[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122658-en":3,"doc-seo-122658-105":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},122658,687197100911,"Himbo","https://ap-avatar.wpscdn.com/avatar/a000239b6f1da00475?x-image-process=image/resize,m_fixed,w_180,h_180&k=1785132997149421697",8,"Research & Report","A Hybrid Ensemble Machine Learning Approach For Arrival Flight Delay Classification Prediction Using Voting Aggregation Technique","Arrival flight delays impact airport efficiency, operational coordination, passenger satisfaction, and economic performance. With growing aviation data volumes and limited feasibility of traditional processing, machine-learning methods are used to forecast delays and mitigate cascading effects. The paper proposes a hybrid ensemble strategy that combines learning models and integrates a voting aggregation technique for improved classification on high-dimensional, imbalanced flight datasets while addressing necessary feature preprocessing and encoding challenges.","2023 AIAA Aviation and Aeronautics Forum and Exposition (AIAA AVIATION Forum), 12-16 June, San Diego, USA. Paper AIAA 2023-4326  \nDOI:10.2514/6.2023-4326  \nA Hybrid Ensemble Machine Learning Approach For Arrival Flight Delay Classification Prediction Using Voting Aggregation Technique  \nDesmond B. Bisandu1*, Irene Moulitsas2  \nCranfield University, Bedford, MK43 0AL, United Kingdom  \nI. Nomenclature  \nµ(i) =mean  \ncj =samples class label d(i) =discriminant power di =discriminant power F =features vector  \nfi,j =index of ith learning sample in the jth feature  \nFre =feature group at the rear Ftop =features group at the top M =dataset matrix definition m =number of dataset sample n =number of dataset features nF =number of the sample feature p(i) =discriminant class S =features significant s =standard error  \nXi =vector collection of features  \nα and β =parameter of the filter feature significant σ(i) =standard deviation  \nII. Introduction  \nMany factors, such as safety, security, air carrier, maintenance, National Aviation System (NAS), weather and airport scheduling, affect flight plans in the civil aviation transportation processes [1-4] . Frequently, scheduled flights cannot arrive on time, affecting subsequent flights. Flight delay occurs conventionally if the flight is 15 minutes later than the scheduled departure or arrival time. Air traffic demand-capacity imbalances in arrival/departure flights resulting from continuous air traffic growth with limited airport expansion capabilities. For example, in 2017, there was 4.3% on European flights relative to 2016 [3] . It corresponds to an average of 1191 flights per day. Also, 20.4% of flights in 2017 experienced arrival delays of 15 minutes and above [6-8] . It is important to predict flight delays to improve airport efficiency and operation coordination. These delays have caused more damage to the aviation industry and passengers with almost an exponential increment, leading to poor passenger satisfaction and a loss of at least $20.5 million to flight delay-related issues in the United States in 2018 [5,9,10] .  \n1*Ph.D. Candidate, Centre for Computational Engineering Sciences; [desmond.bisandu@cranfield.ac.uk](desmond.bisandu@cranfield.ac.uk).  \nAIAA Student Member.  \n2Senior Lecturer, Centre for Computational Engineering Sciences; [i.moultsas@cranfield.ac.uk](i.moultsas@cranfield.ac.uk).  \n1*,2Machine Learning and Data Analytics Laboratory, Digital Aviation Research and Technology Centre (DARTeC) .  \nWith the rapid increase in the amount of data from the air transportation industry due to the constant development in the sector, processing the huge amount of data is becoming tedious and almost impractical with only traditional processing methods such as balancing and shuffling. Flight delay  \nPublished by AIAA. This is the Author Accepted Manuscript issued with: Creative Commons Attribution License (CC:BY 4.0) . The final published version (version of record) is available online at DOI:10.2514/6.2023-4326 . Please refer to any applicable publisher terms of use.  \nprediction based on machine learning has achieved good performance in the past. Some methods such as KNN, decision tree and random forest [3], Support vector classifier, and other methods have good accuracy on large flight on-time datasets but are slow in computation compared with deep learning methods. Machine learning superior performance in prediction compared with other traditional statistical methods has been massively recorded in artificial intelligence and transportation-related research [11,12,13, 14, 15] . Support Vector Machine (SVM) is among the most popular machine learning techniques for classification problems because of high prediction results, especially with high dimensional and imbalanced datasets [13,16, 17] . However, due to the high dimension of the feature, good pre-processing is required to perform flight delay predictions. For instance, one-hot encoding processing will be needed for flight l","cbCaicAfw5S5qhjJ","https://ap.wps.com/l/cbCaicAfw5S5qhjJ","pdf",1058568,1,14,"English","en",105,"# Introduction\n## Flight delay problem and motivation\n## Related machine learning and deep learning approaches\n# Proposed hybrid ensemble approach\n## Ensemble learning and boosting methods\n## Voting aggregation technique\n# Nomenclature","[{\"question\":\"Why is arrival flight delay classification important in civil aviation operations?\",\"answer\":\"Arrival delays affect subsequent flights, reduce airport efficiency, and degrade passenger satisfaction while creating measurable economic losses. Accurate prediction supports better coordination and operational planning.\"},{\"question\":\"What makes flight delay prediction challenging for machine learning models?\",\"answer\":\"High-dimensional features and imbalance in on-time versus delayed cases require careful preprocessing and encoding. One-hot encoding and other categorical encodings can introduce sparsity and may remove information useful for model performance.\"},{\"question\":\"How does the paper’s approach improve classification accuracy?\",\"answer\":\"It uses a hybrid ensemble learning framework and applies a voting aggregation technique to combine multiple predictive functions, aiming to reduce loss through iterative model construction and strengthen performance on imbalanced datasets.\"}]","A Hybrid Ensemble Machine Learning Approach For Arrival Flight Delay Classification Prediction Using Voting Aggregation Technique | PDF",1785812008,35,{"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},"a-hybrid-ensemble-machine-learning-approach-for-arrival-flight-delay-classification-prediction-using-voting-aggregation-technique","",{"@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/a-hybrid-ensemble-machine-learning-approach-for-arrival-flight-delay-classification-prediction-using-voting-aggregation-technique/122658/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is arrival flight delay classification important in civil aviation operations?","Question",{"text":75,"@type":76},"Arrival delays affect subsequent flights, reduce airport efficiency, and degrade passenger satisfaction while creating measurable economic losses. Accurate prediction supports better coordination and operational planning.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What makes flight delay prediction challenging for machine learning models?",{"text":80,"@type":76},"High-dimensional features and imbalance in on-time versus delayed cases require careful preprocessing and encoding. One-hot encoding and other categorical encodings can introduce sparsity and may remove information useful for model performance.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the paper’s approach improve classification accuracy?",{"text":84,"@type":76},"It uses a hybrid ensemble learning framework and applies a voting aggregation technique to combine multiple predictive functions, aiming to reduce loss through iterative model construction and strengthen performance on imbalanced 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},[93,97,101,105,110,115,120,123,128,131,135],{"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"]