{"title":"利用可解释人工智能增强对冬季道路安全的理解:支持向量机和 SHAP 的启示","authors":"Zehua Shuai, Tae J. Kwon, Qian Xie","doi":"10.1139/cjce-2023-0446","DOIUrl":null,"url":null,"abstract":"This study investigates the utility of machine learning (ML) in understanding and mitigating winter road risks. Despite their capability in managing complex data structures, ML models often lack interpretability. We address this issue by integrating Shapley Additive Explanations (SHAP) with a Support Vector Machine (SVM) model. Utilizing a comprehensive dataset of 231 snowstorm events collected in the city of Edmonton across two winter seasons, the SVM model achieved an accuracy rate of 87.2%. Following model development, a SHAP summary plot was employed to identify the contribution of individual features to collision predictions—an insight not achievable through ML alone. Next, SHAP waterfall plots were used to assess the reliability of individual predictions. The findings enhanced our understanding of the complex SVM model and provided greater insights into the diverse factors affecting winter road safety.","PeriodicalId":9414,"journal":{"name":"Canadian Journal of Civil Engineering","volume":null,"pages":null},"PeriodicalIF":1.1000,"publicationDate":"2024-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Using Explainable AI for Enhanced Understanding of Winter Road Safety: Insights with Support Vector Machines and SHAP\",\"authors\":\"Zehua Shuai, Tae J. Kwon, Qian Xie\",\"doi\":\"10.1139/cjce-2023-0446\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study investigates the utility of machine learning (ML) in understanding and mitigating winter road risks. Despite their capability in managing complex data structures, ML models often lack interpretability. We address this issue by integrating Shapley Additive Explanations (SHAP) with a Support Vector Machine (SVM) model. Utilizing a comprehensive dataset of 231 snowstorm events collected in the city of Edmonton across two winter seasons, the SVM model achieved an accuracy rate of 87.2%. Following model development, a SHAP summary plot was employed to identify the contribution of individual features to collision predictions—an insight not achievable through ML alone. Next, SHAP waterfall plots were used to assess the reliability of individual predictions. The findings enhanced our understanding of the complex SVM model and provided greater insights into the diverse factors affecting winter road safety.\",\"PeriodicalId\":9414,\"journal\":{\"name\":\"Canadian Journal of Civil Engineering\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.1000,\"publicationDate\":\"2024-02-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Canadian Journal of Civil Engineering\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1139/cjce-2023-0446\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Canadian Journal of Civil Engineering","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1139/cjce-2023-0446","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
Using Explainable AI for Enhanced Understanding of Winter Road Safety: Insights with Support Vector Machines and SHAP
This study investigates the utility of machine learning (ML) in understanding and mitigating winter road risks. Despite their capability in managing complex data structures, ML models often lack interpretability. We address this issue by integrating Shapley Additive Explanations (SHAP) with a Support Vector Machine (SVM) model. Utilizing a comprehensive dataset of 231 snowstorm events collected in the city of Edmonton across two winter seasons, the SVM model achieved an accuracy rate of 87.2%. Following model development, a SHAP summary plot was employed to identify the contribution of individual features to collision predictions—an insight not achievable through ML alone. Next, SHAP waterfall plots were used to assess the reliability of individual predictions. The findings enhanced our understanding of the complex SVM model and provided greater insights into the diverse factors affecting winter road safety.
期刊介绍:
The Canadian Journal of Civil Engineering is the official journal of the Canadian Society for Civil Engineering. It contains articles on environmental engineering, hydrotechnical engineering, structural engineering, construction engineering, engineering mechanics, engineering materials, and history of civil engineering. Contributors include recognized researchers and practitioners in industry, government, and academia. New developments in engineering design and construction are also featured.