[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120170-en":3,"doc-seo-120170-105":29,"detail-sidebar-cat-0-en-105":89},{"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":20,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},120170,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Advancing Lightweight Engineered Cementitious Composites - An Interpretable Machine Learning Framework","The study advances Lightweight Engineered Cementitious Composites (LWECCs) for civil engineering by integrating machine learning to predict and interpret key mechanical performance. XGBoost, LightGBM, and gene expression programming are trained to forecast compressive strength and flexural strength using literature-derived mixture data. SHAP analysis is used to quantify component influence, highlighting how W/B ratio and mixture proportions affect strength. A GEP-based empirical equation is validated on a new dataset for accurate application-ready predictions, supporting improved mixture design and performance optimization.","|  | Advancing Lightweight Engineered Cementitious Composites: An\u003Cbr>Interpretable Machine Learning Framework\u003Cbr>Name of Presenter: Md Nasir Uddin\u003Cbr>Degree and program (of presenter): PhD in MSEC\u003Cbr>Co-Authors names: Dr. Xijun Shi\u003Cbr>Funders if any: None\u003Cbr> |  |  |\n| --- | --- | --- | --- |\n| Purpose |  | Methodology | Industrial implications |\n\nThis abstract outlines a research study focused on enhancing the design and utilization of Lightweight Engineered Cementitious Composites (LWECCs) in civil engineering through the application of Machine Learning (ML) techniques. The primary purposes of this research are:  \nPredictive Modeling of Material Properties: Developing predictive models using advanced ML algorithms like eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM) and gene expression programming (GEP) to accurately forecast the Compressive Strength (CS) and Flexural Strength (FS) of LWECCs. These strength parameters are crucial for assessing the material's suitability for various construction applications.  \nOptimization of Mixture Designs: By collecting data on mixture design components and their resulting strengths from existing literature, and analyzing this data through ML models, the research aims to identify the most effective combinations of materials, specifically focusing on LWECCs reinforced with fiber  \nInsight into Material Properties through SHAP Analysis: Utilizing SHapley Additive exPlanations (SHAP) analysis to understand how different mixture components influence the predictive models' outcomes. This can provide valuable insights into how various ingredients in the composites contribute to their overall strength, informing better material design and engineering practices.  \nDevelop Empirical equation for the material application: The overarching goal of this research is to demonstrate how integrating cutting-edge ML techniques can significantly advance material design and optimization in civil engineering – especially using GEP modeling.  \n| \u003Cbr>\u003Cbr>\u003Cbr> |  |\n| --- | --- |\n\nML results  \nSHAP results  \nConclusion  \nXGBoost  \nmax_depth  \nn_estimators gamma learning_rate subsample  \n[1,15]  \n[100, 500]  \n[0, 1]  \n[0.01, 0.05]  \n[0.6,1]  \n15  \n500  \n0  \n0.03  \n01  \n[1,5]  \n[100, 500]  \n[0, 1]  \n[0.01, 0.5]  \n[0.6,1]  \n5  \n250  \n1  \n0.5  \n1  \n[1] C. Cakiroglu, Y. Aydın, G. Bekdaş, and Z. W. Geem,“Interpretable Predictive Modelling of Basalt Fiber Reinforced Concrete Splitting Tensile Strength Using Ensemble Machine Learning Methods and SHAP Approach,” Materials (Basel)., vol. 16, no. 13, p. 4578, 2023, doi: 10.3390/ma16134578 .  \n[2] P. G. Asteris, A. D. Skentou, A. Bardhan, P. Samui, and K. Pilakoutas,“Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models,” Cem. Concr. Res., vol. 145, 2021, doi: 10.1016/j.cemconres.2021.106449 .  \n[3] Mousavi SM, Aminian P, Gandomi AH, Alavi AH, Bolandi H. A new predictive model for compressive strength of HPC using gene expression programming. Adv Eng Softw 2012;45:105–14. [https://doi.org/10.1016/j.advengsoft.2011.09.014](https://doi.org/10.1016/j.advengsoft.2011.09.014) .  \n1. The ML models XGB and LGBM exhibited high accuracy in predicting the CS of LWECC during training (R 2 = 0.89 and 0.90) and testing (R2 = 0.88 and 0.88) respectively. This indicates that the XGB and LGBM models exhibited similar levels of accuracy with minimal error and overfitting.  \n2. Hyperparametric techniques, using GridsearhCV was utilized to optimize the ML performances.  \n3. SHAP results also presented for the CS here, which shows W/B ratio has higher impact in the compressive strength. It also represents if we increase the W/B, SP (%), HGMs (%) and FAC in the mixture it will decrease the compressive strength.  \n4. A novel empirical equation based was developed on GEP to predict the CS of LWECC. The GEP model was rigorously validated using the new dataset. This equation exhibits a high level of accuracy in predictin","cbCaiuu3pj9Et7YK","https://ap.wps.com/l/cbCaiuu3pj9Et7YK","pdf",1486515,1,"English","en",105,"# Purpose and Objectives\n## Predictive modeling of compressive and flexural strength\n## Optimization of mixture design\n## Interpretability using SHAP analysis\n## Empirical equation via GEP\n# Methods and Results\n## Model performance: XGBoost, LightGBM, and GEP\n## Hyperparameter optimization\n## SHAP feature impact findings\n# Empirical equation and validation\n# Conclusion","[{\"question\":\"Which machine learning models are used to predict LWECC strength performance?\",\"answer\":\"The framework uses XGBoost, LightGBM, and gene expression programming (GEP) to predict compressive strength (and related outcomes). Training and testing performance are reported with high accuracy metrics.\"},{\"question\":\"How does the research optimize mixture designs for LWECCs?\",\"answer\":\"It collects component and strength data from existing literature and analyzes it through ML models to identify effective material combinations, focusing on fiber-reinforced LWECC mixtures.\"},{\"question\":\"What does SHAP analysis reveal about controlling factors for compressive strength?\",\"answer\":\"SHAP results indicate the W/B ratio has higher impact on compressive strength. Increasing W/B along with certain mixture components (e.g., SP (%), HGMs (%), FAC) is associated with reduced compressive strength.\"}]","Advancing Lightweight Engineered Cementitious Composites - An Interpretable Machine Learning Framework | PDF",1785728542,3,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":27},"advancing-lightweight-engineered-cementitious-composites-an-interpretable-machine-learning-framework","",{"@graph":35,"@context":83},[36,52,66],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,49],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":28},"https://docshare.wps.com/document/research-report/",{"item":50,"name":13,"@type":42,"position":51},"https://docshare.wps.com/document/advancing-lightweight-engineered-cementitious-composites-an-interpretable-machine-learning-framework/120170/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":40,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":63,"interactionType":64,"userInteractionCount":20},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"Which machine learning models are used to predict LWECC strength performance?","Question",{"text":73,"@type":74},"The framework uses XGBoost, LightGBM, and gene expression programming (GEP) to predict compressive strength (and related outcomes). Training and testing performance are reported with high accuracy metrics.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"How does the research optimize mixture designs for LWECCs?",{"text":78,"@type":74},"It collects component and strength data from existing literature and analyzes it through ML models to identify effective material combinations, focusing on fiber-reinforced LWECC mixtures.",{"name":80,"@type":71,"acceptedAnswer":81},"What does SHAP analysis reveal about controlling factors for compressive strength?",{"text":82,"@type":74},"SHAP results indicate the W/B ratio has higher impact on compressive strength. Increasing W/B along with certain mixture components (e.g., SP (%), HGMs (%), FAC) is associated with reduced compressive strength.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":45,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":104,"slug":136},19,"General","general"]