{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T14:14:28Z","timestamp":1773843268683,"version":"3.50.1"},"reference-count":30,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T00:00:00Z","timestamp":1750723200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Epileptic seizure detection and classification from EEG recordings faces significant challenges due to extreme class imbalance. Analysis of the Temple University Hospital Seizure (TUSZ) dataset reveals imbalance ratios of 150:1 between common and rare seizure types, with high temporal heterogeneity (seizure durations of 1\u20131638 s). We propose a cascaded deep learning architecture with two specialized CNNs: a binary detector followed by a multi-class classifier. This approach decomposes the classification problem, reducing the maximum imbalance from 150:1 to manageable levels (9:1 binary, 5:1 type). The architecture implements a high-confidence filtering mechanism (threshold = 0.9), creating a 99.5% pure dataset for type classification, dynamic class-weighted optimization proportional to inverse class frequencies, and information flow refinement through progressive stages. Loss dynamics analysis reveals that our weighting scheme strategically redistributes optimization attention, reducing variance by 90.7% for majority classes while increasing variance for minority classes, ensuring all seizure types receive proportional learning signals regardless of representation. The binary classifier achieves 99.64% specificity and 98.23% sensitivity (ROC-AUC = 0.995). The type classifier demonstrates &gt;99% accuracy across seven seizure categories with perfect (100%) classification for three seizure types despite minimal representation. Cross-dataset validation on the University of Bonn dataset confirms robust generalization (96.0% accuracy) for binary seizure detection. This framework effectively addresses multi-level imbalance in neurophysiological signal classification with hierarchical class structures.<\/jats:p>","DOI":"10.3390\/info16070532","type":"journal-article","created":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T06:49:38Z","timestamp":1750747778000},"page":"532","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Hierarchical Deep Learning for Comprehensive Epileptic Seizure Analysis: From Detection to Fine-Grained Classification"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-8657-2435","authenticated-orcid":false,"given":"Peter","family":"Akor","sequence":"first","affiliation":[{"name":"School of Engineering, Computing and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2686-7035","authenticated-orcid":false,"given":"Godwin","family":"Enemali","sequence":"additional","affiliation":[{"name":"School of Engineering, Computing and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Usman","family":"Muhammad","sequence":"additional","affiliation":[{"name":"School of Engineering, Computing and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1808-3433","authenticated-orcid":false,"given":"Rajiv Ranjan","family":"Singh","sequence":"additional","affiliation":[{"name":"School of Engineering, Computing and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6826-207X","authenticated-orcid":false,"given":"Hadi","family":"Larijani","sequence":"additional","affiliation":[{"name":"School of Engineering, Computing and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2019). Epilepsy: A Public Health Imperative: Summary."},{"key":"ref_2","unstructured":"World Health Organization (2017). Atlas: Country Resources for Neurological Disorders."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1159\/000115641","article-title":"Errors in EEG interpretation and misdiagnosis of epilepsy","volume":"59","author":"Benbadis","year":"2008","journal-title":"Eur. Neurol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1097\/00004691-198404000-00001","article-title":"A practical guide for routine EEG studies in epilepsy","volume":"1","author":"Engel","year":"1984","journal-title":"J. Clin. Neurophysiol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1097\/00004691-200302000-00005","article-title":"Overintepretation of EEGs and misdiagnosis of epilepsy","volume":"20","author":"Benbadis","year":"2003","journal-title":"J. Clin. Neurophysiol."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Michel, C.M., and Brunet, D. (2019). EEG Source Imaging: A Practical Review of the Analysis Steps. Front. Neurol., 10.","DOI":"10.3389\/fneur.2019.00325"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"012093","DOI":"10.1088\/1742-6596\/1706\/1\/012093","article-title":"Methods for removal of artifacts from EEG signal: A review","volume":"1706","author":"Kotte","year":"2020","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.cnp.2020.12.002","article-title":"Under-sampling in epilepsy: Limitations of conventional EEG","volume":"6","author":"Baud","year":"2021","journal-title":"Clin. Neurophysiol. Pract."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"051001","DOI":"10.1088\/1741-2552\/ab260c","article-title":"Deep learning-based electroencephalography analysis: A systematic review","volume":"16","author":"Roy","year":"2019","journal-title":"J. Neural Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"031001","DOI":"10.1088\/1741-2552\/ab0ab5","article-title":"Deep learning for electroencephalogram (EEG) classification tasks: A review","volume":"16","author":"Craik","year":"2019","journal-title":"J. Neural Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.neunet.2018.04.018","article-title":"Convolutional neural networks for seizure prediction using intracranial and scalp electroencephalogram","volume":"105","author":"Truong","year":"2018","journal-title":"Neural Netw."},{"key":"ref_12","unstructured":"Covert, I., Krishnan, B., Najm, I., Zhan, J., Shore, M., Hixson, J., and Po, M.J. (2019, January 8\u201310). Temporal graph convolutional networks for automatic seizure detection. Proceedings of the Machine Learning for Healthcare Conference, PMLR, Ann Arbor, MI, USA."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1817","DOI":"10.1111\/epi.13907","article-title":"Automated analysis of seizure semiology and brain electrical activity in presurgery evaluation of epilepsy: A focused survey","volume":"58","author":"Fookes","year":"2017","journal-title":"Epilepsia"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Raut, S., and Rathee, N. (2021). Comparative Study on Machine Learning Classifiers for Epileptic Seizure Detection in Reference to EEG Signals. Smart Healthcare Systems: An Internet of Things Perspective, Springer.","DOI":"10.1007\/978-981-15-4992-2_18"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Li, Q., Gao, J., Zhang, Z., Huang, Q., Wu, Y., and Xu, B. (2020). Distinguishing epileptiform discharges from normal electroencephalograms using adaptive fractal and network analysis: A clinical perspective. Front. Physiol., 11.","DOI":"10.3389\/fphys.2020.00828"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li, Y., Cui, W., Li, H., Huang, M., and Cui, L. (2018). Detection of epileptic seizure based on entropy analysis of short-term EEG. PLoS ONE, 13.","DOI":"10.1371\/journal.pone.0193691"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1109\/TKDE.2008.239","article-title":"Learning from Imbalanced Data","volume":"21","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s40537-019-0192-5","article-title":"Survey on deep learning with class imbalance","volume":"6","author":"Johnson","year":"2019","journal-title":"J. Big Data"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Statsenko, Y., Babushkin, V., Talako, T., Kurbatova, T., Smetanina, D., Simiyu, G.L., Habuza, T., Ismail, F., Almansoori, T.M., and Gorkom, K.N.V. (2023). Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach. Biomedicines, 11.","DOI":"10.3390\/biomedicines11092370"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Shah, V., von Weltin, E., Lopez, S., McHugh, J.R., Veloso, L., Golmohammadi, M., Obeid, I., and Picone, J. (2018). The Temple University Hospital Seizure Detection Corpus. Front. Neuroinf., 12.","DOI":"10.3389\/fninf.2018.00083"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Asif, U., Roy, S., Tang, J., and Harrer, S. (2020, January 4\u20138). SeizureNet: Multi-Spectral Deep Feature Learning for Seizure Type Classification. Proceedings of the Third International Workshop, MLCN 2020, and Second International Workshop, RNO-AI 2020, Held in Conjunction with MICCAI 2020, Lima, Peru.","DOI":"10.1007\/978-3-030-66843-3_8"},{"key":"ref_23","first-page":"2243","article-title":"Optimized deep neural networks for real-time seizure detection systems","volume":"27","author":"Hussein","year":"2019","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"061907","DOI":"10.1103\/PhysRevE.64.061907","article-title":"Indications of nonlinear deterministic and finite-dimensional structures in time series of brain electrical activity: Dependence on recording region and brain state","volume":"64","author":"Andrzejak","year":"2001","journal-title":"Phys. Rev. E"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"228","DOI":"10.7555\/JBR.33.20190016","article-title":"Epileptic seizure detection using EEG signals and extreme gradient boosting","volume":"34","author":"Vanabelle","year":"2020","journal-title":"J. Biomed. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"109732","DOI":"10.1016\/j.yebeh.2024.109732","article-title":"Attention-based deep convolutional neural network for classification of generalized and focal epileptic seizures","volume":"155","author":"Gill","year":"2024","journal-title":"Epilepsy Behav."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zeng, W., Shan, L., Su, B., and Du, S. (2023). Epileptic seizure detection with deep EEG features by convolutional neural network and shallow classifiers. Front. Neurosci., 17.","DOI":"10.3389\/fnins.2023.1145526"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Albaqami, H.A., Hassan, G.M., and Datta, A. (2022). Wavelet-Based Multi-Class Seizure Type Classification System. Appl. Sci., 12.","DOI":"10.2139\/ssrn.4040674"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1109\/TNSRE.2024.3350074","article-title":"Epileptic seizure detection based on path signature and Bi-LSTM Network with attention mechanism","volume":"32","author":"Tang","year":"2024","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"121040","DOI":"10.1016\/j.eswa.2023.121040","article-title":"Epileptic multi-seizure type classification using electroencephalogram signals from the Temple University Hospital Seizure Corpus: A review","volume":"234","author":"McCallan","year":"2023","journal-title":"Expert Syst. Appl."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/7\/532\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:57:30Z","timestamp":1760032650000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/7\/532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,24]]},"references-count":30,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["info16070532"],"URL":"https:\/\/doi.org\/10.3390\/info16070532","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,24]]}}}