[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125696-en":3,"doc-seo-125696-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},125696,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",7,"Healthcare","Automatic seizure detection - based on Machine Learning and EEG - Bachelor’s Thesis","Accurate seizure detection underpins diagnosis and treatment of epilepsy, yet clinical assessment of EEG remains a time-consuming visual process requiring trained specialists. This thesis introduces experiments using multiple machine learning architectures, including SVM, KNN, random forest, FFNN, and CNN, on multichannel EEG signals from the CHBT MIT Scalp EEG Database. The best-performing approach combines a feed forward network with a convolutional network, using CNN inputs built via STFT-derived images merged with statistical metrics. Results report 98.615% accuracy, 98.737% sensitivity, and 98.425% specificity, along with discussion of future research directions.","DTU Health Tech  \nDepartment of Health Technology  \nAutomatic seizure detection  \nbased on Machine Learning and EEG Bachelor’s Thesis  \nZhensheng Chen  \nAutomatic seizure detection  \nbased on Machine Learning and EEG  \nBachelor’s Thesis September, 2022  \nBy: Zhensheng Chen  \nSupervisors: Ying Gu and Helge Bjarup Dissing Sørensen  \nCover photo: Generated by Dalle 2 Open IA  \n”For my friend who passed away of epilepsy while I was writing this thesis.  \nI hope that one day humanity will be able to overcome this disease.”  \nAutomatic seizure detection  \nbased on Machine Learning and EEG  \nZhensheng Chen  \nAbstract  \nThe diagnosis and treatment of epilepsy depend on accurate seizure detection. In clinical practice, the evaluation of seizures is done by visual inspection of an electroencephalogram (EEG) . it is very time consuming and requires trained experts. Automatic seizure detection is important. Machine learning approaches are intensely being applied to this problem due to their ability to classify seizure conditions from a large amount of data, and provide pre screened results for neurologists.  \nThis work proposes a variety of experiments with different machine learning architectures (support vector machine SVM, K nearest neighbour KNN, random forest RF, feef forward neural network FFNN and convolutional neural network CNN) for the detection of epileptic seizures using multichannel EEG signals from the CHBT MIT Scalp EEG Database. The best model built in this work contains a combination of a feed forward neural network (FFNN) and a convolutional neural network (CNN) . CNN input images are constructed by applying short time Fourier transform (STFT) to electroencephalography (EEG) signals and then merged with statistical metrics into a FFNN. The best model of this project showed an outstanding performance of 98.615% accuracy, 98.737% sensitivity and 98 .425% specificity. This work also includes a discussion of other exciting ideas that could lead to future research investigations.  \nAutomatic seizure detection iii  \nContents  \n1 Introduction 1  \n1. 1 Related work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1  \n1.2 Project Description ................................ 2  \n2 Background 3  \n2.1 Epilepsy ...................................... 3  \n2.2 Electroencephalography ............................. 3  \n2.3 Short time Fourier transform . . . . . . . . . . . . . . . . . . . . . . . . . . 4  \n2.4 Standarization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4  \n2.5 Neural Network .................................. 5  \n2.5.1 Feed Forward Neural Network ..................... 6  \n2.5.2 Convolutional Neural Network ..................... 7  \n2.6 Performance metrics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7  \n3 Methodology 8  \n3.1 Dataset ...................................... 8  \n3.2 Preprocessing .................................. 9  \n3.2.1 Data inspection .............................. 9  \n3.2.2 Features selection ............................ 9  \n3.2.3 Data cleaning ............................... 10  \n3.3 1 dimensional data model training ....................... 11  \n3.3.1 Feed forward neural network model architecture ........... 11  \n3.3.2 Feed forward neural network model training .............. 12  \n3.3.3 Comparing with other Machine learning models ............ 13  \n3.4 2 dimensional data model training ....................... 13  \n3.4.1 2 dimensional data extraction ...................... 14  \n3.4.2 convolutional model architecture .................... 15  \n3.4.3 convolutional model training ....................... 15  \n4 Results 16  \n4.1 2 dimensional data visulization ......................... 16  \n4.2 Models comparison ............................... 16  \n4.3 Testing with unbalanced data .......................... 17  \n5 Discussion 18  \n6 Conclusion 20  \nBibliography 21  \niv Automatic seizure detection  \n1 Introduction  \nEpilepsy is a serious disorder of t","cbCaifpd7cbBLW0H","https://ap.wps.com/l/cbCaifpd7cbBLW0H","pdf",7660940,1,51,"English","en",105,"# Introduction\n## Related work\n## Project Description\n# Background\n## Epilepsy\n## Electroencephalography\n## Short time Fourier transform\n## Standarization\n## Neural Network\n## Performance metrics\n# Methodology\n## Dataset\n## Preprocessing\n### Data inspection\n### Features selection\n### Data cleaning\n## 1 dimensional data model training\n## 2 dimensional data model training\n# Results\n## 2 dimensional data visualization\n## Models comparison\n## Testing with unbalanced data\n# Discussion\n# Conclusion\n# Bibliography","[{\"question\":\"Why is automatic seizure detection important for epilepsy care?\",\"answer\":\"Manual EEG inspection is slow and depends on expert judgment, which can lead to inaccuracies. Automated detection supports more reliable identification of seizure events for clinical use.\"},{\"question\":\"Which machine learning models were evaluated in this thesis?\",\"answer\":\"The thesis tests SVM, KNN, random forest, FFNN, and CNN architectures for detecting epileptic seizures from multichannel EEG signals.\"},{\"question\":\"What is the best model configuration and its reported performance?\",\"answer\":\"The top model combines an FFNN with a CNN, where CNN inputs are created from STFT-based EEG representations and merged with statistical metrics. It achieves 98.615% accuracy, 98.737% sensitivity, and 98.425% specificity.\"}]","Automatic seizure detection - based on Machine Learning and EEG - Bachelor’s Thesis | PDF",1785900700,129,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"automatic-seizure-detection-based-on-machine-learning-and-eeg-bachelors-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/automatic-seizure-detection-based-on-machine-learning-and-eeg-bachelors-thesis/125696/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is automatic seizure detection important for epilepsy care?","Question",{"text":75,"@type":76},"Manual EEG inspection is slow and depends on expert judgment, which can lead to inaccuracies. Automated detection supports more reliable identification of seizure events for clinical use.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models were evaluated in this thesis?",{"text":80,"@type":76},"The thesis tests SVM, KNN, random forest, FFNN, and CNN architectures for detecting epileptic seizures from multichannel EEG signals.",{"name":82,"@type":73,"acceptedAnswer":83},"What is the best model configuration and its reported performance?",{"text":84,"@type":76},"The top model combines an FFNN with a CNN, where CNN inputs are created from STFT-based EEG representations and merged with statistical metrics. It achieves 98.615% accuracy, 98.737% sensitivity, and 98.425% specificity.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,118,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":116,"slug":117},40,"healthcare",{"id":119,"doc_module":4,"doc_module_name":46,"category_name":120,"show_sort_weight":121,"slug":122},8,"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]