M. Hameed, Faidhalrahman Khaleel, Deiaaldeen Khaleel
{"title":"采用稳健的数据驱动模型来评估安装灌浆柱对环境造成的损害","authors":"M. Hameed, Faidhalrahman Khaleel, Deiaaldeen Khaleel","doi":"10.1109/IEEECONF53624.2021.9668027","DOIUrl":null,"url":null,"abstract":"The jet grouting process involves injecting large quantities of highly pressurized fluids into the soil, which may result in a substantial ground displacement and adverse effects on the environment around the excavation. Consequently, the ground displacement must be estimated accurately in the design phase. In this study, two machine learning models namely, extreme learning machine (ELM) and modified K-nearest neighbor (KNN) are used to estimate the ground displacements. The comparison results show that the ELM is superior to the KNN model in terms of estimation accuracy (coefficient of determination is 0.940). Moreover, the ELM model shows an enhancement by 11.43% higher accuracy in terms of reducing the mean absolute error compared to the KNN model. Overall, the results indicate that ELM has the ability to accurately assess the harmful damages caused by installing grouted columns.","PeriodicalId":389608,"journal":{"name":"2021 Third International Sustainability and Resilience Conference: Climate Change","volume":"27 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Employing a robust data-driven model to assess the environmental damages caused by installing grouted columns\",\"authors\":\"M. Hameed, Faidhalrahman Khaleel, Deiaaldeen Khaleel\",\"doi\":\"10.1109/IEEECONF53624.2021.9668027\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The jet grouting process involves injecting large quantities of highly pressurized fluids into the soil, which may result in a substantial ground displacement and adverse effects on the environment around the excavation. Consequently, the ground displacement must be estimated accurately in the design phase. In this study, two machine learning models namely, extreme learning machine (ELM) and modified K-nearest neighbor (KNN) are used to estimate the ground displacements. The comparison results show that the ELM is superior to the KNN model in terms of estimation accuracy (coefficient of determination is 0.940). Moreover, the ELM model shows an enhancement by 11.43% higher accuracy in terms of reducing the mean absolute error compared to the KNN model. Overall, the results indicate that ELM has the ability to accurately assess the harmful damages caused by installing grouted columns.\",\"PeriodicalId\":389608,\"journal\":{\"name\":\"2021 Third International Sustainability and Resilience Conference: Climate Change\",\"volume\":\"27 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-11-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 Third International Sustainability and Resilience Conference: Climate Change\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IEEECONF53624.2021.9668027\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 Third International Sustainability and Resilience Conference: Climate Change","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IEEECONF53624.2021.9668027","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Employing a robust data-driven model to assess the environmental damages caused by installing grouted columns
The jet grouting process involves injecting large quantities of highly pressurized fluids into the soil, which may result in a substantial ground displacement and adverse effects on the environment around the excavation. Consequently, the ground displacement must be estimated accurately in the design phase. In this study, two machine learning models namely, extreme learning machine (ELM) and modified K-nearest neighbor (KNN) are used to estimate the ground displacements. The comparison results show that the ELM is superior to the KNN model in terms of estimation accuracy (coefficient of determination is 0.940). Moreover, the ELM model shows an enhancement by 11.43% higher accuracy in terms of reducing the mean absolute error compared to the KNN model. Overall, the results indicate that ELM has the ability to accurately assess the harmful damages caused by installing grouted columns.