{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T17:10:44Z","timestamp":1770138644275,"version":"3.49.0"},"reference-count":57,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2018,5,24]],"date-time":"2018-05-24T00:00:00Z","timestamp":1527120000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In the last decade, seizure prediction systems have gained a lot of attention because of their enormous potential to largely improve the quality-of-life of the epileptic patients. The accuracy of the prediction algorithms to detect seizure in real-world applications is largely limited because the brain signals are inherently uncertain and affected by various factors, such as environment, age, drug intake, etc., in addition to the internal artefacts that occur during the process of recording the brain signals. To deal with such ambiguity, researchers transitionally use active learning, which selects the ambiguous data to be annotated by an expert and updates the classification model dynamically. However, selecting the particular data from a pool of large ambiguous datasets to be labelled by an expert is still a challenging problem. In this paper, we propose an active learning-based prediction framework that aims to improve the accuracy of the prediction with a minimum number of labelled data. The core technique of our framework is employing the Bernoulli-Gaussian Mixture model (BGMM) to determine the feature samples that have the most ambiguity to be annotated by an expert. By doing so, our approach facilitates expert intervention as well as increasing medical reliability. We evaluate seven different classifiers in terms of the classification time and memory required. An active learning framework built on top of the best performing classifier is evaluated in terms of required annotation effort to achieve a high level of prediction accuracy. The results show that our approach can achieve the same accuracy as a Support Vector Machine (SVM) classifier using only    20 %    of the labelled data and also improve the prediction accuracy even under the noisy condition.<\/jats:p>","DOI":"10.3390\/s18061698","type":"journal-article","created":{"date-parts":[[2018,5,28]],"date-time":"2018-05-28T03:54:21Z","timestamp":1527479661000},"page":"1698","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Towards an Online Seizure Advisory System\u2014An Adaptive Seizure Prediction Framework Using Active Learning Heuristics"],"prefix":"10.3390","volume":"18","author":[{"given":"Vignesh Raja","family":"Karuppiah Ramachandran","sequence":"first","affiliation":[{"name":"Pervasive Systems Research Group, University of Twente, Drienerlolaan 5, 7522 NB Enschede, The Netherlands"}]},{"given":"Huibert J.","family":"Alblas","sequence":"additional","affiliation":[{"name":"Pervasive Systems Research Group, University of Twente, Drienerlolaan 5, 7522 NB Enschede, The Netherlands"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7851-0869","authenticated-orcid":false,"given":"Duc V.","family":"Le","sequence":"additional","affiliation":[{"name":"Pervasive Systems Research Group, University of Twente, Drienerlolaan 5, 7522 NB Enschede, The Netherlands"}]},{"given":"Nirvana","family":"Meratnia","sequence":"additional","affiliation":[{"name":"Pervasive Systems Research Group, University of Twente, Drienerlolaan 5, 7522 NB Enschede, The Netherlands"}]}],"member":"1968","published-online":{"date-parts":[[2018,5,24]]},"reference":[{"key":"ref_1","unstructured":"(2017, September 30). WHO. Available online: http:\/\/www.who.int\/mediacentre\/factsheets\/fs355\/en\/."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1111\/j.0013-9580.2005.66104.x","article-title":"Epileptic seizures and epilepsy: Definitions proposed by the International League Against Epilepsy (ILAE) and the International Bureau for Epilepsy (IBE)","volume":"46","author":"Fisher","year":"2005","journal-title":"Epilepsia"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"522","DOI":"10.1111\/epi.13670","article-title":"Operational classification of seizure types by the International League Against Epilepsy: Position Paper of the ILAE Commission for Classification and Terminology","volume":"58","author":"Fisher","year":"2017","journal-title":"Epilepsia"},{"key":"ref_4","unstructured":"(2017, September 30). WHO. Available online: http:\/\/www.who.int\/mediacentre\/factsheets\/fs999\/en\/."},{"key":"ref_5","unstructured":"Lee, K., Roberts, D., and Hartov, A. (2006). Deep Brain Stimulator. (App. 11\/244,134), U.S. Patent."},{"key":"ref_6","unstructured":"Osorio, I., and Frei, M.G. (2002). Vagal Nerve Stimulation Techniques for Treatment of Epileptic Seizures. (6,341,236), U.S. Patent."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1728","DOI":"10.1111\/epi.13860","article-title":"Seizure outcome after hippocampal deep brain stimulation in patients with refractory temporal lobe epilepsy: A prospective, controlled, randomized, double-blind study","volume":"58","author":"Cukiert","year":"2017","journal-title":"Epilepsia"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Morace, R., Di Gennaro, G., Quarato, P.P., D\u2019Aniello, A., Mascia, A., Grammaldo, L., De Risi, M., Sparano, A., Di Cola, F., and De Angelis, M. (2017). Vagal Nerve Stimulation for Drug-Resistant Epilepsy: Adverse Events and Outcome in a Series of Patients with Long-Term Follow-Up. Trends in Reconstructive Neurosurgery: Neurorehabilitation, Restoration and Reconstruction, Springer International Publishing.","DOI":"10.1007\/978-3-319-39546-3_8"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1136\/jnnp.1.4.359","article-title":"Critical review: The technique and application of electro-encephalography","volume":"1","author":"Walter","year":"1938","journal-title":"J. Neurol. Psychiatry"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Penfield, W., and Jasper, H. (1954). Epilepsy and the Functional Anatomy of the Human Brain, Little, Brown & Co.","DOI":"10.1097\/00007611-195407000-00024"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13534-017-0008-5","article-title":"On predicting epileptic seizures from intracranial electroencephalography","volume":"7","author":"Yoo","year":"2017","journal-title":"Biomed. Eng. Lett."},{"key":"ref_12","first-page":"435","article-title":"Proceedings: Epileptic seizure prediction","volume":"39","author":"Viglione","year":"1975","journal-title":"Electroencephalogr. Clin. Neurophysiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1007\/BF00335153","article-title":"On the prediction of epileptic seizures","volume":"42","author":"Rogowski","year":"1981","journal-title":"Biol. Cybern."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/j.yebeh.2014.06.023","article-title":"Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy","volume":"37","author":"Ramgopal","year":"2014","journal-title":"Epilepsy Behav."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1016\/j.yebeh.2004.05.005","article-title":"Patient-specific seizure onset detection","volume":"5","author":"Shoeb","year":"2004","journal-title":"Epilepsy Behav."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1650037","DOI":"10.1142\/S0129065716500374","article-title":"Generalized models for the classification of abnormal movements in daily life and its applicability to epilepsy convulsion recognition","volume":"26","author":"Villar","year":"2016","journal-title":"Int. J. Neural Syst."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1465","DOI":"10.1016\/j.clinph.2009.05.019","article-title":"Seizure prediction: Any better than chance?","volume":"120","author":"Andrzejak","year":"2009","journal-title":"Clin. Neurophys."},{"key":"ref_18","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_19","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1016\/S1474-4422(13)70075-9","article-title":"Prediction of seizure likelihood with a long-term, implanted seizure advisory system in patients with drug-resistant epilepsy: A first-in-man study","volume":"12","author":"Cook","year":"2013","journal-title":"Lancet Neurol."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Shamir, R., Noecker, A., and McIntyre, C. (2014). Deep Brain Stimulation. Front Young Minds.","DOI":"10.3389\/frym.2014.00012"},{"key":"ref_21","unstructured":"Balakrishnan, G., and Syed, Z. (2012, January 21\u201323). Scalable personalization of long-term physiological monitoring: Active learning methodologies for epileptic seizure onset detection. Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, La Palma, Canary Islands."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1097\/00019052-200204000-00008","article-title":"Seizure prediction and the preseizure period","volume":"15","author":"Litt","year":"2002","journal-title":"Curr. Opin. Neurol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/j.yebeh.2015.03.010","article-title":"On the proper selection of preictal period for seizure prediction","volume":"46","author":"Bandarabadi","year":"2015","journal-title":"Epilepsy Behav."},{"key":"ref_24","unstructured":"(2017, September 30). IEEG.ORG. Available online: http:\/\/www.ieeg.org\/."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1109\/TBME.2016.2586475","article-title":"SVM-Based System for Prediction of Epileptic Seizures From iEEG Signal","volume":"64","author":"Shiao","year":"2017","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_26","unstructured":"Xiao, C., Wang, S., Iasemidis, L., Wong, S., and Chaovalitwongse, W.A. (2017). An Adaptive Pattern Learning Framework to Personalize Online Seizure Prediction. IEEE Trans. Big Data."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1109\/TNSRE.2015.2458982","article-title":"Epileptic seizure prediction by exploiting spatiotemporal relationship of EEG signals using phase correlation","volume":"24","author":"Parvez","year":"2016","journal-title":"IEEE Trans. Neural Syst. Rehabilit. Eng."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1016\/j.clinph.2017.04.026","article-title":"Seizure prediction in patients with focal hippocampal epilepsy","volume":"128","author":"Aarabi","year":"2017","journal-title":"Clin. Neurophysiol."},{"key":"ref_29","unstructured":"Hansen, D.L., Ecker, R.M., and Solheim, P.R. (2014). Pacemaker Event Queue to Control Device Processor Operating Power. (8,634,914), U.S. Patent."},{"key":"ref_30","unstructured":"Venkatesan, L., Bornzin, G.A., Bharmi, R., Nabutovsky, Y., Shah, R., and Wilson, K. (2016). Systems and Methods for Performing Deep Brain Stimulation. (9,247,895), U.S. Patent."},{"key":"ref_31","unstructured":"Howell, F.W., MacLEOD, J., and Rodbard, D. (2014). Method and System to Indicate Glycemic Impacts of Insulin Infusion Pump Commands. (App. 13\/612,506), U.S. Patent."},{"key":"ref_32","unstructured":"Dueck, W.F., Pawsey, N.C.K., Sibary, P.R., and Tasche, C. (2016). Cochlear Implant Stimulation. (9,440,073), U.S. Patent."},{"key":"ref_33","unstructured":"Kaku, T. (2012). Endoscope System. (App. 13\/323,568), U.S. Patent."},{"key":"ref_34","unstructured":"Modha, D.S. (2017, September 30). Available online: http:\/\/www.research.ibm.com\/articles\/brain-chip.shtml."},{"key":"ref_35","unstructured":"Buzsaki, G. (2006). Rhythms of the Brain, Oxford University Press."},{"key":"ref_36","first-page":"8","article-title":"Heart rate variability as a biomarker for epilepsy seizure prediction","volume":"3","author":"Moridani","year":"2017","journal-title":"Clin. Study"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1713","DOI":"10.1093\/brain\/aww045","article-title":"Crowdsourcing reproducible seizure forecasting in human and canine epilepsy","volume":"139","author":"Brinkmann","year":"2016","journal-title":"Brain"},{"key":"ref_38","unstructured":"Kuhlmann, L. (2017, September 30). Available online: https:\/\/www.epilepsyecosystem.org\/."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.jneumeth.2015.06.010","article-title":"Seizure prediction for therapeutic devices: A review","volume":"260","author":"Gadhoumi","year":"2016","journal-title":"J. Neurosci. Methods"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1745","DOI":"10.1016\/j.clinph.2013.04.006","article-title":"Seizure prediction in patients with mesial temporal lobe epilepsy using EEG measures of state similarity","volume":"124","author":"Gadhoumi","year":"2013","journal-title":"Clin. Neurophysiol."},{"key":"ref_41","unstructured":"Gupta, M. (2016). Complexity Reduction for Near Real-Time High Dimensional Filtering and Estimation Applied to Biological Signals. [Ph.D. Thesis, Harvard University]."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/s10994-015-5519-7","article-title":"Multi-task seizure detection: Addressing intra-patient variation in seizure morphologies","volume":"102","author":"Smith","year":"2016","journal-title":"Mach. Learn."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"036015","DOI":"10.1088\/1741-2560\/8\/3\/036015","article-title":"Modeling electroencephalography waveforms with semi-supervised deep belief nets: Fast classification and anomaly measurement","volume":"8","author":"Wulsin","year":"2011","journal-title":"J. Neural Eng."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"S94","DOI":"10.1016\/j.yebeh.2011.09.001","article-title":"Seizure prediction: Methods","volume":"22","author":"Carney","year":"2011","journal-title":"Epilepsy Behav."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1767","DOI":"10.1016\/j.tcs.2010.12.054","article-title":"Two faces of active learning","volume":"412","author":"Dasgupta","year":"2011","journal-title":"Theor. Comput. Sci."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Settles, B., and Craven, M. (2008, January 25\u201327). An analysis of active learning strategies for sequence labeling tasks. Proceedings of the Conference on Empirical Methods in Natural Language Processing, Honolulu, Hawaii.","DOI":"10.3115\/1613715.1613855"},{"key":"ref_47","unstructured":"Zhao, L., Sukthankar, G., and Sukthankar, R. (2012, January 11\u201315). Importance-weighted label prediction for active learning with noisy annotations. Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), Tsukuba, Japan."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Culotta, A., and McCallum, A. (2004, January 2\u20137). Confidence estimation for information extraction. Proceedings of the HLT-NAACL 2004: Short Papers, Boston, MA, USA.","DOI":"10.3115\/1613984.1614012"},{"key":"ref_49","unstructured":"(2017, September 30). MSEL-LAB. Available online: http:\/\/msel.mayo.edu\/data.html."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Page, A., Oates, S.P.T., and Mohsenin, T. (2015, January 25\u201329). An ultra low power feature extraction and classification system for wearable seizure detection. Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy.","DOI":"10.1109\/EMBC.2015.7320031"},{"key":"ref_51","unstructured":"Platt, J.C. (1999). Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. Advances in Large Margin Classifiers, MIT Press."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/S1525-5050(03)00105-7","article-title":"The seizure prediction characteristic: A general framework to assess and compare seizure prediction methods","volume":"4","author":"Winterhalder","year":"2003","journal-title":"Epilepsy Behav."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1016\/j.clinph.2014.05.022","article-title":"Epileptic seizure prediction using relative spectral power features","volume":"126","author":"Bandarabadi","year":"2015","journal-title":"Clin. Neurophys."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1109\/TNSRE.2013.2282153","article-title":"Seizure prediction using spike rate of intracranial EEG","volume":"21","author":"Li","year":"2013","journal-title":"IEEE Trans. Neural Syst. Rehabilit. Eng."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1016\/j.yebeh.2012.07.007","article-title":"Seizure prediction using EEG spatiotemporal correlation structure","volume":"25","author":"Williamson","year":"2012","journal-title":"Epilepsy Behav."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.1016\/j.clinph.2012.01.014","article-title":"A rule-based seizure prediction method for focal neocortical epilepsy","volume":"123","author":"Aarabi","year":"2012","journal-title":"Clin. Neurophysiol."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.eplepsyres.2010.07.014","article-title":"Patient-specific bivariate-synchrony-based seizure prediction for short prediction horizons","volume":"91","author":"Kuhlmann","year":"2010","journal-title":"Epilepsy Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/6\/1698\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T15:05:49Z","timestamp":1760195149000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/18\/6\/1698"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,24]]},"references-count":57,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2018,6]]}},"alternative-id":["s18061698"],"URL":"https:\/\/doi.org\/10.3390\/s18061698","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,24]]}}}