{"title":"基于自适应网络的模糊推理系统评估不确定性事件对公路建设项目成本的影响","authors":"A. Moghayedi","doi":"10.1680/jensu.21.00061","DOIUrl":null,"url":null,"abstract":"This research examines the uncertainty events encountered in the process of constructing highways and evaluates their impact on South African highway construction costs. The rationale for this examination stems from the scholarly view that the costs of highway construction projects are underestimated due to the lack of appropriate evaluation of the impact of uncertainty events encountered in the construction process of highway projects. To counteract such underestimation, this research has developed an Adaptive Neuro-Fuzzy Inference System (ANFIS) as a simple advanced machine learning technique to assess the impact of uncertainty events involved in the construction of linear infrastructure projects. To validate the ANFIS model, the Stepwise Regression models (SRA) and Fuzzy Bayesian Network (FBN) have been designed, and their results are compared with the outputs of the ANFIS. The prediction performance comparison proved that the ANFIS has a higher performance than SRA and FBN with an accuracy degree of 99.15%, the margin of the error of 0.85% and excellent fitness (∼1) of the prediction model. Based on the result of the study, it can be deduced that the ANFIS model is a more accurate and reliable technique in assessing the impact of uncertainty events on the cost of the construction projects compared to the statistical and probabilistic models. Therefore, the study concludes that using hybrid intelligent machine learning techniques such as ANFIS not only minimises the time and difficulty of the estimation process but also reduces the potential inconsistency of correlation between variables in construction cost prediction. The model developed enables cost engineers to estimate the construction cost with a higher degree of accuracy.","PeriodicalId":49671,"journal":{"name":"Proceedings of the Institution of Civil Engineers-Engineering Sustainability","volume":"30 1","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2022-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Evaluating the impact of uncertainty events on the cost of highway construction project using Adaptive-Network-based Fuzzy Inference System\",\"authors\":\"A. Moghayedi\",\"doi\":\"10.1680/jensu.21.00061\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This research examines the uncertainty events encountered in the process of constructing highways and evaluates their impact on South African highway construction costs. The rationale for this examination stems from the scholarly view that the costs of highway construction projects are underestimated due to the lack of appropriate evaluation of the impact of uncertainty events encountered in the construction process of highway projects. To counteract such underestimation, this research has developed an Adaptive Neuro-Fuzzy Inference System (ANFIS) as a simple advanced machine learning technique to assess the impact of uncertainty events involved in the construction of linear infrastructure projects. To validate the ANFIS model, the Stepwise Regression models (SRA) and Fuzzy Bayesian Network (FBN) have been designed, and their results are compared with the outputs of the ANFIS. The prediction performance comparison proved that the ANFIS has a higher performance than SRA and FBN with an accuracy degree of 99.15%, the margin of the error of 0.85% and excellent fitness (∼1) of the prediction model. Based on the result of the study, it can be deduced that the ANFIS model is a more accurate and reliable technique in assessing the impact of uncertainty events on the cost of the construction projects compared to the statistical and probabilistic models. Therefore, the study concludes that using hybrid intelligent machine learning techniques such as ANFIS not only minimises the time and difficulty of the estimation process but also reduces the potential inconsistency of correlation between variables in construction cost prediction. The model developed enables cost engineers to estimate the construction cost with a higher degree of accuracy.\",\"PeriodicalId\":49671,\"journal\":{\"name\":\"Proceedings of the Institution of Civil Engineers-Engineering Sustainability\",\"volume\":\"30 1\",\"pages\":\"\"},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2022-03-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the Institution of Civil Engineers-Engineering Sustainability\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1680/jensu.21.00061\",\"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":"Proceedings of the Institution of Civil Engineers-Engineering Sustainability","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1680/jensu.21.00061","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}
Evaluating the impact of uncertainty events on the cost of highway construction project using Adaptive-Network-based Fuzzy Inference System
This research examines the uncertainty events encountered in the process of constructing highways and evaluates their impact on South African highway construction costs. The rationale for this examination stems from the scholarly view that the costs of highway construction projects are underestimated due to the lack of appropriate evaluation of the impact of uncertainty events encountered in the construction process of highway projects. To counteract such underestimation, this research has developed an Adaptive Neuro-Fuzzy Inference System (ANFIS) as a simple advanced machine learning technique to assess the impact of uncertainty events involved in the construction of linear infrastructure projects. To validate the ANFIS model, the Stepwise Regression models (SRA) and Fuzzy Bayesian Network (FBN) have been designed, and their results are compared with the outputs of the ANFIS. The prediction performance comparison proved that the ANFIS has a higher performance than SRA and FBN with an accuracy degree of 99.15%, the margin of the error of 0.85% and excellent fitness (∼1) of the prediction model. Based on the result of the study, it can be deduced that the ANFIS model is a more accurate and reliable technique in assessing the impact of uncertainty events on the cost of the construction projects compared to the statistical and probabilistic models. Therefore, the study concludes that using hybrid intelligent machine learning techniques such as ANFIS not only minimises the time and difficulty of the estimation process but also reduces the potential inconsistency of correlation between variables in construction cost prediction. The model developed enables cost engineers to estimate the construction cost with a higher degree of accuracy.
期刊介绍:
Engineering Sustainability provides a forum for sharing the latest thinking from research and practice, and increasingly is presenting the ''how to'' of engineering a resilient future. The journal features refereed papers and shorter articles relating to the pursuit and implementation of sustainability principles through engineering planning, design and application. The tensions between and integration of social, economic and environmental considerations within such schemes are of particular relevance. Methodologies for assessing sustainability, policy issues, education and corporate responsibility will also be included. The aims will be met primarily by providing papers and briefing notes (including case histories and best practice guidance) of use to decision-makers, practitioners, researchers and students.