finally, CMEpiNet uses a spatial attention-guided 3D convolutional classifier. The classifier jointly models the temporal, feature, and modality dimensions. Experimental results on the SeizeIT2 dataset show that CMEpiNet improves seizure detection sensitivity, reduces the false alarm rate, and maintains stable performance under perturbations.<\/jats:p>","DOI":"10.3390\/s26134186","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:48:32Z","timestamp":1782992912000},"page":"4186","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CMEpiNet: Complex-Valued Multimodal Epilepsy Detection Network Model"],"prefix":"10.3390","volume":"26","author":[{"given":"Tianyi","family":"Su","sequence":"first","affiliation":[{"name":"Department of Electrical and Information Engineering, Shandong University of Science and Technology, Jinan 250031, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyan","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Physical Education and Health Linyi, Linyi University, Linyi 276012, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Linyi University, Linyi 276012, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5381-1657","authenticated-orcid":false,"given":"Haifeng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Linyi University, Linyi 276012, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"871","DOI":"10.1186\/s12967-025-06862-z","article-title":"Multi-stream feature fusion of vision transformer and CNN for precise epileptic seizure detection from EEG signals","volume":"23","author":"Li","year":"2025","journal-title":"J. Transl. Med."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2578","DOI":"10.1111\/epi.18360","article-title":"Unique features of seizure-induced cardiorespiratory failure in SS Kcnj16-\/- rats: Implications for sudden unexpected death in epilepsy","volume":"66","author":"Eilbes","year":"2025","journal-title":"Epilepsia"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"ii2","DOI":"10.1136\/jnnp.2005.069245","article-title":"EEG in the diagnosis, classification, and management of patients with epilepsy","volume":"76","author":"Smith","year":"2005","journal-title":"J. Neurol. Neurosurg. Psychiatry"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.neucom.2019.01.053","article-title":"Classification for EEG report generation and epilepsy detection","volume":"335","author":"Oliva","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Liu, G., Xiao, R., Xu, L., and Cai, J. (2021). Minireview of epilepsy detection techniques based on electroencephalogram signals. Front. Syst. Neurosci., 15.","DOI":"10.3389\/fnsys.2021.685387"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/0013-4694(70)90143-4","article-title":"EEG analysis based on time domain properties","volume":"29","author":"Hjorth","year":"1970","journal-title":"Electroencephalogr. Clin. Neurophysiol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1109\/TBME.1981.324753","article-title":"Autoregressive estimation of short segment spectra for computerized EEG analysis","volume":"9","author":"Jansen","year":"1981","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1016\/0013-4694(82)90038-4","article-title":"Automatic recognition of epileptic seizures in the EEG","volume":"54","author":"Gotman","year":"1982","journal-title":"Electroencephalogr. Clin. Neurophysiol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1109\/10.552241","article-title":"A patient-specific algorithm for the detection of seizure onset in long-term EEG monitoring: Possible use as a warning device","volume":"44","author":"Qu","year":"1997","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1016\/S0165-0270(02)00340-0","article-title":"Analysis of EEG records in an epileptic patient using wavelet transform","volume":"123","author":"Adeli","year":"2003","journal-title":"J. Neurosci. Methods"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/j.eswa.2005.04.007","article-title":"Epileptic seizure detection using dynamic wavelet network","volume":"29","author":"Subasi","year":"2005","journal-title":"Expert Syst. Appl."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.seizure.2015.01.012","article-title":"Wavelet-based EEG processing for computer-aided seizure detection and epilepsy diagnosis","volume":"26","author":"Faust","year":"2015","journal-title":"Seizure"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1016\/j.cmpb.2005.06.012","article-title":"Entropies for detection of epilepsy in EEG","volume":"80","author":"Kannathal","year":"2005","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1563","DOI":"10.1007\/s10916-010-9433-z","article-title":"Application of higher order spectra to identify epileptic EEG","volume":"35","author":"Chua","year":"2011","journal-title":"J. Med. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"401","DOI":"10.1016\/j.bspc.2011.07.007","article-title":"Automated diagnosis of epileptic EEG using entropies","volume":"7","author":"Acharya","year":"2012","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1016\/j.physa.2019.02.017","article-title":"Dynamical analysis of epileptic characteristics based on recurrence quantification of SEEG recordings","volume":"523","author":"Yang","year":"2019","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"19","DOI":"10.4103\/jmss.jmss_73_24","article-title":"A Nonlinear Method to Identify Seizure Dynamic Trajectory Based on Variance of Recurrence Rate in Human Epilepsy Patients Using EEG","volume":"15","author":"Farahi","year":"2025","journal-title":"J. Med. Signals Sens."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1016\/j.amc.2006.09.022","article-title":"Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform","volume":"187","author":"Polat","year":"2007","journal-title":"Appl. Math. Comput."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1109\/TITB.2009.2017939","article-title":"Epileptic seizure detection in EEGs using time\u2013frequency analysis","volume":"13","author":"Tzallas","year":"2009","journal-title":"IEEE Trans. Inf. Technol. Biomed."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"13475","DOI":"10.1016\/j.eswa.2011.04.149","article-title":"EEG signals classification using the K-means clustering and a multilayer perceptron neural network model","volume":"38","author":"Orhan","year":"2011","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1080\/03091900701559408","article-title":"Analysis of epileptic EEG signals using higher order spectra","volume":"33","author":"Chua","year":"2009","journal-title":"J. Med. Eng. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.eswa.2011.07.008","article-title":"Detection of epileptic electroencephalogram based on permutation entropy and support vector machines","volume":"39","author":"Nicolaou","year":"2012","journal-title":"Expert Syst. Appl."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.1016\/j.eswa.2006.02.005","article-title":"EEG signal classification using wavelet feature extraction and a mixture of expert model","volume":"32","author":"Subasi","year":"2007","journal-title":"Expert Syst. Appl."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1007\/s40708-015-0030-2","article-title":"Epileptic seizure detection from EEG signals using logistic model trees","volume":"3","author":"Kabir","year":"2016","journal-title":"Brain Inform."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1016\/j.neucom.2017.02.053","article-title":"Automated epileptic seizure detection using improved correlation-based feature selection with random forest classifier","volume":"241","author":"Mursalin","year":"2017","journal-title":"Neurocomputing"},{"key":"ref_26","unstructured":"Thodoroff, P., Pineau, J., and Lim, A. (2016). Learning robust features using deep learning for automatic seizure detection. Proceedings of the Machine Learning for Healthcare Conference, PMLR."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.compbiomed.2017.09.017","article-title":"Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals","volume":"100","author":"Acharya","year":"2018","journal-title":"Comput. Biol. Med."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"101684","DOI":"10.1016\/j.nicl.2019.101684","article-title":"Seizure detection by convolutional neural network-based analysis of scalp electroencephalography plot images","volume":"22","author":"Emami","year":"2019","journal-title":"Neuroimage Clin."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"804","DOI":"10.1109\/TBCAS.2019.2929053","article-title":"Efficient epileptic seizure prediction based on deep learning","volume":"13","author":"Daoud","year":"2019","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.clinph.2018.10.010","article-title":"Optimized deep neural network architecture for robust detection of epileptic seizures using EEG signals","volume":"130","author":"Hussein","year":"2019","journal-title":"Clin. Neurophysiol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1927","DOI":"10.1016\/j.clinph.2009.09.002","article-title":"Classification of patterns of EEG synchronization for seizure prediction","volume":"120","author":"Mirowski","year":"2009","journal-title":"Clin. Neurophysiol."},{"key":"ref_32","unstructured":"Tang, S., Dunnmon, J.A., Saab, K., Zhang, X., Huang, Q., Dubost, F., Rubin, D.L., and Lee-Messer, C. (2021). Self-supervised graph neural networks for improved electroencephalographic seizure analysis. arXiv."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"12189","DOI":"10.1109\/TCYB.2021.3071860","article-title":"Spatio-temporal-spectral hierarchical graph convolutional network with semisupervised active learning for patient-specific seizure prediction","volume":"52","author":"Li","year":"2021","journal-title":"IEEE Trans. Cybern."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"07TR01","DOI":"10.1088\/1361-6579\/ac7a8d","article-title":"Seizures detection using multimodal signals: A scoping review","volume":"43","author":"Chen","year":"2022","journal-title":"Physiol. Meas."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"3529","DOI":"10.1109\/JBHI.2022.3157877","article-title":"A multimodal AI system for out-of-distribution generalization of seizure identification","volume":"26","author":"Yang","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"065005","DOI":"10.1088\/1361-6579\/ad4e94","article-title":"Multimodal wearable EEG, EMG and accelerometry measurements improve the accuracy of tonic-clonic seizure detection","volume":"45","author":"Zhang","year":"2024","journal-title":"Physiol. Meas."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1038\/s41597-025-05580-x","article-title":"SeizeIT2: Wearable dataset of patients with focal Epilepsy","volume":"12","author":"Bhagubai","year":"2025","journal-title":"Sci. Data"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"766","DOI":"10.1111\/epi.16470","article-title":"Visual seizure annotation and automated seizure detection using behind-the-ear electroencephalographic channels","volume":"61","author":"Vandecasteele","year":"2020","journal-title":"Epilepsia"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Roy, S., Kiral-Kornek, I., and Harrer, S. (2019). ChronoNet: A deep recurrent neural network for abnormal EEG identification. Proceedings of the Conference on Artificial Intelligence in Medicine in Europe, Springer.","DOI":"10.1007\/978-3-030-21642-9_8"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1007\/s10618-020-00710-y","article-title":"Inceptiontime: Finding alexnet for time series classification","volume":"34","author":"Lucas","year":"2020","journal-title":"Data Min. Knowl. Discov."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4186\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T10:28:02Z","timestamp":1783420082000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/13\/4186"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"references-count":40,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["s26134186"],"URL":"https:\/\/doi.org\/10.3390\/s26134186","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]}}}