{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T11:17:11Z","timestamp":1767957431118,"version":"3.49.0"},"reference-count":58,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T00:00:00Z","timestamp":1767916800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Brain Sciences"],"abstract":"<jats:p>Background: Epileptic seizures are unpredictable, and while existing deep learning models achieve high accuracy, their deployment on wearable devices is constrained by high computational costs and latency. To address this, this work proposes the RGF-Model, a lightweight network that unifies seizure prediction and detection within a single causal framework. Methods: By integrating Feature-wise Linear Modulation (FiLM) with a Ring-Buffer Gated Recurrent Unit (Ring-GRU), the model achieves adaptive task-specific feature conditioning while strictly enforcing causal consistency for real-time inference. A multi-teacher knowledge distillation strategy is employed to transfer complementary knowledge from complex teacher ensembles to the lightweight student, significantly reducing complexity without sacrificing accuracy. Results: Evaluations on the CHB-MIT and Siena datasets demonstrate that the RGF-Model outperforms state-of-the-art teacher models in terms of efficiency while maintaining comparable accuracy. Specifically, on CHB-MIT, it achieves 99.54% Area Under the Curve (AUC) and 0.01 False Prediction Rate per hour (FPR\/h) for prediction, and 98.78% Accuracy (Acc) for detection, with only 0.082 million parameters. Statistical significance was assessed using a random predictor baseline (p &lt; 0.05). Conclusions: The results indicate that the RGF-Model provides a highly efficient solution for real-time wearable epilepsy monitoring.<\/jats:p>","DOI":"10.3390\/brainsci16010083","type":"journal-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T09:25:02Z","timestamp":1767950702000},"page":"83","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient and Accurate Epilepsy Seizure Prediction and Detection Based on Multi-Teacher Knowledge Distillation RGF-Model"],"prefix":"10.3390","volume":"16","author":[{"given":"Wei","family":"Cao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China"},{"name":"Jilin Provincial International Joint Research Center of Brain Informatics and Intelligence Science, Changchun 130022, China"},{"name":"Zhongshan Institute of Changchun University of Science and Technology, Zhongshan 528437, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianze","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Zhang, X.Z., Zhang, X.L., Huang, Q., and Chen, F.M. (2024). A review of epilepsy detection and prediction methods based on EEG signal processing and deep learning. Front. Neurosci., 18.","DOI":"10.3389\/fnins.2024.1468967"},{"key":"ref_2","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_3","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1097\/WCO.0000000000001246","article-title":"Recent advances in clinical electroencephalography","volume":"37","author":"Frauscher","year":"2024","journal-title":"Curr. Opin. Neurol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"14876","DOI":"10.1038\/s41598-023-41537-z","article-title":"Automated recognition of epilepsy from EEG signals using a combining space-time algorithm of CNN-LSTM","volume":"13","author":"Wang","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_5","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_6","doi-asserted-by":"crossref","first-page":"2450041","DOI":"10.1142\/S0129065724500412","article-title":"Epileptic Seizure Prediction Using Spatiotemporal Feature Fusion on EEG","volume":"34","author":"Ji","year":"2024","journal-title":"Int. J. Neural Syst."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/s13755-023-00239-6","article-title":"Combining temporal and spatial attention for seizure prediction","volume":"11","author":"Wang","year":"2023","journal-title":"Health Inf. Sci. Syst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"895","DOI":"10.1186\/s12967-024-05678-7","article-title":"Epileptic seizure prediction via multidimensional transformer and recurrent neural network fusion","volume":"22","author":"Zhu","year":"2024","journal-title":"J. Transl. Med."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Abdelhameed, A., and Bayoumi, M. (2021). A Deep Learning Approach for Automatic Seizure Detection in Children with Epilepsy. Front. Comput. Neurosci., 15.","DOI":"10.3389\/fncom.2021.650050"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"066045","DOI":"10.1088\/1741-2552\/ada0e5","article-title":"Multi-dimensional hybrid bilinear CNN-LSTM models for epileptic seizure detection and prediction using EEG signals","volume":"21","author":"Liu","year":"2024","journal-title":"J. Neural Eng."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Lee, K.S., Park, H.J., Kim, J.E., Kim, H.J., Chon, S., Kim, S., Jang, J., Kim, J.K., Jang, S., and Gil, Y. (2022). Compressed Deep Learning to Classify Arrhythmia in an Embedded Wearable Device. Sensors, 22.","DOI":"10.3390\/s22051776"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1109\/JBHI.2019.2911367","article-title":"LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices","volume":"24","author":"Saadatnejad","year":"2020","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge Distillation: A Survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1109\/JPROC.2020.2976475","article-title":"Model Compression and Hardware Acceleration for Neural Networks: A Comprehensive Survey","volume":"108","author":"Deng","year":"2020","journal-title":"Proc. IEEE"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Li, Z., Li, H., and Meng, L. (2023). Model Compression for Deep Neural Networks: A Survey. Computers, 12.","DOI":"10.3390\/computers12030060"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"128375","DOI":"10.1016\/j.neucom.2024.128375","article-title":"Difficulty level-based knowledge distillation","volume":"606","author":"Ham","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1016\/j.neucom.2021.04.026","article-title":"Interactive Knowledge Distillation for image classification","volume":"449","author":"Fu","year":"2021","journal-title":"Neurocomputing"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1145\/3675402","article-title":"M2SKD: Multi-to-Single Knowledge Distillation of Real-Time Epileptic Seizure Detection for Low-Power Wearable Systems","volume":"15","author":"Baghersalimi","year":"2024","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"036035","DOI":"10.1088\/1741-2552\/ac73b3","article-title":"Bridging the gap between patient-specific and patient-independent seizure prediction via knowledge distillation","volume":"19","author":"Wu","year":"2022","journal-title":"J. Neural Eng."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"nwaf086","DOI":"10.1093\/nsr\/nwaf086","article-title":"Canine EEG helps human: Cross-species and cross-modality epileptic seizure detection via multi-space alignment","volume":"12","author":"Wang","year":"2025","journal-title":"Natl. Sci. Rev."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.trc.2019.10.014","article-title":"An optimization model for arterial coordination control based on sampled vehicle trajectories: The STREAM model","volume":"109","author":"Yao","year":"2019","journal-title":"Transp. Res. Part C Emerg. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"16916","DOI":"10.1038\/s41598-024-67855-4","article-title":"A scheme combining feature fusion and hybrid deep learning models for epileptic seizure detection and prediction","volume":"14","author":"Zhang","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Choi, W., Kim, M.J., Yum, M.S., and Jeong, D.H. (2022). Deep Convolutional Gated Recurrent Unit Combined with Attention Mechanism to Classify Pre-Ictal from Interictal EEG with Minimized Number of Channels. J. Pers. Med., 12.","DOI":"10.3390\/jpm12050763"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1007\/s11063-022-10950-2","article-title":"Cyclic Gate Recurrent Neural Networks for Time Series Data with Missing Values","volume":"55","author":"Weerakody","year":"2023","journal-title":"Neural Process. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"711","DOI":"10.1002\/jum.16633","article-title":"Improved Birthweight Prediction with Feature-Wise Linear Modulation, GRU, and Attention Mechanism in Ultrasound Data","volume":"44","author":"Priya","year":"2025","journal-title":"J. Ultrasound Med."},{"key":"ref_26","unstructured":"Shoeb, A.H. (2009). Application of Machine Learning to Epileptic Seizure Onset Detection and Treatment. [Ph.D. Thesis, Harvard University]."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Yang, Y., Qin, X.L., Wen, H., Li, F., and Lin, X.G. (2023). Patient-specific approach using data fusion and adversarial training for epileptic seizure prediction. Front. Comput. Neurosci., 17.","DOI":"10.3389\/fncom.2023.1172987"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"109225","DOI":"10.1016\/j.compbiomed.2024.109225","article-title":"Real-time sub-milliwatt epilepsy detection implemented on a spiking neural network edge inference processor","volume":"183","author":"Li","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1016\/j.neuroimage.2016.04.049","article-title":"The Virtual Epileptic Patient: Individualized whole-brain models of epilepsy spread","volume":"145","author":"Jirsa","year":"2017","journal-title":"Neuroimage"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1536","DOI":"10.1109\/TNSRE.2022.3180155","article-title":"Patient-Specific Seizure Prediction via Adder Network and Supervised Contrastive Learning","volume":"30","author":"Zhao","year":"2022","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_31","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_32","doi-asserted-by":"crossref","first-page":"111948","DOI":"10.1016\/j.measurement.2022.111948","article-title":"EEG-based seizure prediction via Transformer guided CNN","volume":"203","author":"Li","year":"2022","journal-title":"Measurement"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Chung, Y.G., Cho, A., Kim, H., and Kim, K.J. (2024). Single-channel seizure detection with clinical confirmation of seizure locations using CHB-MIT dataset. Front. Neurol., 15.","DOI":"10.3389\/fneur.2024.1389731"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1038\/s41597-023-02525-0","article-title":"DISCOVER-EEG: An open, fully automated EEG pipeline for biomarker discovery in clinical neuroscience","volume":"10","author":"Avila","year":"2023","journal-title":"Sci. Data"},{"key":"ref_35","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_36","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s40708-022-00159-3","article-title":"Seizure classification with selected frequency bands and EEG montages: A natural language processing approach","volume":"9","author":"Wang","year":"2022","journal-title":"Brain Inform."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"117572","DOI":"10.1016\/j.oceaneng.2024.117572","article-title":"Long time series of ocean wave prediction based on PatchTST model","volume":"301","author":"Huang","year":"2024","journal-title":"Ocean Eng."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"230601","DOI":"10.1098\/rsos.230601","article-title":"Epileptic seizure detection using CHB-MIT dataset: The overlooked perspectives","volume":"11","author":"Ali","year":"2024","journal-title":"R. Soc. Open Sci."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1109\/JTEHM.2023.3290036","article-title":"An Epileptic Seizure Prediction Method Based on CBAM-3D CNN-LSTM Model","volume":"11","author":"Lu","year":"2023","journal-title":"IEEE J. Transl. Eng. Health Med. JTEHM"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"107427","DOI":"10.1016\/j.compbiomed.2023.107427","article-title":"A self-attention model for cross-subject seizure detection","volume":"165","author":"Abdallah","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"2350042","DOI":"10.1142\/S0129065723500429","article-title":"Epileptic EEG Classification via Graph Transformer Network","volume":"33","author":"Lian","year":"2023","journal-title":"Int. J. Neural Syst."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1850011","DOI":"10.1142\/S0129065718500119","article-title":"Neonatal Seizure Detection Using Deep Convolutional Neural Networks","volume":"29","author":"Ansari","year":"2019","journal-title":"Int. J. Neural Syst."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"104441","DOI":"10.1016\/j.bspc.2022.104441","article-title":"Interactive local and global feature coupling for EEG-based epileptic seizure detection","volume":"81","author":"Zhao","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1097\/WCO.0000000000000429","article-title":"A forward-looking review of seizure prediction","volume":"30","author":"Freestone","year":"2017","journal-title":"Curr. Opin. Neurol."},{"key":"ref_45","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_46","doi-asserted-by":"crossref","first-page":"2474","DOI":"10.1109\/TNSRE.2021.3129467","article-title":"ScoreNet: A Neural Network-Based Post-Processing Model for Identifying Epileptic Seizure Onset and Offset in EEGs","volume":"29","author":"Boonyakitanont","year":"2021","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Ru, Y.D., An, G.Y., Wei, Z., and Chen, H.M. (2024). Epilepsy detection based on multi-head self-attention mechanism. PLoS ONE, 19.","DOI":"10.1371\/journal.pone.0305166"},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"106021","DOI":"10.1016\/j.compbiomed.2022.106021","article-title":"Full wave simulation of arterial response under acoustic radiation force","volume":"149","author":"Roy","year":"2022","journal-title":"Comput. Biol. Med."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"102767","DOI":"10.1016\/j.bspc.2021.102767","article-title":"Deep learning based efficient epileptic seizure prediction with EEG channel optimization","volume":"68","author":"Jana","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1573076","DOI":"10.1155\/2022\/1573076","article-title":"Semisupervised Seizure Prediction in Scalp EEG Using Consistency Regularization","volume":"2022","author":"Liang","year":"2022","journal-title":"J. Healthc. Eng."},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Bonetti, F., Zotto, M.D., and Minasian, R. (2024). SymTFTs for Continuous non-Abelian Symmetries. arXiv.","DOI":"10.1016\/j.physletb.2025.140010"},{"key":"ref_52","doi-asserted-by":"crossref","unstructured":"Kumaravel, V.P., Pale, U., Teijeiro, T., Farella, E., and Atienza, D. (2023). Knowledge Distillation-based Channel Reduction for Wearable EEG Applications. IEEE J. Biomed. Health Inform.","DOI":"10.36227\/techrxiv.22651156.v1"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"18919","DOI":"10.1007\/s00521-024-10207-0","article-title":"KDTL: Knowledge-distilled transfer learning framework for diagnosing mental disorders using EEG spectrograms","volume":"36","author":"Singh","year":"2024","journal-title":"Neural Comput. Appl."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"18998","DOI":"10.1038\/s41598-022-23656-1","article-title":"Graph-generative neural network for EEG-based epileptic seizure detection via discovery of dynamic brain functional connectivity","volume":"12","author":"Li","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_55","first-page":"253","article-title":"Automatic epilepsy detection with an attention-based multiscale residual network","volume":"41","author":"Wang","year":"2024","journal-title":"Sheng Wu Yi Xue Gong Cheng Xue Za Zhi"},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1845","DOI":"10.1109\/JBHI.2022.3223970","article-title":"LightSeizureNet: A Lightweight Deep Learning Model for Real-Time Epileptic Seizure Detection","volume":"27","author":"Qiu","year":"2023","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"28362","DOI":"10.1038\/s41598-024-80018-9","article-title":"Research on information leakage in time series prediction based on empirical mode decomposition","volume":"14","author":"Yang","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"6165","DOI":"10.1109\/ACCESS.2022.3142311","article-title":"A Combined Projection for Remote Control of a Vehicle Based on Movement Imagination: A Single Trial Brain Computer Interface Study","volume":"10","author":"Hekmatmanesh","year":"2022","journal-title":"IEEE Access"}],"container-title":["Brain Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3425\/16\/1\/83\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T09:34:48Z","timestamp":1767951288000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3425\/16\/1\/83"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,9]]},"references-count":58,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["brainsci16010083"],"URL":"https:\/\/doi.org\/10.3390\/brainsci16010083","relation":{},"ISSN":["2076-3425"],"issn-type":[{"value":"2076-3425","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,9]]}}}