{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T18:58:23Z","timestamp":1774378703436,"version":"3.50.1"},"reference-count":54,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T00:00:00Z","timestamp":1677196800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T00:00:00Z","timestamp":1677196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100015539","name":"Australia Government","doi-asserted-by":"crossref","award":["Research Training Program (RTP)"],"award-info":[{"award-number":["Research Training Program (RTP)"]}],"id":[{"id":"10.13039\/100015539","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Microsoft","award":["Microsoft AI for Accessibility grant."],"award-info":[{"award-number":["Microsoft AI for Accessibility grant."]}]},{"DOI":"10.13039\/501100001774","name":"The University of Sydney","doi-asserted-by":"crossref","award":["SOAR Fellowship"],"award-info":[{"award-number":["SOAR Fellowship"]}],"id":[{"id":"10.13039\/501100001774","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Neuromorph. Comput. Eng."],"published-print":{"date-parts":[[2023,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    The vast majority of studies that process and analyze neural signals are conducted on cloud computing resources, which is often necessary for the demanding requirements of deep neural network workloads. However, applications such as epileptic seizure detection stand to benefit from edge devices that can securely analyze sensitive medical data in a real-time and personalised manner. In this work, we propose a novel neuromorphic computing approach to seizure detection using a surrogate gradient-based deep spiking neural network (SNN), which consists of a novel spiking ConvLSTM unit. We have trained, validated, and rigorously tested the proposed SNN model across three publicly accessible datasets, including Boston Children\u2019s Hospital\u2013MIT (CHB-MIT) dataset from the U.S., and the Freiburg (FB) and EPILEPSIAE intracranial electroencephalogram datasets from Germany. The average leave-one-out cross-validation area under the curve score for FB, CHB-MIT and EPILEPSIAE datasets can reach 92.7\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mi mathvariant=\"normal\">%<\/mml:mi>\n                      <\/mml:math>\n                      <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"nceacbab8ieqn1.gif\" xlink:type=\"simple\"\/>\n                    <\/jats:inline-formula>\n                    , 89.0\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mi mathvariant=\"normal\">%<\/mml:mi>\n                      <\/mml:math>\n                      <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"nceacbab8ieqn2.gif\" xlink:type=\"simple\"\/>\n                    <\/jats:inline-formula>\n                    , and 81.1\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mi mathvariant=\"normal\">%<\/mml:mi>\n                      <\/mml:math>\n                      <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"nceacbab8ieqn3.gif\" xlink:type=\"simple\"\/>\n                    <\/jats:inline-formula>\n                    , respectively, while the computational overhead and energy consumption are significantly reduced when compared to alternative state-of-the-art models, showing the potential for building an accurate hardware-friendly, low-power neuromorphic system. This is the first feasibility study using a deep SNN for seizure detection on several reliable public datasets.\n                  <\/jats:p>","DOI":"10.1088\/2634-4386\/acbab8","type":"journal-article","created":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T17:28:35Z","timestamp":1675963715000},"page":"014010","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":36,"title":["Neuromorphic deep spiking neural networks for seizure detection"],"prefix":"10.1088","volume":"3","author":[{"given":"Yikai","family":"Yang","sequence":"first","affiliation":[]},{"given":"Jason K","family":"Eshraghian","sequence":"additional","affiliation":[]},{"given":"Nhan","family":"Duy Truong","sequence":"additional","affiliation":[]},{"given":"Armin","family":"Nikpour","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2753-5553","authenticated-orcid":true,"given":"Omid","family":"Kavehei","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2023,2,24]]},"reference":[{"key":"nceacbab8bib1","first-page":"pp 1","article-title":"The economic burden of epilepsy in Australia, 2019\u20132020","author":"","year":"2020"},{"key":"nceacbab8bib2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1528-1167.2009.02397.x","article-title":"Definition of drug resistant epilepsy: consensus proposal by the ad hoc task force of the ILAE commission on therapeutic strategies","author":"Kwan","year":"2010"},{"key":"nceacbab8bib3","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.eplepsyres.2009.03.003","article-title":"The descriptive epidemiology of epilepsy\u2014a review","volume":"85","author":"Banerjee","year":"2009","journal-title":"Epilepsy Res."},{"key":"nceacbab8bib4","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.phrs.2016.03.003","article-title":"Addressing the burden of epilepsy: many unmet needs","volume":"107","author":"Beghi","year":"2016","journal-title":"Pharmacol. Res."},{"key":"nceacbab8bib5","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/S1474-4422(05)70020-X","article-title":"Epilepsy and social identity: the stigma of a chronic neurological disorder","volume":"4","author":"Jacoby","year":"2005","journal-title":"Lancet Neurol."},{"key":"nceacbab8bib6","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1590\/S0004-282X2012000200013","article-title":"Quality of life issues and occupational performance of persons with epilepsy","volume":"70","author":"Nickel","year":"2012","journal-title":"Arq. Neuro-Psiquiatr."},{"key":"nceacbab8bib7","doi-asserted-by":"publisher","first-page":"e3221","DOI":"10.1212\/WNL.0000000000010862","article-title":"The costs of epilepsy in Australia: a productivity-based analysis","volume":"95","author":"Foster","year":"2020","journal-title":"Neurology"},{"key":"nceacbab8bib8","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/S0920-1211(00)00126-1","article-title":"The impact of epilepsy from the patient\u2019s perspective I. Descriptions and subjective perceptions","volume":"41","author":"Fisher","year":"2000","journal-title":"Epilepsy Res."},{"key":"nceacbab8bib9","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1111\/epi.12550","article-title":"ILAE official report: a practical clinical definition of epilepsy","volume":"55","author":"Fisher","year":"2014","journal-title":"Epilepsia"},{"key":"nceacbab8bib10","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1684\/epd.2020.1151","article-title":"The role of EEG in patients with suspected epilepsy","volume":"22","author":"Benbadis","year":"2020","journal-title":"Epileptic Disorders"},{"key":"nceacbab8bib11","doi-asserted-by":"publisher","first-page":"5780","DOI":"10.3390\/ijerph18115780","article-title":"Epileptic seizures detection using deep learning techniques: a review","volume":"18","author":"Shoeibi","year":"2021","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"nceacbab8bib12","doi-asserted-by":"publisher","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 Inf."},{"key":"nceacbab8bib13","first-page":"pp 2191","article-title":"A comparative study of AI systems for epileptic seizure recognition based on EEG or ECG","author":"Yang","year":"2021"},{"key":"nceacbab8bib14","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.ebiom.2017.11.032","article-title":"Epileptic seizure prediction using big data and deep learning: toward a mobile system","volume":"27","author":"Kiral-Kornek","year":"2018","journal-title":"EBioMedicine"},{"key":"nceacbab8bib15","first-page":"pp 1737","article-title":"Deep learning with limited numerical precision","author":"Gupta","year":"2015"},{"key":"nceacbab8bib16","article-title":"MobileNets: efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"nceacbab8bib17","first-page":"pp 806","article-title":"Sparse convolutional neural networks","author":"Liu","year":"2015"},{"key":"nceacbab8bib18","article-title":"Learning sparse neural networks through L 0 regularization","author":"Louizos","year":"2017"},{"key":"nceacbab8bib19","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"nceacbab8bib20","article-title":"Deep rewiring: training very sparse deep networks","author":"Bellec","year":"2017"},{"key":"nceacbab8bib21","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1145\/3140659.3080254","article-title":"SCNN: an accelerator for compressed-sparse convolutional neural networks","volume":"45","author":"Parashar","year":"2017","journal-title":"ACM SIGARCH Comput. Archit. News"},{"key":"nceacbab8bib22","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MNANO.2022.3141443","article-title":"Memristor-based binarized spiking neural networks: challenges and applications","volume":"16","author":"Eshraghian","year":"2022","journal-title":"IEEE Nanotechnol. Mag."},{"key":"nceacbab8bib23","article-title":"Training spiking neural networks using lessons from deep learning","author":"Eshraghian","year":"2021"},{"key":"nceacbab8bib24","first-page":"pp 254","article-title":"Efficient neuromorphic signal processing with Loihi 2","author":"Orchard","year":"2021"},{"key":"nceacbab8bib25","first-page":"pp 1","article-title":"Reckon: a 28nm sub-mm2 task-agnostic spiking recurrent neural network processor enabling on- chip learning over second-long timescales","volume":"vol 65","author":"Frenkel","year":"2022"},{"key":"nceacbab8bib26","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/s41586-019-1677-2","article-title":"Towards spike-based machine intelligence with neuromorphic computing","volume":"575","author":"Roy","year":"2019","journal-title":"Nature"},{"key":"nceacbab8bib27","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1109\/LED.2019.2900867","article-title":"Inherent stochastic learning in CMOS-integrated HfO2 arrays for neuromorphic computing","volume":"40","author":"Wenger","year":"2019","journal-title":"IEEE Electron Device Lett."},{"key":"nceacbab8bib28","first-page":"pp 1","article-title":"A new neuromorphic computing approach for epileptic seizure prediction","author":"Tian","year":"2021"},{"key":"nceacbab8bib29","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.220374","article-title":"Weak self-supervised learning for seizure forecasting: a feasibility study","volume":"9","author":"Yang","year":"2022","journal-title":"R. Soc. Open Sci."},{"key":"nceacbab8bib30","article-title":"The fine line between dead neurons and sparsity in binarized spiking neural networks","author":"Eshraghian","year":"2022"},{"key":"nceacbab8bib31","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1109\/MSP.2019.2931595","article-title":"Surrogate gradient learning in spiking neural networks: bringing the power of gradient-based optimization to spiking neural networks","volume":"36","author":"Neftci","year":"2019","journal-title":"IEEE Signal Process. Mag."},{"key":"nceacbab8bib32","first-page":"pp 389","article-title":"Epileptic seizure detection using a neuromorphic-compatible deep spiking neural network","author":"Zarrin","year":"2020"},{"key":"nceacbab8bib33","article-title":"Application of machine learning to epileptic seizure onset detection and treatment","author":"Shoeb","year":"2009"},{"key":"nceacbab8bib34","article-title":"EEG Database at the Epilepsy Center of the University Hospital of Freiburg, Germany","author":"","year":"2003"},{"key":"nceacbab8bib35","doi-asserted-by":"publisher","DOI":"10.1111\/j.1528-1167.2012.03564.x","article-title":"The EPILEPSIAE database: an extensive electroencephalography database of epilepsy patients","author":"Klatt","year":"2012"},{"key":"nceacbab8bib36","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1109\/JETCAS.2018.2842761","article-title":"Integer convolutional neural network for seizure detection","volume":"8","author":"Truong","year":"2018","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"key":"nceacbab8bib37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-020-0264-0","article-title":"Weak supervision as an efficient approach for automated seizure detection in electroencephalography","volume":"3","author":"Saab","year":"2020","journal-title":"npj Digit. Med."},{"key":"nceacbab8bib38","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118083","article-title":"Continental generalization of an AI system for clinical seizure recognition","volume":"207","author":"Yang","year":"2022","journal-title":"Expert Syst. Appl."},{"key":"nceacbab8bib39","doi-asserted-by":"publisher","first-page":"83","DOI":"10.3389\/fninf.2018.00083","article-title":"The Temple University Hospital seizure detection corpus","volume":"12","author":"Shah","year":"2018","journal-title":"Front. Neuroinform."},{"key":"nceacbab8bib40","doi-asserted-by":"publisher","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":"nceacbab8bib41","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1002\/ana.22548","article-title":"High-frequency oscillations as a new biomarker in epilepsy","volume":"71","author":"Zijlmans","year":"2012","journal-title":"Ann. Neurol."},{"key":"nceacbab8bib42","article-title":"Self-supervised graph neural networks for improved electroencephalographic seizure analysis","author":"Tang","year":"2022"},{"key":"nceacbab8bib43","first-page":"pp 802","article-title":"Convolutional LSTM network: a machine learning approach for precipitation nowcasting","volume":"vol 2015","author":"Shi","year":"2015"},{"key":"nceacbab8bib44","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"nceacbab8bib45","first-page":"pp 2623","article-title":"Optuna: a next-generation hyperparameter optimization framework","author":"Akiba","year":"2019"},{"key":"nceacbab8bib46","article-title":"KerasSpiking package for estimating model energy","author":"","year":"2021"},{"key":"nceacbab8bib47","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/TVLSI.2015.2392942","article-title":"Assessing trends in performance per watt for signal processing applications","volume":"24","author":"Degnan","year":"2015","journal-title":"IEEE Trans. Very Large Scale Integr. (VLSI) Syst."},{"key":"nceacbab8bib48","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MM.2018.112130359","article-title":"Loihi: a neuromorphic manycore processor with on-chip learning","volume":"38","author":"Davies","year":"2018","journal-title":"IEEE Micro"},{"key":"nceacbab8bib49","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1109\/TBME.2003.810689","article-title":"Adaptive epileptic seizure prediction system","volume":"50","author":"Iasemidis","year":"2003","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"nceacbab8bib50","doi-asserted-by":"publisher","first-page":"172","DOI":"10.3389\/fneur.2018.00172","article-title":"Predictability and resetting in a case of convulsive status epilepticus","volume":"9","author":"Hutson","year":"2018","journal-title":"Frontiers Neurol."},{"key":"nceacbab8bib51","first-page":"323","article-title":"Frequency evolution during tonic-clonic seizures","volume":"42","author":"Quiroga","year":"2002","journal-title":"Electromyogr. Clin. Neurophysiol."},{"key":"nceacbab8bib52","doi-asserted-by":"publisher","first-page":"637","DOI":"10.3389\/fnins.2020.00637","article-title":"Hand-gesture recognition based on EMG and event-based camera sensor fusion: a benchmark in neuromorphic computing","volume":"14","author":"Ceolini","year":"2020","journal-title":"Front. Neurosci."},{"key":"nceacbab8bib53","doi-asserted-by":"publisher","first-page":"4837","DOI":"10.1109\/TCSI.2021.3126555","article-title":"How to build a memristive integrate-and-fire model for spiking neuronal signal generation","volume":"68","author":"Kang","year":"2021","journal-title":"IEEE Trans. Circuits Syst. I"},{"key":"nceacbab8bib54","doi-asserted-by":"crossref","DOI":"10.1109\/JETCAS.2022.3224071","article-title":"Gradient-based neuromorphic learning on dynamical RRAM arrays","author":"Zhou","year":"2022"}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acbab8","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acbab8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acbab8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acbab8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acbab8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acbab8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acbab8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acbab8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T08:10:03Z","timestamp":1677226203000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/acbab8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,24]]},"references-count":54,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,2,24]]},"published-print":{"date-parts":[[2023,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/acbab8","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.20444970","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.20444970.v1","asserted-by":"object"}]},"ISSN":["2634-4386"],"issn-type":[{"value":"2634-4386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,24]]},"assertion":[{"value":"Neuromorphic deep spiking neural networks for seizure detection","name":"article_title","label":"Article Title"},{"value":"Neuromorphic Computing and Engineering","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-10-11","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-02-09","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-02-24","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}