{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/human-intracranial-eeg-quantitative-analysis","title":"Human Intracranial EEG Quantitative Analysis and Automatic Feature Learning for Epileptic Seizure Prediction","arxiv_id":"1904.03603","date":"2019-04-07","proceeding":null,"authors":["Ramy Hussein","Mohamed Osama Ahmed","Rabab Ward","Z. Jane Wang","Levin Kuhlmann","Yi Guo"],"abstract":"Objective: The aim of this study is to develop an efficient and reliable\nepileptic seizure prediction system using intracranial EEG (iEEG) data,\nespecially for people with drug-resistant epilepsy. The prediction procedure\nshould yield accurate results in a fast enough fashion to alert patients of\nimpending seizures. Methods: We quantitatively analyze the human iEEG data to\nobtain insights into how the human brain behaves before and between epileptic\nseizures. We then introduce an efficient pre-processing method for reducing the\ndata size and converting the time-series iEEG data into an image-like format\nthat can be used as inputs to convolutional neural networks (CNNs). Further, we\npropose a seizure prediction algorithm that uses cooperative multi-scale CNNs\nfor automatic feature learning of iEEG data. Results: 1) iEEG channels contain\ncomplementary information and excluding individual channels is not advisable to\nretain the spatial information needed for accurate prediction of epileptic\nseizures. 2) The traditional PCA is not a reliable method for iEEG data\nreduction in seizure prediction. 3) Hand-crafted iEEG features may not be\nsuitable for reliable seizure prediction performance as the iEEG data varies\nbetween patients and over time for the same patient. 4) Seizure prediction\nresults show that our algorithm outperforms existing methods by achieving an\naverage sensitivity of 87.85% and AUC score of 0.84. Conclusion: Understanding\nhow the human brain behaves before seizure attacks and far from them\nfacilitates better designs of epileptic seizure predictors. Significance:\nAccurate seizure prediction algorithms can warn patients about the next seizure\nattack so they could avoid dangerous activities. Medications could then be\nadministered to abort the impending seizure and minimize the risk of injury.","url_abs":"http://arxiv.org/abs/1904.03603v1","url_pdf":"http://arxiv.org/pdf/1904.03603v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"eeg-1","task_name":"EEG"},{"task_slug":"eeg","task_name":"Electroencephalogram (EEG)"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"seizure-prediction","task_name":"Seizure prediction"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/seizure-prediction-on-melbourne-university","task":"Seizure prediction","dataset":"Melbourne University Seizure Prediction","model":"CNN+FCN","rank_in_archive_order":1,"of":2,"metrics":{"AUC":"0.84"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}