[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120013-en":3,"doc-seo-120013-105":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},120013,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Severity classification of Finnish motorcycle accidents with machine learning methods - Master’s thesis","Traffic accident fatalities among vulnerable road users, including motorcyclists, create an urgent need for effective, evidence-based interventions. This master’s thesis studies factors influencing motorcycle accident severity and compares machine learning models for severity classification. A Finnish dataset covering 2005–2021 is used to train K-nearest neighbor, support vector machine, and random forest models. Variable importance is estimated with ReliefF and random-forest out-of-bag permutation to identify influential factors driving severe outcomes.","Tuuli Tuominen  \nSEVERITY CLASSIFICATION OF FINNISH MOTORCYCLE ACCIDENTS WITH MACHINE LEARNING METHODS  \nFaculty of Information Technology and Communication Sciences Master’s thesis May 2024  \nABSTRACT  \nTuuli Tuominen: Severity classification of Finnish motorcycle accidents with machine learning methods  \nMaster’s thesis Tampere University  \nMaster’s Degree Programme in Computer Science April 2024  \nTraffic accident fatalities among vulnerable road users, such as motorcyclists, are a global burden requiring effective and evidence-based interventions. Currently the use of machine learning is becoming more common in traffic accident modeling, offering new insights into the causes and risk factors of severe accidents.  \nThe purpose of this thesis was to analyze important factors affecting the severity of motorcycle accidents and to compare the performance of machine learning models in the task of motorcycle accident severity classification. A Finnish motorcycle accident dataset covering years 2005–2021 was acquired from Finnish Transport Infrastructure Agency , and K-nearest neighbor classifier, support vector machine and random forest were trained on the dataset. Additionally, the variable importance values were estimated using ReliefF algorithm and out-of-bag permutation of the random forest.  \nOf the three models, random forest achieved the highest performance in all six performance measures computed. However, the model’s performance was observed to be significantly lower compared to previous research, potentially caused by the lack of important features in the dataset. Variable importance estimates of both methods indicated the type of the accident to be important , as well as the geographical location and whether the accident occurred on dual-carriageway road. Potentially interesting variables that were identified important by one of the two methods included weather, day of the week, motorcycle age and motorcycle weight.  \nKeywords: machine learning, k-nearest neighbor, support vector machine, random forest, road traffic accident, motorcycle accident, severity classification  \nThe originality of this thesis has been checked using the Turnitin OriginalityCheck service.  \n1 Introduction ............................................................................................................. 1  \n2 Severity classification of motorcycle accidents ..................................................... 3  \n2.1 Motorcycle accidents and their risk factors as a research subject 3  \n2.2 Risk factors of the machine element 5  \n2.3 Risk factors of the environmental element 8  \n2.4 Risk factors of the human element 11  \n2.5 Machine learning classifiers in road traffic accident modeling 15  \n3 Data preprocessing methods................................................................................. 17  \n3.1 Data encoding and normalization 18  \n3.2 Missing values and imputation 20  \n3.3 Feature selection 23  \n3.4 Preprocessing imbalanced datasets 25  \n4 Machine learning classifiers ................................................................................. 29  \n4.1 K-nearest neighbor classifier 29  \n4.2 Support vector machines 32  \n4.3 Random forests and AdaBoost 35  \n5 Hyperparameter optimization.............................................................................. 40  \n6 Performance evaluation measures ....................................................................... 44  \n7 Dataset and experimental setup ........................................................................... 49  \n8 Results..................................................................................................................... 57  \n9 Conclusion .............................................................................................................. 65  \nReferences...................................................................................................................... 67  \n1 Introduction  \nWHO (2018) estimates the r","cbCaifpmXcRHeyqA","https://ap.wps.com/l/cbCaifpmXcRHeyqA","pdf",2202358,1,75,"English","en",105,"# Introduction\n## Motorcycle accidents and their risk factors as a research subject\n## Risk factors of the machine element\n## Risk factors of the environmental element\n## Risk factors of the human element\n## Machine learning classifiers in road traffic accident modeling\n# Data preprocessing methods\n## Data encoding and normalization\n## Missing values and imputation\n## Feature selection\n## Preprocessing imbalanced datasets\n# Machine learning classifiers\n## K-nearest neighbor classifier\n## Support vector machines\n## Random forests and AdaBoost\n# Hyperparameter optimization\n# Performance evaluation measures\n# Dataset and experimental setup\n# Results\n# Conclusion","[{\"question\":\"What is the main objective of this thesis?\",\"answer\":\"The thesis analyzes key factors affecting motorcycle accident severity and compares multiple machine learning models on the severity classification task.\"},{\"question\":\"Which data and time span were used in the study?\",\"answer\":\"A Finnish motorcycle accident dataset covering years 2005–2021 was acquired from the Finnish Transport Infrastructure Agency.\"},{\"question\":\"Which model achieved the best results and what may explain the performance gap?\",\"answer\":\"Random forest achieved the highest performance across six evaluation measures, while its performance was lower than in previous research, potentially due to missing important features in the dataset.\"}]","Severity classification of Finnish motorcycle accidents with machine learning methods - Master’s thesis | PDF",1785727736,189,{"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},"severity-classification-of-finnish-motorcycle-accidents-with-machine-learning-methods-masters-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/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/severity-classification-of-finnish-motorcycle-accidents-with-machine-learning-methods-masters-thesis/120013/",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","2026-08-03",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 is the main objective of this thesis?","Question",{"text":75,"@type":76},"The thesis analyzes key factors affecting motorcycle accident severity and compares multiple machine learning models on the severity classification task.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which data and time span were used in the study?",{"text":80,"@type":76},"A Finnish motorcycle accident dataset covering years 2005–2021 was acquired from the Finnish Transport Infrastructure Agency.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model achieved the best results and what may explain the performance gap?",{"text":84,"@type":76},"Random forest achieved the highest performance across six evaluation measures, while its performance was lower than in previous research, potentially due to missing important features in the dataset.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},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"]