[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128329-en":3,"doc-seo-128329-105":30,"detail-sidebar-cat-0-en-105":92},{"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":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},128329,962085564549,"Genevieve","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Enhancing the Performance and Transparency of Machine Learning (ML) using MRI-derived data - Alternative Approaches to ML Interpretability","This thesis tackles three core challenges in improving machine learning model performance: generalisability in high-dimensional settings, interpretability, and the burden of high data requirements. It develops methods that reduce input dimensionality, increase transparency, and leverage prior knowledge to moderate data needs, enhancing practicality, reliability, and efficiency. Three independent approaches are proposed: two filter-based feature selection techniques driven by correlation and clustering, an ensemble explainability framework combining SHAP with Sobol indices for stable attributions, and a multi-stage transfer-learning pipeline with an autoencoder to reduce labelled data dependence while preserving performance.","University of Reading  \nDoctor of Philosophy  \nEnhancing the Performance and Transparency of Machine Learning (ML) using MRI-derived data: Alternative Approaches to ML Interpretability  \nExplainability  \nAuthor: AtmakuruAkhila  \nSupervisors: Prof. Atta Badii, Prof. Giuseppe Di Fatta, Dr. Ferran Espuny-Pujol  \nDepartment of Computer Science  \nNovember 2025  \nDeclaration  \nI confirm that this is my own work, and the use of all material from other sources has been properly and fully acknowledged.  \nAkhila Atmakuru  \nScientific Publications  \nAtmakuru, A., Di Fatta, G., Nicosia, G., and Badii, A. (2023, September) . Improved filterbased feature selection using correlation and clustering techniques. In International Conference on Machine Learning, Optimization, and Data Science (pp. 379-389) . Cham: Springer Nature Switzerland.  \nDOI: [https://doi.org/10.1007/978-3-031-53969-5_28](https://doi.org/10.1007/978-3-031-53969-5_28)  \nAtmakuru, A., Di Fatta, G., Nicosia, G., Varzandian, A., and Badii, A. (2023, September) . Sensitivity analysis for feature importance in predicting Alzheimer’s Disease. In International Conference on Machine Learning, Optimization, and Data Science (pp. 449-465) . Cham: Springer Nature Switzerland.  \nDOI: [https://doi.org/10.1007/978-3-031-53966-4_33](https://doi.org/10.1007/978-3-031-53966-4_33)  \nAtmakuru, A., Badii, A., and Di Fatta, G. (2024, September) . Transfer Learning for the Cognitive Staging Prediction in Alzheimer’s Disease. In International Conference on Machine Learning, Optimization, and Data Science (pp. 176-190) . Cham: Springer Nature Switzerland.  \nDOI: [https://doi.org/10.1007/978-3-031-82487-6_13](https://doi.org/10.1007/978-3-031-82487-6_13)  \nAbstract  \nThis thesis addresses the three fundamental challenges for enhancing the performance of Machine Learning (ML) models. Despite their evolving predictive capabilities, MLs still present significant limitations in generalisability, particularly in high-dimensional settings, interpretability, and high data requirements. These issues require methodologies that reduce input data dimensionality, enhance transparency, and utilise prior knowledge to moderate the scale of data requirements, thereby improving the performance, reliability, and efficiency of machine learning solutions in practical applications.  \nAccordingly, this thesis introduces three independent methods responsive to the above main limitations that need to be overcome to enhance the performance and transparency of models in complex task domains. First, two filter-based feature selection techniques—one correlation-driven and the other clustering-based—are developed to reduce redundancy and enhance generalisability in high-dimensional data. The correlation-based technique outperforms the state-of-the-art (as represented by ReliefF) in both internal and external validations. Second, an ensemble explainability framework integrates Shapley Additive Explanations (SHAP) values with Sobol indices, combining their rankings to yield stable and interpretable attributions. Third, a multi-stage algorithm couples transfer learning with an autoencoder to minimise labelled data requirements without adversely affecting performance.  \nAll proposed methods yielded quantifiable improvements. The feature selection techniques reduced input dimensionality while enhancing accuracy and generalisability compared to ReliefF. The ensemble explainability framework produced consistent attributions under varying data distributions and reliably identified informative input features. The multistage algorithm achieved enhanced classification performance with reduced reliance on labelled data.  \nCase-Study: The proposed methods were validated in the context of medical diagnosis for early-stage prediction of dementia, utilising a structural Alzheimer’s MRI dataset. In this application, optimising the feature selection, as described above, enhanced the cross-cohort accuracy and decreased the data dimensionality. T","cbCaibPaqm87XNe4","https://ap.wps.com/l/cbCaibPaqm87XNe4","pdf",5647171,1,249,"English","en",105,"# Abstract\n## Three core challenges\n## Proposed methods\n## Results and case study\n# List of Abbreviations","[{\"question\":\"What three fundamental challenges does the thesis focus on?\",\"answer\":\"It targets generalisability in high-dimensional settings, interpretability, and high data requirements for machine learning models.\"},{\"question\":\"How does the thesis improve transparency and interpretability?\",\"answer\":\"It introduces an ensemble explainability framework that integrates SHAP values with Sobol indices to produce stable, interpretable feature attributions.\"},{\"question\":\"How is labelled-data demand reduced in the proposed approach?\",\"answer\":\"The thesis presents a multi-stage algorithm that couples transfer learning with an autoencoder to minimise labelled data requirements without degrading performance.\"}]","Enhancing the Performance and Transparency of Machine Learning (ML) using MRI-derived data - Alternative Approaches to ML Interpretability | PDF",1785946861,627,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"enhancing-the-performance-and-transparency-of-machine-learning-ml-using-mri-derived-data-alternative-approaches-to-ml-interpretability","",{"@graph":36,"@context":86},[37,54,69],{"@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/enhancing-the-performance-and-transparency-of-machine-learning-ml-using-mri-derived-data-alternative-approaches-to-ml-interpretability/128329/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What three fundamental challenges does the thesis focus on?","Question",{"text":76,"@type":77},"It targets generalisability in high-dimensional settings, interpretability, and high data requirements for machine learning models.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the thesis improve transparency and interpretability?",{"text":81,"@type":77},"It introduces an ensemble explainability framework that integrates SHAP values with Sobol indices to produce stable, interpretable feature attributions.",{"name":83,"@type":74,"acceptedAnswer":84},"How is labelled-data demand reduced in the proposed approach?",{"text":85,"@type":77},"The thesis presents a multi-stage algorithm that couples transfer learning with an autoencoder to minimise labelled data requirements without degrading performance.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]