{"id":2839,"date":"2020-11-15T17:46:10","date_gmt":"2020-11-15T22:46:10","guid":{"rendered":"https:\/\/engineering.jhu.edu\/nsa\/?p=2839"},"modified":"2021-02-07T17:48:02","modified_gmt":"2021-02-07T22:48:02","slug":"our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control","status":"publish","type":"post","link":"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/","title":{"rendered":"Our paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control"},"content":{"rendered":"

Title:<\/strong> Automated Inter-Patient Seizure Detection Using Multichannel Convolutional and Recurrent Neural Networks<\/p>\n

Abstract:<\/strong> We present an end-to-end deep learning model that can automatically detect epileptic seizures in multichannel electroencephalography (EEG) recordings. Our model combines a Convolutional Neural Network (CNN) and a Bidirectional Long Short-Term Memory (BLSTM) network to e\u000eciently mine information from the EEG data using a small number of trainable parameters. Specifically, the CNN learns a latent encoding for each one second window of raw multichannel EEG data. In conjunction, the BLSTM learns the temporal evolution of seizure presentations given the CNN encodings. The combination of these architectures allows our model to capture both the short time scale EEG features indicative of seizure activity as well as the long term correlations in seizure presentations. Unlike most prior work in seizure detection, we mimic an in-patient monitoring setting through a leave-one-patient-out cross validation procedure, attaining an average seizure detection sensitivity of 0.91 across all patients. This strategy verifies that our model can generalize to new patients. We demonstrate that our CNN-BLSTM outperforms both conventional feature extraction methods and state-of-the-art deep learning approaches that rely on larger and more complex network architectures.<\/p>\n","protected":false},"excerpt":{"rendered":"

Title: Automated Inter-Patient Seizure Detection Using Multichannel Convolutional and Recurrent Neural Networks Abstract: We present an end-to-end deep learning model that can automatically detect epileptic seizures in multichannel electroencephalography (EEG) recordings. Our model combines a Convolutional Neural Network (CNN) and … Continue reading →<\/span><\/a><\/p>\n","protected":false},"author":1476,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_exactmetrics_skip_tracking":false,"_exactmetrics_sitenote_active":false,"_exactmetrics_sitenote_note":"","_exactmetrics_sitenote_category":0,"footnotes":""},"categories":[1],"tags":[],"coauthors":[],"class_list":["post-2839","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"yoast_head":"\nOur paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control - Neural Systems Analysis Laboratory<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Our paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control - Neural Systems Analysis Laboratory\" \/>\n<meta property=\"og:description\" content=\"Title: Automated Inter-Patient Seizure Detection Using Multichannel Convolutional and Recurrent Neural Networks Abstract: We present an end-to-end deep learning model that can automatically detect epileptic seizures in multichannel electroencephalography (EEG) recordings. Our model combines a Convolutional Neural Network (CNN) and … Continue reading →\" \/>\n<meta property=\"og:url\" content=\"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/\" \/>\n<meta property=\"og:site_name\" content=\"Neural Systems Analysis Laboratory\" \/>\n<meta property=\"article:published_time\" content=\"2020-11-15T22:46:10+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2021-02-07T22:48:02+00:00\" \/>\n<meta name=\"author\" content=\"Archana Venkataraman\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Archana Venkataraman\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/2020\\\/11\\\/15\\\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\\\/#article\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/2020\\\/11\\\/15\\\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\\\/\"},\"author\":{\"name\":\"Archana Venkataraman\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/#\\\/schema\\\/person\\\/5621056827aad54caccd12d5fe6f6cf2\"},\"headline\":\"Our paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control\",\"datePublished\":\"2020-11-15T22:46:10+00:00\",\"dateModified\":\"2021-02-07T22:48:02+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/2020\\\/11\\\/15\\\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\\\/\"},\"wordCount\":207,\"inLanguage\":\"en-US\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/2020\\\/11\\\/15\\\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\\\/\",\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/2020\\\/11\\\/15\\\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\\\/\",\"name\":\"Our paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control - Neural Systems Analysis Laboratory\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/#website\"},\"datePublished\":\"2020-11-15T22:46:10+00:00\",\"dateModified\":\"2021-02-07T22:48:02+00:00\",\"author\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/#\\\/schema\\\/person\\\/5621056827aad54caccd12d5fe6f6cf2\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/2020\\\/11\\\/15\\\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/2020\\\/11\\\/15\\\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/2020\\\/11\\\/15\\\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Our paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/#website\",\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/\",\"name\":\"Neural Systems Analysis Laboratory\",\"description\":\"Decoding the Brain, One Snapshot at a Time\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/#\\\/schema\\\/person\\\/5621056827aad54caccd12d5fe6f6cf2\",\"name\":\"Archana Venkataraman\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/3a0c67f7e8031b0ba2dbfd2fe8ebbc66eb50283a85de44ad81b106aa3efef3f8?s=96&d=mm&r=ga7b67543af0f1e73c44a2e0c776f67e8\",\"url\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/3a0c67f7e8031b0ba2dbfd2fe8ebbc66eb50283a85de44ad81b106aa3efef3f8?s=96&d=mm&r=g\",\"contentUrl\":\"https:\\\/\\\/secure.gravatar.com\\\/avatar\\\/3a0c67f7e8031b0ba2dbfd2fe8ebbc66eb50283a85de44ad81b106aa3efef3f8?s=96&d=mm&r=g\",\"caption\":\"Archana Venkataraman\"},\"url\":\"https:\\\/\\\/engineering.jhu.edu\\\/nsa\\\/author\\\/avenka14\\\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Our paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control - Neural Systems Analysis Laboratory","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/","og_locale":"en_US","og_type":"article","og_title":"Our paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control - Neural Systems Analysis Laboratory","og_description":"Title: Automated Inter-Patient Seizure Detection Using Multichannel Convolutional and Recurrent Neural Networks Abstract: We present an end-to-end deep learning model that can automatically detect epileptic seizures in multichannel electroencephalography (EEG) recordings. Our model combines a Convolutional Neural Network (CNN) and … Continue reading →","og_url":"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/","og_site_name":"Neural Systems Analysis Laboratory","article_published_time":"2020-11-15T22:46:10+00:00","article_modified_time":"2021-02-07T22:48:02+00:00","author":"Archana Venkataraman","twitter_misc":{"Written by":"Archana Venkataraman","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/#article","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/"},"author":{"name":"Archana Venkataraman","@id":"https:\/\/engineering.jhu.edu\/nsa\/#\/schema\/person\/5621056827aad54caccd12d5fe6f6cf2"},"headline":"Our paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control","datePublished":"2020-11-15T22:46:10+00:00","dateModified":"2021-02-07T22:48:02+00:00","mainEntityOfPage":{"@id":"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/"},"wordCount":207,"inLanguage":"en-US"},{"@type":"WebPage","@id":"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/","url":"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/","name":"Our paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control - Neural Systems Analysis Laboratory","isPartOf":{"@id":"https:\/\/engineering.jhu.edu\/nsa\/#website"},"datePublished":"2020-11-15T22:46:10+00:00","dateModified":"2021-02-07T22:48:02+00:00","author":{"@id":"https:\/\/engineering.jhu.edu\/nsa\/#\/schema\/person\/5621056827aad54caccd12d5fe6f6cf2"},"breadcrumb":{"@id":"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/engineering.jhu.edu\/nsa\/2020\/11\/15\/our-paper-on-deep-learning-for-seizure-detection-is-accepted-to-biomedical-signal-processing-and-control\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/engineering.jhu.edu\/nsa\/"},{"@type":"ListItem","position":2,"name":"Our paper on Deep Learning for Seizure Detection is Accepted to Biomedical Signal Processing and Control"}]},{"@type":"WebSite","@id":"https:\/\/engineering.jhu.edu\/nsa\/#website","url":"https:\/\/engineering.jhu.edu\/nsa\/","name":"Neural Systems Analysis Laboratory","description":"Decoding the Brain, One Snapshot at a Time","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/engineering.jhu.edu\/nsa\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/engineering.jhu.edu\/nsa\/#\/schema\/person\/5621056827aad54caccd12d5fe6f6cf2","name":"Archana Venkataraman","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/3a0c67f7e8031b0ba2dbfd2fe8ebbc66eb50283a85de44ad81b106aa3efef3f8?s=96&d=mm&r=ga7b67543af0f1e73c44a2e0c776f67e8","url":"https:\/\/secure.gravatar.com\/avatar\/3a0c67f7e8031b0ba2dbfd2fe8ebbc66eb50283a85de44ad81b106aa3efef3f8?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/3a0c67f7e8031b0ba2dbfd2fe8ebbc66eb50283a85de44ad81b106aa3efef3f8?s=96&d=mm&r=g","caption":"Archana Venkataraman"},"url":"https:\/\/engineering.jhu.edu\/nsa\/author\/avenka14\/"}]}},"_links":{"self":[{"href":"https:\/\/engineering.jhu.edu\/nsa\/wp-json\/wp\/v2\/posts\/2839","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/engineering.jhu.edu\/nsa\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/engineering.jhu.edu\/nsa\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/engineering.jhu.edu\/nsa\/wp-json\/wp\/v2\/users\/1476"}],"replies":[{"embeddable":true,"href":"https:\/\/engineering.jhu.edu\/nsa\/wp-json\/wp\/v2\/comments?post=2839"}],"version-history":[{"count":1,"href":"https:\/\/engineering.jhu.edu\/nsa\/wp-json\/wp\/v2\/posts\/2839\/revisions"}],"predecessor-version":[{"id":2840,"href":"https:\/\/engineering.jhu.edu\/nsa\/wp-json\/wp\/v2\/posts\/2839\/revisions\/2840"}],"wp:attachment":[{"href":"https:\/\/engineering.jhu.edu\/nsa\/wp-json\/wp\/v2\/media?parent=2839"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/engineering.jhu.edu\/nsa\/wp-json\/wp\/v2\/categories?post=2839"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/engineering.jhu.edu\/nsa\/wp-json\/wp\/v2\/tags?post=2839"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/engineering.jhu.edu\/nsa\/wp-json\/wp\/v2\/coauthors?post=2839"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}