{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T17:20:07Z","timestamp":1778606407489,"version":"3.51.4"},"reference-count":47,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIS"],"published-print":{"date-parts":[[2022,1,20]]},"abstract":"<jats:p>Epilepsy is a chronic brain disease resulted from the central nervous system lesion, which leads to repeated seizure occurs for the patients. Automatic seizure detection with Electroencephalogram (EEG) has witnessed great progress. However, existing methods paid little attention to the topological relationships of different EEG electrodes. Latest neuroscience researches have demonstrated the connectivity between different brain regions. Besides, class-imbalance is a common problem in EEG based seizure detection. The duration of epileptic EEG signals is much shorter than that of normal signals. In order to deal with the above mentioned two challenges, we propose to model the multi-channel EEG data using the Attention-based Graph ResNet (AGRN). In particular, each channel of the EEG signal represents a node of the graph and the inter-channel relations are modeled via the adjacency matrix in the graph. The loss function of the ARGN model is re-designed using focal loss to cope with the class-imbalance problem. The proposed ARGN with focal model could learn discriminative features from the raw EEG data. Experiments are carried out on the CHB-MIT dataset. The proposed model achieves an average accuracy of 98.70%, a sensitivity of 97.94%, a specificity of 98.66% and a precision of 98.62%. The Area Under the ROC Curve (AUC) is 98.69%.<\/jats:p>","DOI":"10.3233\/ais-210086","type":"journal-article","created":{"date-parts":[[2021,12,10]],"date-time":"2021-12-10T11:50:22Z","timestamp":1639137022000},"page":"61-73","source":"Crossref","is-referenced-by-count":10,"title":["Attention-based Graph ResNet with focal loss for epileptic seizure detection"],"prefix":"10.1177","volume":"14","author":[{"given":"Changxu","family":"Dong","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan 250358, P.R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanna","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan 250358, P.R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaobo","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan 250358, P.R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingrui","family":"Xue","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan 250358, P.R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengyu","family":"Chu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan 250358, P.R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiatong","family":"He","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan 250358, P.R.\u00a0China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinting","family":"Ge","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong Normal University, Jinan 250358, P.R.\u00a0China"},{"name":"School of Medical Imaging, Xuzhou Medical University, 221004, Xuzhou, Jiangsu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/AIS-210086_ref1","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1016\/j.compbiomed.2017.09.017","article-title":"Deep convolutional neural network for the automated detection and diagnosis of seizure using EEG signals","volume":"100","author":"Acharya","year":"2018","journal-title":"Computers in Biology and Medicine"},{"issue":"1","key":"10.3233\/AIS-210086_ref2","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/S0165-0270(02)00340-0","article-title":"Analysis of EEG records in an epileptic patient using wavelet transform","volume":"123","author":"Adeli","year":"2003","journal-title":"Journal of Neuroscience Methods"},{"issue":"3","key":"10.3233\/AIS-210086_ref3","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TNSRE.2015.2505238","article-title":"Analysis of high-dimensional phase space via Poincare section for patient-specific seizure detection","volume":"24","author":"Aggelos","year":"2016","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"issue":"4","key":"10.3233\/AIS-210086_ref4","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1016\/j.physd.2011.09.008","article-title":"Visibility graph similarity: A\u00a0new measure of generalized synchronization in coupled dynamic systems","volume":"241","author":"Ahmadlou","year":"2012","journal-title":"Physica\u00a0D: Nonlinear Phenomena"},{"issue":"3","key":"10.3233\/AIS-210086_ref5","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1177\/1550059413480504","article-title":"Spatiotemporal analysis of relative convergence of EEGs reveals differences between brain dynamics of depressive women and men","volume":"44","author":"Ahmadlou","year":"2013","journal-title":"Clinical EEG and Neuroscience"},{"key":"10.3233\/AIS-210086_ref6","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065718500119"},{"key":"10.3233\/AIS-210086_ref7","doi-asserted-by":"crossref","unstructured":"A.\u00a0Antoniades, L.\u00a0Spyrou, C.C.\u00a0Took and S.\u00a0Sanei, Deep learning for epileptic intracranial EEG data, in: IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP), 2016, pp.\u00a01\u20136.","DOI":"10.1109\/MLSP.2016.7738824"},{"key":"10.3233\/AIS-210086_ref8","doi-asserted-by":"publisher","first-page":"7716","DOI":"10.1109\/ACCESS.2016.2585661","article-title":"DWT based epileptic seizure detection from EEG signals using naive Bayes\/ k-NN classifiers","volume":"4","author":"Ashok","year":"2016","journal-title":"IEEE Access"},{"key":"10.3233\/AIS-210086_ref9","doi-asserted-by":"crossref","unstructured":"M.\u00a0Avcu, Z.\u00a0Zhang and D.\u00a0Chan, Seizure detection using least EEG channels by deep convolutional neural network, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, pp.\u00a01120\u20131124.","DOI":"10.1109\/ICASSP.2019.8683229"},{"issue":"4","key":"10.3233\/AIS-210086_ref10","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MSP.2017.2693418","article-title":"Geometric deep learning: Going beyond Euclidean data","volume":"34","author":"Bronstein","year":"2017","journal-title":"IEEE Signal Processing Magazine"},{"key":"10.3233\/AIS-210086_ref11","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0173138"},{"key":"10.3233\/AIS-210086_ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20351-1_22"},{"key":"10.3233\/AIS-210086_ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20351-1_22"},{"key":"10.3233\/AIS-210086_ref15","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume":"29","author":"Defferrard","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"2","key":"10.3233\/AIS-210086_ref16","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1097\/00019052-200104000-00008","article-title":"Future trends in epileptology","volume":"14","author":"Elger","year":"2001","journal-title":"Current Opinion in Neurology"},{"issue":"4","key":"10.3233\/AIS-210086_ref17","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1111\/epi.12550","article-title":"ILAE official report: A\u00a0practical clinical definition of epilepsy","volume":"55","author":"Fisher","year":"2014","journal-title":"Epilepsia"},{"key":"10.3233\/AIS-210086_ref18","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.jneumeth.2014.05.019","article-title":"An efficient seizure prediction method using KNN-based undersampling and linear frequency measures","volume":"232","author":"Ghaderyan","year":"2014","journal-title":"Journal of Neuroscience Methods"},{"key":"10.3233\/AIS-210086_ref20","doi-asserted-by":"crossref","unstructured":"M.\u00a0Golmohammadi, S.\u00a0Ziyabari, V.\u00a0Shah, E.\u00a0Von Weltin, C.\u00a0Campbell, I.\u00a0Obeid and J.\u00a0Picone, Gated recurrent networks for seizure detection, in: 2017 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), 2017.","DOI":"10.1109\/SPMB.2017.8257020"},{"issue":"5","key":"10.3233\/AIS-210086_ref21","doi-asserted-by":"publisher","first-page":"373","DOI":"10.3233\/AIS-210611","article-title":"A\u00a0novel computer vision-based data driven modelling approach for person specific fall detection","volume":"13","author":"Gong","year":"2021","journal-title":"Journal of Ambient Intelligence and Smart Environments"},{"issue":"5","key":"10.3233\/AIS-210086_ref22","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1016\/0013-4694(82)90038-4","article-title":"Automatic recognition of epileptic seizures in the EEG","volume":"54","author":"Gotman","year":"1982","journal-title":"Electroencephalography and Clinical Neurophysiology"},{"issue":"1","key":"10.3233\/AIS-210086_ref23","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.jneumeth.2010.08.030","article-title":"Epileptic seizure detection using multiwavelet transform based approximate entropy and artificial neural networks","volume":"193","author":"Guo","year":"2010","journal-title":"Journal of Neuroscience Methods"},{"key":"10.3233\/AIS-210086_ref24","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.neucom.2019.12.010","article-title":"A\u00a0novel automatic classification detection for epileptic seizure based on dictionary learning and sparse representation","volume":"424","author":"Hong","year":"2021","journal-title":"Neurocomputing"},{"issue":"7","key":"10.3233\/AIS-210086_ref25","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1016\/j.compbiomed.2008.04.010","article-title":"A\u00a0multi-level wavelet approach for automatic detection of epileptic spikes in the electroencephalogram","volume":"38","author":"Indiradevi","year":"2008","journal-title":"Computers in Biology and Medicine"},{"issue":"3","key":"10.3233\/AIS-210086_ref27","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1109\/TKDE.2005.50","article-title":"Using AUC and accuracy in evaluating learning algorithms","volume":"17","author":"Jin","year":"2005","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"10.3233\/AIS-210086_ref28","first-page":"5766","article-title":"Seizure detection in EEG using biorthogonal wavelet and fuzzy KNN classifier","author":"Jose","year":"2010","journal-title":"Elixir Hum Physiol"},{"issue":"7","key":"10.3233\/AIS-210086_ref29","doi-asserted-by":"crossref","first-page":"347","DOI":"10.3233\/AIS-210609","article-title":"Urban management image classification approach based on deep learning","volume":"13","author":"Kang","year":"2021","journal-title":"Journal of Ambient Intelligence and Smart Environments"},{"key":"10.3233\/AIS-210086_ref30","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Khan, N.\u00a0Rafiuddin and O.\u00a0Farooq, Automated seizure detection in scalp EEG using multiple wavelet scales, in: Proceedings of the International Conference on Signal Processing, Computing and Control, 2012, pp.\u00a01\u20135.","DOI":"10.1109\/ISPCC.2012.6224361"},{"key":"10.3233\/AIS-210086_ref31","unstructured":"T.N.\u00a0Kipf and M.\u00a0Welling, Semi-supervised classification with graph convolutional networks, in: International Conference on Learning Representations, 2017."},{"key":"10.3233\/AIS-210086_ref32","doi-asserted-by":"crossref","unstructured":"T.\u00a0Lin, P.\u00a0Goyal, R.\u00a0Girshick, K.\u00a0He and P.\u00a0Doll\u00e1r, Focal loss for dense object detection, in: IEEE International Conference on Computer Vision, 2017, pp.\u00a02999\u20133007.","DOI":"10.1109\/ICCV.2017.324"},{"issue":"2","key":"10.3233\/AIS-210086_ref33","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1109\/TPAMI.2018.2858826","article-title":"Focal loss for dense object detection","volume":"42","author":"Lin","year":"2020","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"2","key":"10.3233\/AIS-210086_ref34","first-page":"141","article-title":"Seizure control through genetic and pharmacological manipulation of pumilio in Drosophila: A\u00a0key component of neuronal homeostasis","volume":"10","author":"Lin","year":"2017","journal-title":"Disease Models and Mechanisms"},{"issue":"2","key":"10.3233\/AIS-210086_ref35","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1080\/09540261.2017.1282438","article-title":"Closed loop neuromodulation systems: Next generation treatments for psychiatric illness","volume":"29","author":"Lo","year":"2017","journal-title":"International Review of Psychiatry"},{"key":"10.3233\/AIS-210086_ref37","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.neulet.2018.12.015","article-title":"Visibility graph analysis of speech evoked auditory brainstem response in persistent developmental stuttering","volume":"696","author":"Mozaffarilegha","year":"2019","journal-title":"Neuroscience Letters"},{"key":"10.3233\/AIS-210086_ref38","doi-asserted-by":"publisher","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 and Behavior"},{"issue":"3","key":"10.3233\/AIS-210086_ref39","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1615\/JLongTermEffMedImplants.2016017569","article-title":"Electrostimulation for refractory epilepsy: A\u00a0review","volume":"26","author":"Shenoy","year":"2016","journal-title":"Journal of Long-Term Effects of Medical Implants"},{"key":"10.3233\/AIS-210086_ref41","first-page":"23","article-title":"Deep feature learning for EEG recordings","volume":"165","author":"Stober","year":"2015","journal-title":"Computer Science"},{"key":"10.3233\/AIS-210086_ref42","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065719500217"},{"key":"10.3233\/AIS-210086_ref44","unstructured":"P.\u00a0Thodoroff, J.\u00a0Pineau and A.\u00a0Lim, Learning robust features using deep learning for automatic seizure detection, in: Proceedings of the 1st Machine Learning for Healthcare Conference, Vol.\u00a056, 2016, pp.\u00a0178\u2013190."},{"key":"10.3233\/AIS-210086_ref45","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.compbiomed.2018.05.019","article-title":"A\u00a0long short-term memory deep learning network for the prediction of epileptic seizures using EEG signals","volume":"99","author":"Tsiouris","year":"2018","journal-title":"Computers in Biology and Medicine"},{"key":"10.3233\/AIS-210086_ref46","doi-asserted-by":"crossref","unstructured":"L.\u00a0Vidyaratne, A.\u00a0Glandon and M.\u00a0Alam, Deep recurrent neural networks for seizure detection, in: IEEE International Joint Conference on Neural Networks, 2016, pp.\u00a01202\u20131207.","DOI":"10.1109\/IJCNN.2016.7727334"},{"issue":"6","key":"10.3233\/AIS-210086_ref47","first-page":"399","article-title":"Deep convolution neural network and autoencoders-based unsupervised feature learning of EEG signals","volume":"25","author":"Wen","year":"2018","journal-title":"IEEE Access"},{"issue":"4","key":"10.3233\/AIS-210086_ref49","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.yebeh.2012.05.009","article-title":"Epileptic seizure detection with linear and nonlinear features","volume":"24","author":"Yuan","year":"2012","journal-title":"Epilepsy and Behavior"},{"key":"10.3233\/AIS-210086_ref50","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.seizure.2017.05.018","article-title":"Epileptic seizure detection based on imbalanced classification and wavelet packet transform","volume":"50","author":"Yuan","year":"2017","journal-title":"Seizure"},{"key":"10.3233\/AIS-210086_ref51","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065715500033"},{"issue":"3","key":"10.3233\/AIS-210086_ref52","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1109\/TNSRE.2015.2505238","article-title":"Analysis of high-dimensional phase space via Poincare section for patient-specific seizure detection","volume":"24","author":"Zabihi","year":"2016","journal-title":"IEEE Transactions on Neural Systems and Rehabilitation Engineering"},{"key":"10.3233\/AIS-210086_ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3012278"},{"issue":"3","key":"10.3233\/AIS-210086_ref54","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1109\/TBCAS.2015.2477264","article-title":"Low-complexity seizure prediction from iEEG\/sEEG using spectral power and ratios of spectral power","volume":"10","author":"Zhang","year":"2015","journal-title":"IEEE Transactions on Biomedical Circuits and Systems"}],"container-title":["Journal of Ambient Intelligence and Smart Environments"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/AIS-210086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T09:19:12Z","timestamp":1777367952000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/AIS-210086"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,20]]},"references-count":47,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/ais-210086","relation":{},"ISSN":["1876-1372","1876-1364"],"issn-type":[{"value":"1876-1372","type":"electronic"},{"value":"1876-1364","type":"print"}],"subject":[],"published":{"date-parts":[[2022,1,20]]}}}