[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124742-en":3,"doc-seo-124742-105":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},124742,16904993612988,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Heterogeneous Machine Learning Ensembles for Predicting Train Delays","Train delays persist as a serious problem in the UK and other countries, where rail networks operating near full capacity allow an initial delay to cascade into many reactionary delays and degrade overall performance. To support timely alternative planning, the study proposes heterogeneous machine learning ensembles built with two novel model-selection methods that jointly use accuracy and diversity. Experiments on real-world data show improved accuracy and robustness over single models and state-of-the-art homogeneous baselines, and results remain consistent on an independent dataset from a different train operator.","This article has been accepted for inclusion in a future issue of this journal. Content is final as presented, with the exception of pagination.  \nIEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 1  \nHeterogeneous Machine Learning Ensembles for  \nPredicting Train Delays  \nMostafa Al Ghamdi, Gerard Parr, and Wenjia Wang  \nAbstract—Train delays have been a serious persisting problem in the UK and also many other countries. Due to increasing demand, rail networks are running close to their full capacity. As a consequence, an initial delay can cause many knock-on delays to other trains, and this is the main reason for the overall deterioration in the performance of the rail networks. Therefore, it is really useful to have an AI-based method that can predict delays accurately and reliably, to help train controllers to make and apply alternative plans in time to reduce or prevent further delays, when a delay occurs. However, existing machine learning models are not only inaccurate but more importantly unreliable. In this study, we have proposed a new approach to build heterogeneous ensembles with two novel model selection methods based on accuracy and diversity. We tested our heterogeneous ensembles using the real-world data and the results indicated that they are more accurate and robust than single models and state-of-the-art homogeneous ensembles, e.g. Random Forest and XGBoost. We then verified their performances with an independent dataset from a different train operating company and found that they achieved the consistent and accurate results.  \nIndex Terms—Train delay prediction, heterogeneous ensemble, random forest, diversity.  \nI. INTRODUCTION  \nDESPITE significant efforts made by train operating com  \npanies (TOCs) in the UK to improve the performance of train services, the Public Performance Measure (PPM) 1 [1] decreased from 91% in 2013-14 to 82 . 8% and On-Time measure to 62.3% in December of 2022 [2] . In general, train delays can be classified into two types: primary and reactionary. A primary delay is an initial delay that can becaused by a variety of factors, such as accidents, equipment or signal failures, construction works, bad and hot weather,flooding, vandalism, trespass, etc. [3] . A primary delay can then initiate a series of consequential reactionary delays on other trains running on the same or related rail networks [4] . Over the decades, the number of train passengers has been steadily increasing, except at the peak of the Covid-19  \nManuscript received 16 November 2022; revised 13 March 2023; accepted 1 November 2023 . The Associate Editor for this article was D. Pelusi. (Corresponding author: Mostafa Al Ghamdi.)  \nMostafa Al Ghamdi is with the School of Computing and Information, Al-Baha University, Al Baha 65779, Saudi Arabia (e-mail: [malsager@bu.edu.sa](malsager@bu.edu.sa)).  \nGerard Parr and Wenjia Wang are with the School of Computing Sciences, University of East Anglia, NR4 7TJ Norwich, U.K.  \nDigital Object Identifier 10.1109/TITS.2023.3337858  \n1PPM has been the performance indicator of train services in the UK. It was replaced by an enhanced metric—Control Period 6 (CP6) in April 2019, but PPM is still a useful indication and as our data was up to 2019 before the Covid-19 Pandemic, we used it in this study.  \npandemic, so the number of train services has had to be increased accordingly. But the increased train services put more pressure on the rail networks to be running close to their full capacity, and hence leave very little buffer to absorb disturbance of train operations. As a consequence, one small primary delay can cause many reactionary delays cascading through the rail network. This can result in major disruptions to the network and significant inconvenience to the passengers. Whilst the Covid-19 pandemic was very bad for many things, it provided an unprecedented opportunity to verify the impact of rail networks running at their capacity. Due to the significant drop of passenger numbe","cbCaijspMruZZb2H","https://ap.wps.com/l/cbCaijspMruZZb2H","pdf",3171733,1,16,"English","en",105,"# Abstract\n# Index Terms\n# Introduction","[{\"question\":\"Why is predicting train delays important for rail operations?\",\"answer\":\"Initial delays can trigger long chains of reactionary delays when networks run close to full capacity. Accurate prediction enables train controllers to create and apply alternative plans early to reduce disruption and inconvenience.\"},{\"question\":\"What is the main contribution of the proposed method?\",\"answer\":\"The paper introduces heterogeneous machine learning ensembles constructed using two novel model selection methods that emphasize both accuracy and diversity.\"},{\"question\":\"How was the approach evaluated and what were the results?\",\"answer\":\"The ensembles were tested on real-world data and shown to be more accurate and robust than single models and homogeneous baselines such as Random Forest and XGBoost. Performance was further verified on an independent dataset from a different train operating company, producing consistent and accurate results.\"}]","Heterogeneous Machine Learning Ensembles for Predicting Train Delays | PDF",1785894243,40,{"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},"heterogeneous-machine-learning-ensembles-for-predicting-train-delays","",{"@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/heterogeneous-machine-learning-ensembles-for-predicting-train-delays/124742/",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 predicting train delays important for rail operations?","Question",{"text":75,"@type":76},"Initial delays can trigger long chains of reactionary delays when networks run close to full capacity. Accurate prediction enables train controllers to create and apply alternative plans early to reduce disruption and inconvenience.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the main contribution of the proposed method?",{"text":80,"@type":76},"The paper introduces heterogeneous machine learning ensembles constructed using two novel model selection methods that emphasize both accuracy and diversity.",{"name":82,"@type":73,"acceptedAnswer":83},"How was the approach evaluated and what were the results?",{"text":84,"@type":76},"The ensembles were tested on real-world data and shown to be more accurate and robust than single models and homogeneous baselines such as Random Forest and XGBoost. Performance was further verified on an independent dataset from a different train operating company, producing consistent and accurate results.","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"]