[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124442-en":3,"doc-seo-124442-105":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},124442,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Interpreting Time-Series Machine Learning Models through Domain-Informed Basis Functions","Interpreting machine learning models for time-series data is challenging, especially when outputs guide decisions with real-world consequences in domains such as biology. This work proposes domain-defined basis functions to interpret time-series classifiers. The approach is demonstrated on classifying mosquito flight trajectories as insecticide-susceptible (IS) versus insecticide-resistant (IR). Synthetic trajectories generated from relevant parameters probe a trained model to expose learned patterns and features. The results support distinguishing IS and IR populations and can inform more targeted vector control strategies, while extending to broader explainable AI applications via synthetic data probing.","Interpreting Time-Series Machine Learning Models through Domain-Informed Basis Functions  \nYasser Qureshi* School of Engineering, University of Warwick, Coventry, UK  \n[yasser.qureshi@warwick.ac.uk](yasser.qureshi@warwick.ac.uk)  \n*Corresponding author  \nVitaly Voloshin School of Biological and Behavioural Sciences, Queen Mary University of London,  \nLondon, UK  \n[v.voloshin@qmul.ac.uk](v.voloshin@qmul.ac.uk)  \nPhilip J McCall Vector Biology Department, Liverpool School of Tropical Medicine, Liverpool, UK  \n[philip.mccall@lstmed.ac.uk](philip.mccall@lstmed.ac.uk)  \nJames Covington School of Engineering, University of Warwick, Coventry, UK  \n[j](j.a.covington@warwick.ac.uk)[.a.covington@warwick.ac.uk](j.a.covington@warwick.ac.uk)  \nCathy Towers School of Engineering, University of Warwick, Coventry, UK  \n[c.e.towers@warwick.ac.uk](c.e.towers@warwick.ac.uk)  \nDavid Towers School of Engineering, University of Warwick, Coventry, UK  \n[d.towers@warwick.ac.uk](d.towers@warwick.ac.uk)  \nAbstract—Interpreting machine learning models for timeseries data is a critical challenge, particularly in fields where decisions have real-world implications, such as biology. In this work, we introduce a novel approach for interpreting time-series machine learning models using domain-defined basis functions. We apply this method to the classification of mosquito flight trajectories as either insecticide-susceptible (IS) or insecticideresistant (IR), a study into behavioural resistance, which may inform vector control strategies against malaria and other mosquito-borne diseases. By generating synthetic trajectories based on relevant parameters, we systematically probe a trained classifier to reveal the patterns and features it has learned. This approach enhances model interpretation, providing a new perspective on mosquito movement analysis. Furthermore, our findings offer valuable insights into distinguishing between IS and IR mosquito populations, contributing to more targeted and effective mosquito control efforts. Our methodology can be extended and adapted beyond mosquito trajectory analysis, demonstrating how synthetic data can be used to probe and understand complex time-series classifiers thus contributing to the growing field of explainable AI (XAI).  \nKeywords—Explainable AI (XAI), Trajectory Analysis, Machine Learning, Mosquito Behaviour, Time-series Analysis, Insecticide Resistance  \nI. INTRODUCTION  \nMachine learning (ML) has become an essential tool to analyse complex time-series data across various domains, from global markets to biology. In many cases, these time-series datasets contain intricate patterns that are difficult to model using traditional methods. By leveraging large datasets and sophisticated algorithms, machine learning models can capture these patterns offering unique insights that were previously inaccessible. However, despite their predictive power, these models can often suffer from a lack of interpretability, making it challenging for domain experts to trust or understand the decisions being made by these algorithms.  \nYQ was supported by the EPSRC, grant number EP/T51794X/1 .  \nThis challenge has led to an increasing interest in the field of explainable AI (XAI) and model interpretability. Most work in XAI focuses on natural language processing and computer vision [1] with comparatively less attention being given to time-series modelling. The ability to decipher a model becomes particularly important in fields such as biology, where decisions based on machine learning outputs can have significant real-world implications. Recent work in XAI has started to address the interpretability of time-series models with methods ranging from feature importance rankings [2, 3] to visualisation techniques [4] . However, these approaches often provide limited insights as they do not always incorporate domain-specific knowledge that could further refine the understanding of the models.  \nIn this work, we introduce a novel approach","cbCaiuxMUEStn8Hk","https://ap.wps.com/l/cbCaiuxMUEStn8Hk","pdf",770048,1,5,"English","en",105,"# Introduction\n## Explainable AI for time-series models\n## Domain-informed basis functions overview\n# Methods\n## Machine learning classifier\n## Synthetic trajectory generation\n# Results and Discussion\n## Probing learned decision patterns\n## Distinguishing insecticide-susceptible vs resistant mosquitoes\n# Conclusion\n## Extending the approach to other time-series classifiers","[{\"question\":\"What problem does the document address in time-series machine learning?\",\"answer\":\"The document addresses the difficulty of interpreting time-series machine learning models, particularly in domains where model decisions have real-world implications, such as biology.\"},{\"question\":\"How does the proposed method improve model interpretability?\",\"answer\":\"It uses domain-defined basis functions to generate synthetic trajectories from relevant parameters, then systematically probes a trained classifier to reveal patterns and features the model has learned.\"},{\"question\":\"How is the method applied in the mosquito study?\",\"answer\":\"It is applied to classify mosquito flight trajectories as insecticide-susceptible (IS) or insecticide-resistant (IR), providing insights that may help refine vector control strategies.\"}]","Interpreting Time-Series Machine Learning Models through Domain-Informed Basis Functions | PDF",1785822308,13,{"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},"interpreting-time-series-machine-learning-models-through-domain-informed-basis-functions","",{"@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/interpreting-time-series-machine-learning-models-through-domain-informed-basis-functions/124442/",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},"What problem does the document address in time-series machine learning?","Question",{"text":75,"@type":76},"The document addresses the difficulty of interpreting time-series machine learning models, particularly in domains where model decisions have real-world implications, such as biology.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method improve model interpretability?",{"text":80,"@type":76},"It uses domain-defined basis functions to generate synthetic trajectories from relevant parameters, then systematically probes a trained classifier to reveal patterns and features the model has learned.",{"name":82,"@type":73,"acceptedAnswer":83},"How is the method applied in the mosquito study?",{"text":84,"@type":76},"It is applied to classify mosquito flight trajectories as insecticide-susceptible (IS) or insecticide-resistant (IR), providing insights that may help refine vector control strategies.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"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":21,"slug":137},19,"General","general"]