[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126226-en":3,"doc-seo-126226-105":31,"detail-sidebar-cat-0-en-105":93},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126226,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",8,"Research & Report","Evaluating Incremental Machine Learning Models for Road Condition Classification","This degree project evaluates seven incremental machine learning models for predicting Road Surface Conditions (RSC) using a dataset provided by Klimator AB. Accurate RSC identification is critical for autonomous vehicles and traffic safety. Models are trained on vehicle-ride-derived data split into epochs, and performance is compared against a Random Forest baseline and a single Dummy Classifier baseline. Ensemble methods using Logistic Regression and Decision Tree Classifier achieve the highest overall average accuracy, while Hoeffding Tree Classifier excels under rapid concept drift events. Results indicate room for improvement through further optimization of top candidates.","Evaluating Incremental Machine Learning Models for Road Condition Classification  \nDegree Project Report in Computer Science and Engineering-LMTX38  \nDavid Svantesson & Julia Hansen  \nDEPARTMENT OF Computer Science and Engineering  \nCHALMERS UNIVERSITY OF TECHNOLOGY | UNIVERSITY OF GOTHENBURG Gothenburg, Sweden 2024  \n[www.chalmers.se | www.gu.se](www.chalmers.se | www.gu.se)  \nDegree project report in Computer science and engineering  \n-LMTX38 2024  \nEvaluating Incremental Machine Learning Models for Road Condition Classification  \nDavid Svantesson  \nJulia Hansen  \nDepartment of Computer Science and Engineering Chalmers University of Technology University of Gothenburg Gothenburg, Sweden 2024  \nDegree Project Report in Computer Science and Engineering-LMTX38  \nEvaluating Incremental Machine Learning Models for Road Condition Classification David Svantesson & Julia Hansen  \n© David Svantesson & Julia Hansen, 2024 .  \nSupervisor: Adam Breitholtz, Chalmers Data Science och AI  \nSupervisor: Pontus Andersson, Klimator AB  \nExaminer: Jonas, Almström Duregård  \nDegree project report 2024  \nDepartment of Computer Science and Engineering  \nChalmers University of Technology | University of Gothenburg SE-412 96 Gothenburg  \nSweden  \nTelephone +46 31 772 1000  \nCover: Road surface classification visualization showing a road surface with a graphic overlay illustrating the prediction made by an ML model. Predictions are visualized as colours corresponding to specific road surface conditions.  \nTypeset in LATEX  \nGothenburg, Sweden 2024  \nEvaluating Incremental Machine Learning Models for Road Condition Classification David Svantesson & Julia Hansen  \nDepartment of Computer Science and Engineering  \nChalmers University of Technology | University of Gothenburg  \nAbstract  \nThis project was provided by Klimator AB with the aim of evaluating different incremental Machine Learning (ML) models predicting Road Surface Conditions (RSC), using a given data set from Klimator AB. Successfully identifying the RSC is associated with an autonomous vehicle’s traffic safety and therefore an important area of investigation. This project presents the evaluation of seven models, with three of the models, Gaussian Naive Bayes, Complement Naive Bayes and Hoeffding Tree Classifier, being of an incremental nature in their implementation, and the remaining, Decision Tree Classifier, K-Nearest Neighbors, Logistic Regression and Dummy Classifier, employed as ensembles in an incremental manner. The models were evaluated against a Random Forest model serving as a top-level baseline, and a single Dummy Classifier serving as a low-level baseline. All models were trained using datasets derived from vehicle rides under varying RSCs, which were split into smaller intervals called epochs. The findings of this study are that the ensembles of Logistic Regression and Decision Tree Classifier demonstrate the greatest overall strengths, achieving the highest average accuracy. Additionally, the Hoeffding Tree Classifier performs strongest during rapid changes of RSC, so-called concept driftevents. However, the performances of all models fall short of optimal in terms of making accurate predictions. To optimize the top three candidates further, this project identifies opportunities for further development and enhancements, potentially leading to an ML model suited to assist in autonomous vehicles and ensuring traffic safety.  \nKeywords: Machine Learning, Incremental Learning, Road Surface Conditions, Ensemble Method, Concept Drift, Traffic Safety, Model Evaluation, Autonomous Vehicles.  \nAcknowledgements  \nThis project was provided by the company Klimator AB with the purpose of evaluating different machine learning models and identifying their strengths and weaknesses when presented with RSC data. Klimator is a Gotheburg-based company that makes road weather intelligence available through predictive and detective data, aiming to empower safe, sustainable and autonomous driving [1","cbCaitG6M2uAA7g8","https://ap.wps.com/l/cbCaitG6M2uAA7g8","pdf",9582265,5,1,121,"English","en",105,"# Abstract\n## Keywords\n# Acknowledgements\n## List of Acronyms","[{\"question\":\"What is the goal of the project?\",\"answer\":\"The project aims to evaluate different incremental machine learning models for predicting Road Surface Conditions using a dataset provided by Klimator AB.\"},{\"question\":\"How were the models trained and evaluated?\",\"answer\":\"Models were trained on datasets derived from vehicle rides with varying RSCs, split into smaller intervals called epochs, and evaluated against Random Forest and a single Dummy Classifier baselines.\"},{\"question\":\"Which models performed best overall and under concept drift?\",\"answer\":\"Ensembles of Logistic Regression and Decision Tree Classifier showed the greatest overall strengths with the highest average accuracy, while the Hoeffding Tree Classifier performed best during rapid RSC changes, i.e., concept drift events.\"}]","Evaluating Incremental Machine Learning Models for Road Condition Classification | PDF",1785903925,305,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":88,"head_meta":90,"extra_data":92,"updated_unix":29},"evaluating-incremental-machine-learning-models-for-road-condition-classification","",{"@graph":37,"@context":87},[38,55,70],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":54},"https://docshare.wps.com/document/evaluating-incremental-machine-learning-models-for-road-condition-classification/126226/",4,{"url":53,"name":13,"@type":56,"author":57,"headline":13,"publisher":59,"fileFormat":62,"inLanguage":24,"description":14,"dateModified":63,"datePublished":64,"encodingFormat":62,"isAccessibleForFree":65,"interactionStatistic":66},"DigitalDocument",{"name":9,"@type":58},"Person",{"url":42,"name":60,"@type":61},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":67,"interactionType":68,"userInteractionCount":20},"InteractionCounter",{"@type":69},"ViewAction",{"@type":71,"mainEntity":72},"FAQPage",[73,79,83],{"name":74,"@type":75,"acceptedAnswer":76},"What is the goal of the project?","Question",{"text":77,"@type":78},"The project aims to evaluate different incremental machine learning models for predicting Road Surface Conditions using a dataset provided by Klimator AB.","Answer",{"name":80,"@type":75,"acceptedAnswer":81},"How were the models trained and evaluated?",{"text":82,"@type":78},"Models were trained on datasets derived from vehicle rides with varying RSCs, split into smaller intervals called epochs, and evaluated against Random Forest and a single Dummy Classifier baselines.",{"name":84,"@type":75,"acceptedAnswer":85},"Which models performed best overall and under concept drift?",{"text":86,"@type":78},"Ensembles of Logistic Regression and Decision Tree Classifier showed the greatest overall strengths with the highest average accuracy, while the Hoeffding Tree Classifier performed best during rapid RSC changes, i.e., concept drift events.","https://schema.org",{"og:url":53,"og:type":89,"og:title":13,"og:site_name":60,"og:description":14},"article",{"robots":91,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":94},[95,99,103,107,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":96,"show_sort_weight":97,"slug":98},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":100,"show_sort_weight":101,"slug":102},"Literature",80,"literature",{"id":54,"doc_module":4,"doc_module_name":47,"category_name":104,"show_sort_weight":105,"slug":106},"Exam",70,"exam",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":20,"slug":139},19,"General","general"]