[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124240-en":3,"doc-seo-124240-105":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":20,"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},124240,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","ENSEMBLE-BASED MACHINE LEARNING MODELS FOR VEHICLE DRIVERS’ FATIGUE STATE DETECTION UTILIZING EEG SIGNALS","Driver fatigue is increasingly recognized as a major contributor to traffic tragedies, motivating research into fast and reliable fatigue recognition. This study detects fatigue states using ensemble-based machine learning models built on electroencephalogram (EEG) signals. Two ensemble methods—Ensemble-based RUSBoosted Decision Trees and Ensemble-based Random Subspace Discriminant—were trained and compared using an online EEG dataset from 12 individuals under normal and fatigued driving. Fast Fourier Transform was used for feature extraction, and multiple metrics evaluated performance. The RUSBoosted model achieved 98.53% accuracy versus 83.13% for the Random Subspace Discriminant model, outperforming conventional approaches. Results support real-time fatigue detection to improve road safety.","[https://doi.org/10.2298/FUEE2404671H](https://doi.org/10.2298/FUEE2404671H)  \nOriginal scientific paper  \nENSEMBLE-BASED MACHINE LEARNING MODELS FOR VEHICLE DRIVERS’ FATIGUE STATE DETECTION UTILIZING  \nEEG SIGNALS  \nMd Mahmudul Hasan1, Md Nahidul Islam1, Sayma Khandaker1, Norizam Sulaiman1, Ashraful Islam2, Mirza Mahfuj Hossain3  \n1Faculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang Al-Sultan Abdullah, Pahang 26600, Malaysia 2Department of Electrical and Electronic Engineering, Jashore University of Science and Technology, Jashore 7408, Bangladesh 3Department of Computer Science and Engineering, Jashore University of Science and Technology, Jashore 7408, Bangladesh  \nORCID iDs: Md Mahmudul Hasan  [https://orcid.org/0009-0004-6865-3785](https://orcid.org/0009-0004-6865-3785)  \nMd Nahidul Islam  [https://orcid.org/0000-0003-1552-0335](https://orcid.org/0000-0003-1552-0335)[ ](https://orcid.org/0000-0003-1552-0335)Sayma Khandaker  [https://orcid.org/0009-0007-7621-3554](https://orcid.org/0009-0007-7621-3554)  \nNorizam Sulaiman  [https://orcid.org/0000-0002-0625-2327](https://orcid.org/0000-0002-0625-2327)  \nAshraful Islam  [https://orcid.org/0009-0006-1157-5055](https://orcid.org/0009-0006-1157-5055)  \n Mirza Mahfuj Hossain  [https://orcid.org/0009-0009-7391-5635](https://orcid.org/0009-0009-7391-5635)   \n[Abstract](Abstract. Currently)[.](Abstract. Currently)[ Currently](Abstract. Currently), there is a great extent of academic research focused on evaluating fatigue among drivers due to its growing recognition as a major contributor to vehicle tragedies. Combining advanced features and machine learning techniques, signals from the electroencephalogram (EEG) can be analyzed to efficiently detect fatigue in the shortest possible time. This study presents an innovative approach to detect driver fatigue states utilizing ensemble-based machine learning techniques from EEG signals.  \nTwo ensemble models (Ensemble-based RUSBoosted Decision Trees and Ensemblebased Random Subspace Discriminant) were applied and compared. The study utilized an online EEG dataset of 12 individuals, with data collected during normal and fatigued driving conditions and Fast Fourier Transform was applied for feature extraction. The Ensemble-based RUSBoosted Decision Trees model achieved superior performance with 98.53% classification accuracy, compared to 83.13% for the Random Subspace Discriminant model. Multiple performance metrics were used for evaluation model performance. Finally, the proposed Ensemble-based RUSBoosted Decision Trees model outperformed Ensemble-based Random Subspace Discriminant model and existing conventional methods for fatigue state detection. This research contributes to the development of more accurate and reliable fatigue detection systems, which could potentially improve road safety by identifying fatigued drivers in real-time.  \nReceived March 26, 2024; revised July 05, 2024; accepted July 18, 2024  \nCorresponding author: Norizam Sulaiman  \nFaculty of Electrical and Electronics Engineering Technology, Universiti Malaysia Pahang Al-Sultan Abdullah, Pahang 26600, Malaysia  \n[E-mail: norizam@umpsa.edu.my](E-mail: norizam@umpsa.edu.my)  \nKey words: Fatigue state detection, EEG signal, Ensemble based classifier,  \nRUSBoosted Decision Tree, Random Subspace Discriminant  \n1. INTRODUCTION  \nThe excessive frequency of highways catastrophes has led to socioeconomic problems that endanger both human beings and their belongings. The WHO mentions that road accidents cause more than 1,300,000 deaths worldwide each year, and millions additional individuals are injured or left permanently disabled [1] . Furthermore, there has been a noticeable rise in the frequency of vehicle crashes lately, which has prompted communities and governments to give this problem a lot of emphasis [2] . Road accidents are so prevalent that it is critical to focus resources on international projects that try mitigating them. Studi","cbCainxAvKv8rVrk","https://ap.wps.com/l/cbCainxAvKv8rVrk","pdf",731660,1,16,"English","en",105,"# Introduction\n## Fatigue recognition approaches\n## Physiological (physical) strategies\n## Behavioral strategies\n## Vehicle strategies\n# Methods\n## EEG data and experimental setup\n## Feature extraction with Fast Fourier Transform\n## Ensemble models and comparison\n# Results and evaluation\n## Classification performance and metrics\n# Conclusion\n## Practical implications for road safety","[{\"question\":\"What signals and data are used to detect driver fatigue in this study?\",\"answer\":\"The approach uses electroencephalogram (EEG) signals collected while 12 individuals drive under normal and fatigued conditions. An online EEG dataset is used for training and evaluation.\"},{\"question\":\"Which ensemble learning models were compared, and how did they perform?\",\"answer\":\"The study compares Ensemble-based RUSBoosted Decision Trees with Ensemble-based Random Subspace Discriminant. RUSBoosted Decision Trees achieved 98.53% classification accuracy, outperforming 83.13% for the Random Subspace Discriminant model.\"},{\"question\":\"How are EEG features extracted before model training?\",\"answer\":\"Fast Fourier Transform (FFT) is applied to the EEG signals for feature extraction before feeding them into the ensemble classifiers.\"}]","ENSEMBLE-BASED MACHINE LEARNING MODELS FOR VEHICLE DRIVERS’ FATIGUE STATE DETECTION UTILIZING EEG SIGNALS | PDF",1785821185,40,{"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},"ensemble-based-machine-learning-models-for-vehicle-drivers-fatigue-state-detection-utilizing-eeg-signals","",{"@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/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/ensemble-based-machine-learning-models-for-vehicle-drivers-fatigue-state-detection-utilizing-eeg-signals/124240/",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","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What signals and data are used to detect driver fatigue in this study?","Question",{"text":75,"@type":76},"The approach uses electroencephalogram (EEG) signals collected while 12 individuals drive under normal and fatigued conditions. An online EEG dataset is used for training and evaluation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which ensemble learning models were compared, and how did they perform?",{"text":80,"@type":76},"The study compares Ensemble-based RUSBoosted Decision Trees with Ensemble-based Random Subspace Discriminant. RUSBoosted Decision Trees achieved 98.53% classification accuracy, outperforming 83.13% for the Random Subspace Discriminant model.",{"name":82,"@type":73,"acceptedAnswer":83},"How are EEG features extracted before model training?",{"text":84,"@type":76},"Fast Fourier Transform (FFT) is applied to the EEG signals for feature extraction before feeding them into the ensemble classifiers.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":29,"slug":118},7,"Healthcare","healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]