[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119871-en":3,"doc-seo-119871-105":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},119871,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Modeling Asphalt Pavement Frictional Properties using Different Machine Learning Algorithms","The objective of this work is to build and evaluate machine learning models that predict Locked Wheel Skid Trailer (LWST) values from Dynamic Friction Tester (DFT) and Circular Texture Meter (CTM) measurements on asphalt pavement surfaces. Three modeling setups are tested: DFT at multiple speeds (20–64 km/h), DFT combined with Mean Profile Depth (MPD), and a model using International Friction Index (IFI) parameters (F60 and SP). Two supervised approaches—MLP-type ANN and M5P trees—are compared with a lazy KNN/IBL model. Results show MLP achieves the strongest correlation and highest prediction power, while trees remain close with simpler regression.","Modeling Asphalt Pavement Frictional Properties using Different Machine  \nLearning Algorithms  \nMohammad Ali Khasawneh  \nCivil Engineering, Prince Mohammad Bin Fahd University, Al Azeziya, Eastern Province, Kingdom of Saudi Arabia  \n[mkhasawneh@pmu.edu.sa](mkhasawneh@pmu.edu.sa)  \nMohammad Ahmad Alsheyab  \nCivil, Construction and Environmental Engineering, Iowa State University, Ames, Iowa, USA  \n[alsheyab@iastate.edu](alsheyab@iastate.edu)  \nHaneen Issa Al Akhrass  \nCivil Engineering, Jordan University of Science and Technology, Irbid, Jordan  \n[hialakhrass18@eng.just.edu.jo](hialakhrass18@eng.just.edu.jo)  \nAbstract  \nThe objective of this work is to use some machine learning algorithms and test its efficiency in developing models to predict Locked Wheel Skid Trailer (LWST) values from Dynamic Friction Tester (DFT) and Circular Texture Meter (CTM) measurements conducted on asphalt pavement surfaces. For this prediction, three models were developed using DFT measurements at different speeds starting from 20km/h (12.5 mph) up to 64 km/h (40 mph) and then same DFT measurements as combination with Mean Profile Depth (MPD) and the last model used the International Friction Index (IFI) parameters (F60 and SP) . The machine learning techniques includes two supervised learning algorithms: the Multi-Layer Perceptron (MLP) type of Artificial Neural Networks (ANN) and M5P tree model. In addition to one lazy algorithm called the K Nearest Neighbor (KNN) or Instance-Based Learner (IBL) . The results showed that MLP models are the best in terms of the correlation coefficient that resulted in 81% prediction power using DFT parameters. Additionally, it was shown that the result of tree models was close to ANN but with much simpler regression. However, KNN models were recommended for LWST prediction of similar data characteristics and it is expected that this algorithm will be more efficient as the training data set becomes larger.  \nKeywords: Friction; Texture; International Friction Index (IFI); Machine Learning Algorithms  \n1 Introduction  \nPavement skid resistance is defined as the impeding force generated by the interaction between a tire and a pavement under a non-rotating wheel (ASTM 867-02, 2015) . Since skidding occurs when the frictional demand exceeds the available friction force at the interface between a tire and pavement, it is important to measure the ability of a pavement to resist the skidding of a tire on a motor vehicle.  \nLack of sufficient surface friction is one of the factors contributing to crashes on roads. The tirepavement interaction has been a vital field of study due to the volume and severity of motor vehicle accidents on roads as in Hofko et al. (2019) . Theoretically, the surface frictional force developed between a pavement and a tire is composed of two components: adhesion and hysteresis. Adhesion is only significant on dry surfaces at low vehicle speed and hysteresis has a considerable  \nsignificance at high vehicle speed on wet surfaces (Khasawneh & Alsheyab, 2020) .  \nMultiple methods and procedures have been developed to evaluate the tire-pavement interaction and surface textures. There are two major devices used for the measurement of pavement surface friction in the laboratory, namely; British Pendulum Tester (BPT) as outlined in (ASTM E 303-93, 2002) and Dynamic Friction (DF) tester as specified in (ASTM E 1911-98, 2002) . Both are highly portable, easy to handle and can be used in the field.  \nThere are four basic types of full-scale friction-measuring devices. These are side-force, locked wheel, fixed-slip, and variable-slip devices. Unlike the portable devices, these devices can measure friction at or close to highway speeds, see (Henry, 2000) .  \nTo our knowledge, no available devices can measure pavement micro-texture directly. However, they can be measured indirectly at low-speed levels using laboratory friction devices, such as the British Pendulum Tester at 10km/h and the Dynamic Friction Test","cbCaihG5E3uahx4r","https://ap.wps.com/l/cbCaihG5E3uahx4r","pdf",399576,1,9,"English","en",105,"# Abstract\n# Introduction\n## Pavement skid resistance background\n## Measurement devices and friction testers\n## Tire–pavement interaction components\n## Texture and macrotexture measurement methods\n## Role of machine learning in pavement evaluation\n# Materials and Methods\n## Input measurements: DFT, CTM, MPD, IFI\n## Machine learning algorithms used: MLP, M5P, KNN/IBL\n# Results\n## Prediction performance and correlation\n## Comparison across model types\n# Discussion and Conclusions\n## Practical recommendations for similar data characteristics","[{\"question\":\"What variables are used to predict LWST values in this study?\",\"answer\":\"The models predict LWST using measurements from the Dynamic Friction Tester (DFT) and Circular Texture Meter (CTM). Additional setups incorporate Mean Profile Depth (MPD) or International Friction Index (IFI) parameters (F60 and SP).\"},{\"question\":\"Which machine learning algorithms are evaluated?\",\"answer\":\"Two supervised learning methods are tested: an MLP-type Artificial Neural Network (ANN) and an M5P tree model. A lazy method, K Nearest Neighbor (KNN) / Instance-Based Learner (IBL), is also included for comparison.\"},{\"question\":\"Which model performs best for LWST prediction and why is KNN still recommended?\",\"answer\":\"MLP models perform best, delivering the highest correlation and about 81% prediction power using DFT parameters. KNN is recommended for LWST prediction when data characteristics are similar, and it is expected to improve further with larger training datasets.\"}]","Modeling Asphalt Pavement Frictional Properties using Different Machine Learning Algorithms | PDF",1785726751,23,{"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},"modeling-asphalt-pavement-frictional-properties-using-different-machine-learning-algorithms","",{"@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/modeling-asphalt-pavement-frictional-properties-using-different-machine-learning-algorithms/119871/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What variables are used to predict LWST values in this study?","Question",{"text":75,"@type":76},"The models predict LWST using measurements from the Dynamic Friction Tester (DFT) and Circular Texture Meter (CTM). Additional setups incorporate Mean Profile Depth (MPD) or International Friction Index (IFI) parameters (F60 and SP).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning algorithms are evaluated?",{"text":80,"@type":76},"Two supervised learning methods are tested: an MLP-type Artificial Neural Network (ANN) and an M5P tree model. A lazy method, K Nearest Neighbor (KNN) / Instance-Based Learner (IBL), is also included for comparison.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model performs best for LWST prediction and why is KNN still recommended?",{"text":84,"@type":76},"MLP models perform best, delivering the highest correlation and about 81% prediction power using DFT parameters. KNN is recommended for LWST prediction when data characteristics are similar, and it is expected to improve further with larger training datasets.","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},[93,97,101,105,110,115,120,123,127,130,134],{"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":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":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"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"]