{"id":790,"date":"2017-02-06T18:26:32","date_gmt":"2017-02-06T18:26:32","guid":{"rendered":"http:\/\/technicalelvis.com\/blog\/?p=790"},"modified":"2017-02-07T14:10:54","modified_gmt":"2017-02-07T14:10:54","slug":"kaggle-seizure-prediction-competition","status":"publish","type":"post","link":"https:\/\/technicalelvis.com\/blog\/2017\/02\/06\/kaggle-seizure-prediction-competition\/","title":{"rendered":"Kaggle Seizure Prediction Competition"},"content":{"rendered":"<h1>Kaggle Competition Goal<\/h1>\n<p>Detect seizure (<code>preictal<\/code>) or non-seizure (<code>interical<\/code>) segments of intracranial electroencephalography (iEEG) data. <a href=\"https:\/\/www.kaggle.com\/c\/melbourne-university-seizure-prediction\">See Kaggle EEG Competition page for more details<\/a>.<\/p>\n<p>My Approach:<\/p>\n<ul>\n<li>Extract basic stats and FFT features for non-overlapping 30-second iEEG windows<\/li>\n<li>Detect signal drop out and impute missing data with mean for each feature per window<\/li>\n<li>Predict seizure and non-seizure segments using a stacked model.<\/li>\n<\/ul>\n<h1>Model Details<\/h1>\n<p>For more details about the model, \u00a0<a href=\"https:\/\/github.com\/telvis07\/kaggle-melbourne-university-seizure-prediction\">see my github repo with the documentation and R code<\/a>.<\/p>\n<h1>Final Thoughts<\/h1>\n<ul>\n<li>This is my first Kaggle competition. I acheived my goal of making a competition submission. <a href=\"https:\/\/www.kaggle.com\/telvis\">See my profile<\/a>.<\/li>\n<li>I submitted after the deadline but my submission would have ranked 391 of 2440 submissions. <a href=\"https:\/\/github.com\/telvis07\/kaggle-melbourne-university-seizure-prediction\/blob\/master\/images\/kaggle_eeg_submission_capture.png\">Screenshot<\/a><\/li>\n<li>The <a href=\"http:\/\/blog.kaggle.com\/2016\/12\/27\/a-kagglers-guide-to-model-stacking-in-practice\/\">Kaggle model stacking tutorial<\/a> helped me understand cross-fold validation with stacked models.<\/li>\n<li><a href=\"https:\/\/www.kaggle.com\/deepcnn\/melbourne-university-seizure-prediction\/feature-extractor-matlab2python-translated\">Deep's Kernel<\/a> and <a href=\"https:\/\/www.kaggle.com\/treina\/melbourne-university-seizure-prediction\/feature-extractor-matlab2python-translated\">Tony Reina's Kernel<\/a> helped me understand EEG features.<\/li>\n<li>Special thanks to <a href=\"http:\/\/hassanakingravi.com\/\">Hassan Kingravi<\/a> for suggesting the stacked model.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Kaggle Competition Goal Detect seizure (preictal) or non-seizure (interical) segments of intracranial electroencephalography (iEEG) data. See Kaggle EEG Competition page for more details. My Approach: Extract basic stats and FFT features for non-overlapping 30-second iEEG windows Detect signal drop out and impute missing data with mean for each feature per window Predict seizure and non-seizure &hellip; <a href=\"https:\/\/technicalelvis.com\/blog\/2017\/02\/06\/kaggle-seizure-prediction-competition\/\" class=\"more-link\">Continue reading <span class=\"screen-reader-text\">Kaggle Seizure Prediction Competition<\/span> <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[19],"tags":[],"class_list":["post-790","post","type-post","status-publish","format-standard","hentry","category-data-science"],"_links":{"self":[{"href":"https:\/\/technicalelvis.com\/blog\/wp-json\/wp\/v2\/posts\/790","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/technicalelvis.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/technicalelvis.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/technicalelvis.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/technicalelvis.com\/blog\/wp-json\/wp\/v2\/comments?post=790"}],"version-history":[{"count":3,"href":"https:\/\/technicalelvis.com\/blog\/wp-json\/wp\/v2\/posts\/790\/revisions"}],"predecessor-version":[{"id":793,"href":"https:\/\/technicalelvis.com\/blog\/wp-json\/wp\/v2\/posts\/790\/revisions\/793"}],"wp:attachment":[{"href":"https:\/\/technicalelvis.com\/blog\/wp-json\/wp\/v2\/media?parent=790"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/technicalelvis.com\/blog\/wp-json\/wp\/v2\/categories?post=790"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/technicalelvis.com\/blog\/wp-json\/wp\/v2\/tags?post=790"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}