Pub Date : 2024-12-12DOI: 10.1016/j.autcon.2024.105890
Peng Zhou, Yifan Qi, Qian Yang, Yuan Chang
The application of machine learning (ML) in the building domain has rapidly evolved due to developments in ML algorithms. Abundant studies have reviewed the use of ML algorithms to address building-domain-related challenges, but some research questions remain unclear: (i) what is the landscape of ML application topics in building domain, (ii) what are the preferences among different ML application topics and algorithms, and (iii) how these topics, ML algorithms, and their preferences evolve until forming current landscape. To address these aspects, an ML-based topic modeling (TM) approach was used in this paper to identify all ML application topics, elucidate the horizontal correlation and vertical knowledge hierarchy among the topics to reveal their static correlation and dynamic evolution with ML algorithms. Several findings that answered each research question were drawn, and recommendations that can facilitate balanced and rational ML advancements in the building domain are proposed for future research.
{"title":"Neural topic modeling of machine learning applications in building: Key topics, algorithms, and evolution patterns","authors":"Peng Zhou, Yifan Qi, Qian Yang, Yuan Chang","doi":"10.1016/j.autcon.2024.105890","DOIUrl":"https://doi.org/10.1016/j.autcon.2024.105890","url":null,"abstract":"The application of machine learning (ML) in the building domain has rapidly evolved due to developments in ML algorithms. Abundant studies have reviewed the use of ML algorithms to address building-domain-related challenges, but some research questions remain unclear: (i) what is the landscape of ML application topics in building domain, (ii) what are the preferences among different ML application topics and algorithms, and (iii) how these topics, ML algorithms, and their preferences evolve until forming current landscape. To address these aspects, an ML-based topic modeling (TM) approach was used in this paper to identify all ML application topics, elucidate the horizontal correlation and vertical knowledge hierarchy among the topics to reveal their static correlation and dynamic evolution with ML algorithms. Several findings that answered each research question were drawn, and recommendations that can facilitate balanced and rational ML advancements in the building domain are proposed for future research.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"46 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-11DOI: 10.1016/j.autcon.2024.105899
Jiale Li, Chenglong Yuan, Xuefei Wang, Guangqi Chen, Guowei Ma
Computer vision models have shown great potential in pavement distress detection. There is still challenge of low robustness under different scenarios. The model robustness is enhanced with more annotated data. However, this approach is labor-intensive and not a sustainable long-term solution. This paper proposes a semi-supervised instance segmentation method for road distress detection based on deep transfer learning. The interactive segmentation method utilizing SAM are used to enhance the production efficiency of segmentation datasets. The DCNv3 and lightweight segmentation heads are strategically designed to offset potential speed losses. The deep transfer learning method fine-tunes the pre-trained models, enhancing their competency for new tasks. The proposed model achieves comparable performance to supervised learning with fewer annotated data, accurately determining crack dimensions across varied scenarios. This paper provides an efficient and practical approach for pavement distress identification using the hybrid computer vision methodology.
{"title":"Semi-supervised crack detection using segment anything model and deep transfer learning","authors":"Jiale Li, Chenglong Yuan, Xuefei Wang, Guangqi Chen, Guowei Ma","doi":"10.1016/j.autcon.2024.105899","DOIUrl":"https://doi.org/10.1016/j.autcon.2024.105899","url":null,"abstract":"Computer vision models have shown great potential in pavement distress detection. There is still challenge of low robustness under different scenarios. The model robustness is enhanced with more annotated data. However, this approach is labor-intensive and not a sustainable long-term solution. This paper proposes a semi-supervised instance segmentation method for road distress detection based on deep transfer learning. The interactive segmentation method utilizing SAM are used to enhance the production efficiency of segmentation datasets. The DCNv3 and lightweight segmentation heads are strategically designed to offset potential speed losses. The deep transfer learning method fine-tunes the pre-trained models, enhancing their competency for new tasks. The proposed model achieves comparable performance to supervised learning with fewer annotated data, accurately determining crack dimensions across varied scenarios. This paper provides an efficient and practical approach for pavement distress identification using the hybrid computer vision methodology.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"3 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-11DOI: 10.1016/j.autcon.2024.105922
Jongwoo Cho, Jiyu Shin, Junyoung Jang, Tae Wan Kim
Construction sites are high-risk environments owing to the dynamic changes and improper placement of temporary facilities, requiring comprehensive safety management and spatial hazard analyses. Existing construction site layout planning (CSLP) studies have limitations in identifying hazardous zones and accommodating the flexibility stakeholders require. This paper introduces a site information model framework to define digital objects and relationships in the CSLP, proposing methods to identify automatically unsafe spaces by considering facility hazards and visibility. By establishing ontological relationships and developing algorithms to quantify risk in unoccupied spaces, the framework identifies unsafe spaces in alignment with the perceptions of safety practitioners. Case studies at four sites demonstrated the reliability of the framework with a high precision, recall, and an F1-score of 0.945. This framework allows safety practitioners to evaluate systematically and improve site layouts during the preconstruction phase. Future integration with scheduling information could enhance the spatiotemporal hazard analysis and contribute to safer construction sites.
{"title":"Automated identification of hazardous zones on construction sites using a 2D digital information model","authors":"Jongwoo Cho, Jiyu Shin, Junyoung Jang, Tae Wan Kim","doi":"10.1016/j.autcon.2024.105922","DOIUrl":"https://doi.org/10.1016/j.autcon.2024.105922","url":null,"abstract":"Construction sites are high-risk environments owing to the dynamic changes and improper placement of temporary facilities, requiring comprehensive safety management and spatial hazard analyses. Existing construction site layout planning (CSLP) studies have limitations in identifying hazardous zones and accommodating the flexibility stakeholders require. This paper introduces a site information model framework to define digital objects and relationships in the CSLP, proposing methods to identify automatically unsafe spaces by considering facility hazards and visibility. By establishing ontological relationships and developing algorithms to quantify risk in unoccupied spaces, the framework identifies unsafe spaces in alignment with the perceptions of safety practitioners. Case studies at four sites demonstrated the reliability of the framework with a high precision, recall, and an F1-score of 0.945. This framework allows safety practitioners to evaluate systematically and improve site layouts during the preconstruction phase. Future integration with scheduling information could enhance the spatiotemporal hazard analysis and contribute to safer construction sites.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"38 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816509","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
While existing floor tiling robots provide automated tiling for small tiles, robots designed for large and heavy tiles are rare. This paper develops a six-degree-of-freedom Stewart platform-based floor tiling robot for automated tiling of heavy tiles. The key contributions of this paper are: 1) establishing mechanical and kinematic models for a parallel robot to enhance the payload capacity of existing floor tiling robots. 2) designing a dual-camera system for precise visual alignment by capturing tile corner points from a complete perspective. Experimental validation demonstrated the robot's ability to automatically tile heavy floor tiles, with highly synchronized motions. The dual camera system achieved angle and distance deviations within ±0.001° and 0.5 mm. Quantitative analysis using the Borg RPE scale and EMG signals validated a reduction in physical strain. This research provides a feasible solution for automating heavy floor tile installation, effectively mitigating physical fatigue while enhancing the tiling alignment precision.
{"title":"Automated six-degree-of-freedom Stewart platform for heavy floor tiling","authors":"Siwei Chang, Zemin Lyu, Jinhua Chen, Tong Hu, Rui Feng, Haobo Liang","doi":"10.1016/j.autcon.2024.105932","DOIUrl":"https://doi.org/10.1016/j.autcon.2024.105932","url":null,"abstract":"While existing floor tiling robots provide automated tiling for small tiles, robots designed for large and heavy tiles are rare. This paper develops a six-degree-of-freedom Stewart platform-based floor tiling robot for automated tiling of heavy tiles. The key contributions of this paper are: 1) establishing mechanical and kinematic models for a parallel robot to enhance the payload capacity of existing floor tiling robots. 2) designing a dual-camera system for precise visual alignment by capturing tile corner points from a complete perspective. Experimental validation demonstrated the robot's ability to automatically tile heavy floor tiles, with highly synchronized motions. The dual camera system achieved angle and distance deviations within ±0.001° and 0.5 mm. Quantitative analysis using the Borg RPE scale and EMG signals validated a reduction in physical strain. This research provides a feasible solution for automating heavy floor tile installation, effectively mitigating physical fatigue while enhancing the tiling alignment precision.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"22 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816513","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-10DOI: 10.1016/j.autcon.2024.105897
Vito Getuli, Alessandro Bruttini, Farzad Rahimian
The adoption of Building Information Modeling (BIM) in construction site layout planning and activity scheduling faces challenges due to the lack of standardized approaches for digitally reproducing and organizing site elements that meet information requirements of diverse regulatory frameworks and stakeholders' use cases. This paper addresses the question of how to streamline the development of BIM objects for construction site modeling by proposing a vendor-neutral parametric design methodology and introduces a dedicated hierarchical structure for BIM object libraries to support users in their implementation. The methodology includes a six-step process for creating informative content, parametric geometries, and documentation, and is demonstrated through the development and implementation of a construction site BIM object library suitable for the Italian context. This approach fills a gap in BIM object development standards and offers a foundation for future research, benefiting practitioners and industry stakeholders involved in BIM-based site layout modeling and activity planning.
{"title":"Parametric design methodology for developing BIM object libraries in construction site modeling","authors":"Vito Getuli, Alessandro Bruttini, Farzad Rahimian","doi":"10.1016/j.autcon.2024.105897","DOIUrl":"https://doi.org/10.1016/j.autcon.2024.105897","url":null,"abstract":"The adoption of Building Information Modeling (BIM) in construction site layout planning and activity scheduling faces challenges due to the lack of standardized approaches for digitally reproducing and organizing site elements that meet information requirements of diverse regulatory frameworks and stakeholders' use cases. This paper addresses the question of how to streamline the development of BIM objects for construction site modeling by proposing a vendor-neutral parametric design methodology and introduces a dedicated hierarchical structure for BIM object libraries to support users in their implementation. The methodology includes a six-step process for creating informative content, parametric geometries, and documentation, and is demonstrated through the development and implementation of a construction site BIM object library suitable for the Italian context. This approach fills a gap in BIM object development standards and offers a foundation for future research, benefiting practitioners and industry stakeholders involved in BIM-based site layout modeling and activity planning.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"10 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-09DOI: 10.1016/j.autcon.2024.105903
Omar Habib, Mona Abouhamad, AbdElMoniem Bayoumi
Construction cost forecasting is vital for tendering processes, enabling the evaluation of bidding offers to maximize revenues and avoid losses. In recent years, the automation of this forecasting process has gained attention due to the limitations of traditional approaches that rely on human experts, which can lead to subjective judgments. This paper introduces an ensemble learning decision-support framework that combines regression random forests and gradient-boosting regression trees through regression voting to automate cost estimation for residential and commercial projects. Evaluation of this approach using the dataset from San Francisco’s building inspection department in the United States demonstrated significant performance improvements over support vector regression. This paper highlights the importance of automating construction cost forecasting with artificial intelligence techniques for construction companies and is expected to encourage companies and building inspection departments worldwide to publish more datasets for the application of advanced deep learning models.
{"title":"Ensemble learning framework for forecasting construction costs","authors":"Omar Habib, Mona Abouhamad, AbdElMoniem Bayoumi","doi":"10.1016/j.autcon.2024.105903","DOIUrl":"https://doi.org/10.1016/j.autcon.2024.105903","url":null,"abstract":"Construction cost forecasting is vital for tendering processes, enabling the evaluation of bidding offers to maximize revenues and avoid losses. In recent years, the automation of this forecasting process has gained attention due to the limitations of traditional approaches that rely on human experts, which can lead to subjective judgments. This paper introduces an ensemble learning decision-support framework that combines regression random forests and gradient-boosting regression trees through regression voting to automate cost estimation for residential and commercial projects. Evaluation of this approach using the dataset from San Francisco’s building inspection department in the United States demonstrated significant performance improvements over support vector regression. This paper highlights the importance of automating construction cost forecasting with artificial intelligence techniques for construction companies and is expected to encourage companies and building inspection departments worldwide to publish more datasets for the application of advanced deep learning models.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"86 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traditional construction management methodologies often fail to address unforeseen challenges and uncertainties. This paper highlights that projects can exist in different states, often unidentified by project managers. These varying states necessitate different approaches, indicating that one-size-fits-all methods are insufficient. Using project data, entropy calculations, and simulations within a Design Science Research methodology, this paper offers indicators for evaluating project states and improving decision-making. The application of ChaosCompass to eight real-world projects showed higher entropy in projects exceeding budgets and schedules, indicating greater disorder and unpredictability. Conversely, projects on budget and schedule displayed more controlled progress. The findings reveal a significant correlation between high entropy and low forecast accuracy, underscoring entropy's critical role in project dynamics. This paper advocates an entropy-based approach to construction management, promising a more resilient and adaptable framework to address modern project complexities.
{"title":"Entropy-centric framework for understanding and managing project dynamics in construction","authors":"Elyar Pourrahimian, Diana Salhab, Farook Hamzeh, Simaan AbouRizk","doi":"10.1016/j.autcon.2024.105928","DOIUrl":"https://doi.org/10.1016/j.autcon.2024.105928","url":null,"abstract":"Traditional construction management methodologies often fail to address unforeseen challenges and uncertainties. This paper highlights that projects can exist in different states, often unidentified by project managers. These varying states necessitate different approaches, indicating that one-size-fits-all methods are insufficient. Using project data, entropy calculations, and simulations within a Design Science Research methodology, this paper offers indicators for evaluating project states and improving decision-making. The application of ChaosCompass to eight real-world projects showed higher entropy in projects exceeding budgets and schedules, indicating greater disorder and unpredictability. Conversely, projects on budget and schedule displayed more controlled progress. The findings reveal a significant correlation between high entropy and low forecast accuracy, underscoring entropy's critical role in project dynamics. This paper advocates an entropy-based approach to construction management, promising a more resilient and adaptable framework to address modern project complexities.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"249 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Concealed pipeline maintenance in aging residential areas faces a key challenge of discrepancies between existing data and reality. Ground-penetrating radar with dense, high-speed 3D monitoring capabilities can provide massive data, but effective analysis is difficult due to the presence of irrelevant information. To accurately extract target information, this paper first proposes a 3D data array block concept, which enhances the feature relevance of target data blocks while expanding the data volume. An energy density window method is also proposed to enhance horizontal cross-sectional pipeline signals. Furthermore, a model named PR3DCNN for pipeline recognition is developed based on 3D convolutional neural networks and residual modules. Experimental results demonstrate that PR3DCNN has a classification accuracy of 0.871 for pipelines. After strengthening with 3D data array blocks and the energy density window, the PR-EDW-B model achieves an accuracy of 0.900, and can also classify the pipeline material and calculate its orientation.
{"title":"Intelligent enhancement and identification of pipeline hyperbolic signal in 3D ground penetrating radar data","authors":"Yonggang Shen, Guoxuan Ye, Tuqiao Zhang, Tingchao Yu, Yiping Zhang, Zhenwei Yu","doi":"10.1016/j.autcon.2024.105902","DOIUrl":"https://doi.org/10.1016/j.autcon.2024.105902","url":null,"abstract":"Concealed pipeline maintenance in aging residential areas faces a key challenge of discrepancies between existing data and reality. Ground-penetrating radar with dense, high-speed 3D monitoring capabilities can provide massive data, but effective analysis is difficult due to the presence of irrelevant information. To accurately extract target information, this paper first proposes a 3D data array block concept, which enhances the feature relevance of target data blocks while expanding the data volume. An energy density window method is also proposed to enhance horizontal cross-sectional pipeline signals. Furthermore, a model named PR3DCNN for pipeline recognition is developed based on 3D convolutional neural networks and residual modules. Experimental results demonstrate that PR3DCNN has a classification accuracy of 0.871 for pipelines. After strengthening with 3D data array blocks and the energy density window, the PR-EDW-B model achieves an accuracy of 0.900, and can also classify the pipeline material and calculate its orientation.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"29 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-06DOI: 10.1016/j.autcon.2024.105886
Guanlong Chen, Wenwen Dong, Zongwei Yao, Qiushi Bi, Xuefei Li
This paper introduces a bucket fill factor estimation method for earthmoving machinery aimed at solving sensor field-of-view blindness in measurements. Utilizing a point cloud repair technique, the method accurately reconstructs the 3D morphology of materials inside the bucket, even under occlusion conditions. The process begins by merging multiple frames of point cloud data to enhance information density. The material is then segmented from the comprehensive point cloud containing the bucket and other information. A repair strategy based on implicit surfaces reorganizes and fills holes in the point cloud. The Alpha Shape algorithm calculates the volume by using the filled point cloud. Extensive testing on loaders of different sizes proves the method’s robustness and shows significant accuracy improvements with the proposed data correction formula: 96.04% for small loaders and 95.36% for large loaders. Compared with existing volume estimation techniques, this method offers superior adaptability and reliability in real construction scenarios.
{"title":"Estimating bucket fill factor for loaders using point cloud hole repairing","authors":"Guanlong Chen, Wenwen Dong, Zongwei Yao, Qiushi Bi, Xuefei Li","doi":"10.1016/j.autcon.2024.105886","DOIUrl":"https://doi.org/10.1016/j.autcon.2024.105886","url":null,"abstract":"This paper introduces a bucket fill factor estimation method for earthmoving machinery aimed at solving sensor field-of-view blindness in measurements. Utilizing a point cloud repair technique, the method accurately reconstructs the 3D morphology of materials inside the bucket, even under occlusion conditions. The process begins by merging multiple frames of point cloud data to enhance information density. The material is then segmented from the comprehensive point cloud containing the bucket and other information. A repair strategy based on implicit surfaces reorganizes and fills holes in the point cloud. The Alpha Shape algorithm calculates the volume by using the filled point cloud. Extensive testing on loaders of different sizes proves the method’s robustness and shows significant accuracy improvements with the proposed data correction formula: 96.04% for small loaders and 95.36% for large loaders. Compared with existing volume estimation techniques, this method offers superior adaptability and reliability in real construction scenarios.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"8 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-06DOI: 10.1016/j.autcon.2024.105904
Min-Yuan Cheng, Quoc-Tuan Vu, Frederik Elly Gosal
Accurate estimation of construction costs and schedules is crucial for optimizing project planning and resource allocation. Most current approaches utilize traditional statistical analysis and machine learning techniques to process the vast amounts of data regularly generated in construction environments. However, these approaches do not adequately capture the intricate patterns in either time-dependent or time-independent data. Thus, a hybrid deep learning model (NN-BiGRU), combining Neural Network (NN) for time-independent and Bidirectional Gated Recurrent Unit (BiGRU) for time-dependent, was developed in this paper to estimate the final cost and schedule to completion of projects. The Optical Microscope Algorithm (OMA) was used to fine-tune the NN-BiGRU model (OMA-NN-BiGRU). The proposed model earned Reference Index (RI) values of 0.977 for construction costs and 0.932 for completion schedules. These findings underscore the potential of the OMA-NN-BiGRU model to provide highly accurate predictions, enabling stakeholders to make informed decisions that promote project efficiency and overall success.
{"title":"Hybrid deep learning model for accurate cost and schedule estimation in construction projects using sequential and non-sequential data","authors":"Min-Yuan Cheng, Quoc-Tuan Vu, Frederik Elly Gosal","doi":"10.1016/j.autcon.2024.105904","DOIUrl":"https://doi.org/10.1016/j.autcon.2024.105904","url":null,"abstract":"Accurate estimation of construction costs and schedules is crucial for optimizing project planning and resource allocation. Most current approaches utilize traditional statistical analysis and machine learning techniques to process the vast amounts of data regularly generated in construction environments. However, these approaches do not adequately capture the intricate patterns in either time-dependent or time-independent data. Thus, a hybrid deep learning model (NN-BiGRU), combining Neural Network (NN) for time-independent and Bidirectional Gated Recurrent Unit (BiGRU) for time-dependent, was developed in this paper to estimate the final cost and schedule to completion of projects. The Optical Microscope Algorithm (OMA) was used to fine-tune the NN-BiGRU model (OMA-NN-BiGRU). The proposed model earned Reference Index (RI) values of 0.977 for construction costs and 0.932 for completion schedules. These findings underscore the potential of the OMA-NN-BiGRU model to provide highly accurate predictions, enabling stakeholders to make informed decisions that promote project efficiency and overall success.","PeriodicalId":8660,"journal":{"name":"Automation in Construction","volume":"12 1","pages":""},"PeriodicalIF":10.3,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142816520","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：