{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T22:48:51Z","timestamp":1790808531144,"version":"4.1.0"},"reference-count":36,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2021,6,23]],"date-time":"2021-06-23T00:00:00Z","timestamp":1624406400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Biosensors"],"abstract":"<jats:p>The treatment of refractory epilepsy via closed-loop implantable devices that act on seizures either by drug release or electrostimulation is a highly attractive option. For such implantable medical devices, efficient and low energy consumption, small size, and efficient processing architectures are essential. To meet these requirements, epileptic seizure detection by analysis and classification of brain signals with a convolutional neural network (CNN) is an attractive approach. This work presents a CNN for epileptic seizure detection capable of running on an ultra-low-power microprocessor. The CNN is implemented and optimized in MATLAB. In addition, the CNN is also implemented on a GAP8 microprocessor with RISC-V architecture. The training, optimization, and evaluation of the proposed CNN are based on the CHB-MIT dataset. The CNN reaches a median sensitivity of 90% and a very high specificity over 99% corresponding to a median false positive rate of 6.8 s per hour. After implementation of the CNN on the microcontroller, a sensitivity of 85% is reached. The classification of 1 s of EEG data takes t=35 ms and consumes an average power of P\u2248140 \u03bcW. The proposed detector outperforms related approaches in terms of power consumption by a factor of 6. The universal applicability of the proposed CNN based detector is verified with recording of epileptic rats. This results enable the design of future medical devices for epilepsy treatment.<\/jats:p>","DOI":"10.3390\/bios11070203","type":"journal-article","created":{"date-parts":[[2021,6,23]],"date-time":"2021-06-23T04:33:28Z","timestamp":1624422808000},"page":"203","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":35,"title":["Epileptic Seizure Detection on an Ultra-Low-Power Embedded RISC-V Processor Using a Convolutional Neural Network"],"prefix":"10.3390","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8012-6794","authenticated-orcid":false,"given":"Andreas","family":"Bahr","sequence":"first","affiliation":[{"name":"Sensor System Electronics, Institute of Electrical Engineering and Information Technology, Kiel University, 24143 Kiel, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Schneider","sequence":"additional","affiliation":[{"name":"Sensor System Electronics, Institute of Electrical Engineering and Information Technology, Kiel University, 24143 Kiel, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria","family":"Francis","sequence":"additional","affiliation":[{"name":"Sensor System Electronics, Institute of Electrical Engineering and Information Technology, Kiel University, 24143 Kiel, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hendrik","family":"Lehmann","sequence":"additional","affiliation":[{"name":"CMOS Design, Technical University Braunschweig, 38106 Braunschweig, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Igor","family":"Barg","sequence":"additional","affiliation":[{"name":"Multicomponent Materials, Institute for Material Science, Kiel University, 24143 Kiel, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna-Sophia","family":"Buschhoff","sequence":"additional","affiliation":[{"name":"Institute of Physiology, Kiel University, 24118 Kiel, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peer","family":"Wulff","sequence":"additional","affiliation":[{"name":"Institute of Physiology, Kiel University, 24118 Kiel, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3931-5635","authenticated-orcid":false,"given":"Thomas","family":"Strunskus","sequence":"additional","affiliation":[{"name":"Multicomponent Materials, Institute for Material Science, Kiel University, 24143 Kiel, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3367-1655","authenticated-orcid":false,"given":"Franz","family":"Faupel","sequence":"additional","affiliation":[{"name":"Multicomponent Materials, Institute for Material Science, Kiel University, 24143 Kiel, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,23]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2021, June 21). Epilepsy: Key Facts. Available online: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/epilepsy."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1016\/S1525-5050(03)00111-2","article-title":"The impact of epilepsy on quality of life: A qualitative analysis","volume":"4","author":"Bishop","year":"2003","journal-title":"Epilepsy Behav."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1017\/S1092852900008464","article-title":"The Consequences of Uncontrolled Epilepsy","volume":"9","author":"Sperling","year":"2004","journal-title":"CNS Spectrums"},{"key":"ref_4","unstructured":"National Institute of Neurological Disorders and Stroke (2015). Epilepsy: Hope Through Research, NIH Publication."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"606","DOI":"10.1124\/pr.120.019539","article-title":"Drug Resistance in Epilepsy: Clinical Impact, Potential Mechanisms, and New Innovative Treatment Options","volume":"72","author":"Potschka","year":"2020","journal-title":"Pharmacol. Rev."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1001\/jamaneurol.2017.3949","article-title":"Treatment Outcomes in Patients With Newly Diagnosed Epilepsy Treated With Established and New Antiepileptic Drugs: A 30-Year Longitudinal Cohort Study","volume":"75","author":"Chen","year":"2018","journal-title":"JAMA Neurol."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Gernert, M., and Feja, M. (2020). Bypassing the Blood\u2013Brain Barrier: Direct Intracranial Drug Delivery in Epilepsies. Pharmaceutics, 12.","DOI":"10.3390\/pharmaceutics12121134"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1097\/WCO.0000000000000534","article-title":"Neurostimulation for drug-resistant epilepsy: A systematic review of clinical evidence for efficacy, safety, contraindications and predictors for response","volume":"31","author":"Trinka","year":"2018","journal-title":"Curr. Opin. Neurol."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Stevanovic, D. (2012). Automated Epileptic Seizure Detection Methods: A Review Study. Epilepsy\u2014Histological, Electroencephalographic and Psychological Aspects, InTech.","DOI":"10.5772\/1194"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1680","DOI":"10.1093\/brain\/awx098","article-title":"Crowdsourcing seizure detection: Algorithm development and validation on human implanted device recordings","volume":"140","author":"Baldassano","year":"2017","journal-title":"Brain A J. Neurol."},{"key":"ref_11","first-page":"056013.1","article-title":"EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfaces","volume":"15","author":"Lawhern","year":"2016","journal-title":"J. Neural Eng."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"H\u00fcgle, M., Heller, S., Watter, M., Blum, M., Manzouri, F., D\u00fcmpelmann, M., Schulze-Bonhage, A., Woias, P., and Boedecker, J. (2018). Early Seizure Detection with an Energy-Efficient Convolutional Neural Network on an Implantable Microcontroller. arXiv.","DOI":"10.1109\/IJCNN.2018.8489493"},{"key":"ref_13","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_14","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_15","doi-asserted-by":"crossref","unstructured":"Bahr, A., Saleh, L.A., Hinsch, R., Schroeder, D., Isbrandt, D., and Krautschneider, W.H. (2016, January 17\u201320). Small area, low power neural recording integrated circuit in 130 nm CMOS technology for small mammalians. Proceedings of the 2016 28th International Conference on Microelectronics (ICM), Giza, Egypt.","DOI":"10.1109\/ICM.2016.7847887"},{"key":"ref_16","unstructured":"Bahr, A. (2017). Aufnahme Von Hirnsignalen Mit Extrem Miniaturisierten Elektronischen Systemen Zur Untersuchung Von Lokalen Neuronalen Vernetzungen, Logos Verlag Berlin."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1109\/TBCAS.2012.2222881","article-title":"A Battery-Free Multichannel Digital Neural\/EMG Telemetry System for Flying Insects","volume":"6","author":"Thomas","year":"2012","journal-title":"IEEE Trans. Biomed. Circuits Syst."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Laiwalla, F., Lee, J., Lee, A., Mok, E., Leung, V., Shellhammer, S., Song, Y., Larson, L., and Nurmikko, A. (2019, January 23\u201327). A Distributed Wireless Network of Implantable Sub-mm Cortical Microstimulators for Brain-Computer Interfaces. Proceedings of the 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany.","DOI":"10.1109\/EMBC.2019.8857217"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1112","DOI":"10.1016\/S1474-4422(19)30321-7","article-title":"An exoskeleton controlled by an epidural wireless brain\u2013machine interface in a tetraplegic patient: A proof-of-concept demonstration","volume":"18","author":"Benabid","year":"2019","journal-title":"Lancet Neurol."},{"key":"ref_20","unstructured":"Shoeb, A. (2009). Application of Machine Learning to Epileptic Seizure Onset Detection and Treatment. [Ph.D. Thesis, Massachusetts Institute of Technology]. Available online: http:\/\/hdl.handle.net\/1721.1\/54669."},{"key":"ref_21","unstructured":"Shoeb, A., and Guttag, J. (2010, January 21\u201325). Application of Machine Learning to Epileptic Seizure Detection. Proceedings of the 27th International Conference on International Conference on Machine Learning, ICML\u201910, Haifa, Israel."},{"key":"ref_22","unstructured":"Dataport, I. (2021, June 21). EEG of Genetic Absence Epilepsy Rats (GAERS). Available online: https:\/\/ieee-dataport.org\/open-access\/eeg-genetic-absence-epilepsy-rats-gaers."},{"key":"ref_23","unstructured":"Greenwaves Technologies (2021, June 21). GAP8 Manual. Available online: https:\/\/greenwaves-technologies.com\/manuals\/BUILD\/HOME\/html\/index.html."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Flamand, E., Rossi, D., Conti, F., Loi, I., Pullini, A., Rotenberg, F., and Benini, L. (2018, January 10\u201312). GAP-8: A RISC-V SoC for AI at the Edge of the IoT. Proceedings of the 2018 IEEE 29th International Conference on Application-specific Systems, Architectures and Processors (ASAP), Milan, Italy.","DOI":"10.1109\/ASAP.2018.8445101"},{"key":"ref_25","unstructured":"SEMICO Research Corporation (2019). RISC-V Market Analysis: The New Kid on the Block, Available online: https:\/\/semico.com\/sites\/default\/files\/TOC_CC315-19.pdf."},{"key":"ref_26","first-page":"31:1","article-title":"A Survey of Predictive Modeling on Imbalanced Domains","volume":"49","author":"Branco","year":"2016","journal-title":"ACM Comput. Surv."},{"key":"ref_27","doi-asserted-by":"crossref","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":"ref_28","unstructured":"Github (2021, June 21). Matlab Source Code. Available online: https:\/\/github.com\/cau-etit-sse\/cnn-chb-mit."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/S1474-4422(20)30414-2","article-title":"Advancing seizure forecasting from cyclical activity data","volume":"20","author":"Cook","year":"2021","journal-title":"Lancet Neurol."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Eberlein, M., Hildebrand, R., Tetzlaff, R., Hoffmann, N., Kuhlmann, L., Brinkmann, B., and Muller, J. (2018, January 3\u20136). Convolutional Neural Networks for Epileptic Seizure Prediction. Proceedings of the 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Madrid, Spain.","DOI":"10.1109\/BIBM.2018.8621225"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"15649","DOI":"10.1038\/s41598-019-52152-2","article-title":"Bispectrum and Recurrent Neural Networks: Improved Classification of Interictal and Preictal States","volume":"9","author":"Gagliano","year":"2019","journal-title":"Sci. Rep."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2284","DOI":"10.1109\/TNSRE.2019.2943707","article-title":"Seizure Prediction in Scalp EEG Using 3D Convolutional Neural Networks With an Image-Based Approach","volume":"27","author":"Ozcan","year":"2019","journal-title":"IEEE Trans. Neural Syst. Rehabil. Eng."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1111\/epi.14052","article-title":"Seizure detection using scalp-EEG","volume":"59","author":"Baumgartner","year":"2018","journal-title":"Epilepsia"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/0013-4694(96)96001-0","article-title":"Automated seizure detection using a self-organizing neural network","volume":"99","author":"Gabor","year":"1996","journal-title":"Electroencephalogr. Clin. Neurophysiol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1832","DOI":"10.1016\/j.clinph.2010.04.016","article-title":"Assessment of a scalp EEG-based automated seizure detection system","volume":"121","author":"Kelly","year":"2010","journal-title":"Clin. Neurophysiol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"2332","DOI":"10.1016\/j.clinph.2007.07.017","article-title":"An efficient, robust and fast method for the offline detection of epileptic seizures in long-term scalp EEG recordings","volume":"118","author":"Kerling","year":"2007","journal-title":"Clin. Neurophysiol."}],"container-title":["Biosensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2079-6374\/11\/7\/203\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:21:38Z","timestamp":1760163698000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2079-6374\/11\/7\/203"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,23]]},"references-count":36,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021,7]]}},"alternative-id":["bios11070203"],"URL":"https:\/\/doi.org\/10.3390\/bios11070203","relation":{},"ISSN":["2079-6374"],"issn-type":[{"value":"2079-6374","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,23]]}}}