Building information modeling (BIM) ?is an intelligent 3D design and modeling process that gives architects, engineers, construction and facility managers the ability and tools to plan, design, construct and manage buildings more effectively and efficiently. Currently, the construction progress is monitored by comparing the baseline project schedules, which include the planned dates and resources, with the actual dates in the updated schedules. 4D scheduling is used in the construction industry for linking individual model elements with the schedule activities to visualize the progress of construction activities. Also, it provides analyzing tools in the 3D environment to improve the efficiency of project management, such as earned value analysis, project critical path analysis, and analysis of resource allocation. However, the limitation of this approach is a need for the creation of a dedicated activity for monitoring each model element, which can result in an excessive number of activities. Similarly, the required volume of data limits the generation of a dedicated activity for multiple statuses of building elements, such as “testing an element,” and “inspecting an element’. This paper presents a construction progress visualization method, which uses a custom developed add-in to present the status of building elements (e.g., planned, installed) without linking them with the schedule. The new tool enables a visual presentation of the progress of each element within the BIM model during different stages of the construction process to increase the decision-making capabilities. A case study is used to demonstrate the capabilities of the developed BIM add-in tool for construction progress visualization.
{"title":"Construction progress visualisation for varied stages of the individual elements with BIM: A case study","authors":"Daniel Kazado, M. Kavgic, E. Ergen","doi":"10.35490/EC3.2019.172","DOIUrl":"https://doi.org/10.35490/EC3.2019.172","url":null,"abstract":"Building information modeling (BIM) ?is an intelligent 3D design and modeling process that gives architects, engineers, construction and facility managers the ability and tools to plan, design, construct and manage buildings more effectively and efficiently. Currently, the construction progress is monitored by comparing the baseline project schedules, which include the planned dates and resources, with the actual dates in the updated schedules. 4D scheduling is used in the construction industry for linking individual model elements with the schedule activities to visualize the progress of construction activities. Also, it provides analyzing tools in the 3D environment to improve the efficiency of project management, such as earned value analysis, project critical path analysis, and analysis of resource allocation. However, the limitation of this approach is a need for the creation of a dedicated activity for monitoring each model element, which can result in an excessive number of activities. Similarly, the required volume of data limits the generation of a dedicated activity for multiple statuses of building elements, such as “testing an element,” and “inspecting an element’. This paper presents a construction progress visualization method, which uses a custom developed add-in to present the status of building elements (e.g., planned, installed) without linking them with the schedule. The new tool enables a visual presentation of the progress of each element within the BIM model during different stages of the construction process to increase the decision-making capabilities. A case study is used to demonstrate the capabilities of the developed BIM add-in tool for construction progress visualization.","PeriodicalId":126601,"journal":{"name":"Proceedings of the 2019 European Conference on Computing in Construction","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129564351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The evolution of ICT and BIM systems in the construc- tion domain yield detailed views of buildings and their use throughout their lifespan. These systems also provide a structure around which information about buildings and their effect on surrounding infrastructure can be described in space and time. Thus, when aggregated, information provided by these systems can serve as a semantic structure through which other information can be stored and con- textualized. While bespoke systems have explored these approaches in particular contexts, few if any systems have been constructed to provide a flexible, semantically rich structure that can be used to structure information about any urban landscape at district and regional scales. This paper describes such a system. The Dynamic District Information Server (DDIS) provides a core information structure which can be extended to store as yet undefined information structures and allow these to be reasoned about in the contexts that range from neighbourhoods to regions. In addition, the paper describes how the DDIS can serve as a coordinating process in a tool chain by providing a semantically rich and flexible notification system that al- lows tools in the chain to notify one another when steps in some information process have been completed.
{"title":"Dynamic District Information Server: On the Use of W3C Linked Data Standards to Unify Construction Data","authors":"C. Hoare, Usman Ali, James O’Donnell","doi":"10.35490/EC3.2019.185","DOIUrl":"https://doi.org/10.35490/EC3.2019.185","url":null,"abstract":"The evolution of ICT and BIM systems in the construc- tion domain yield detailed views of buildings and their use throughout their lifespan. These systems also provide a structure around which information about buildings and their effect on surrounding infrastructure can be described in space and time. Thus, when aggregated, information provided by these systems can serve as a semantic structure through which other information can be stored and con- textualized. While bespoke systems have explored these approaches in particular contexts, few if any systems have been constructed to provide a flexible, semantically rich structure that can be used to structure information about any urban landscape at district and regional scales. This paper describes such a system. The Dynamic District Information Server (DDIS) provides a core information structure which can be extended to store as yet undefined information structures and allow these to be reasoned about in the contexts that range from neighbourhoods to regions. In addition, the paper describes how the DDIS can serve as a coordinating process in a tool chain by providing a semantically rich and flexible notification system that al- lows tools in the chain to notify one another when steps in some information process have been completed.","PeriodicalId":126601,"journal":{"name":"Proceedings of the 2019 European Conference on Computing in Construction","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126088099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As building energy management becomes a complicated process, traditional risk analysis is not adequate to address the management needs and advanced complex modelling techniques are required to handle the multi-dimensional synthesis of risks in the electricity systems. STPA (System-Theoretic Process Analysis) is a new hazard analysis technique using concepts of system and control theory. In this paper, the development of a risk management structure in the field of building energy management is presented. The hazard analysis process based on SafetyHAT information tool is applied for building operation 'accident' prevention, by illustrating the usage of the proposed tool. For this purpose, a case study considering a holistic energy management system in the tertiary building sector is examined.
随着建筑能源管理成为一个复杂的过程，传统的风险分析已不足以满足管理需求，需要先进的复杂建模技术来处理电力系统中的多维综合风险。系统理论过程分析(system - theoretical Process Analysis，简称STPA)是一种运用系统论和控制论概念的新型危害分析技术。本文介绍了建筑能源管理领域风险管理结构的发展。基于SafetyHAT信息工具的危害分析过程通过说明所建议工具的使用，应用于建筑操作“事故”预防。为此目的，考虑在第三建筑部门整体能源管理系统的案例研究进行了审查。
{"title":"Systems-theoretic process analysis (STPA) in building energy risk management","authors":"S. Karatzas, A. Chassiakos","doi":"10.35490/EC3.2019.183","DOIUrl":"https://doi.org/10.35490/EC3.2019.183","url":null,"abstract":"As building energy management becomes a complicated process, traditional risk analysis is not adequate to address the management needs and advanced complex modelling techniques are required to handle the multi-dimensional synthesis of risks in the electricity systems. STPA (System-Theoretic Process Analysis) is a new hazard analysis technique using concepts of system and control theory. In this paper, the development of a risk management structure in the field of building energy management is presented. The hazard analysis process based on SafetyHAT information tool is applied for building operation 'accident' prevention, by illustrating the usage of the proposed tool. For this purpose, a case study considering a holistic energy management system in the tertiary building sector is examined.","PeriodicalId":126601,"journal":{"name":"Proceedings of the 2019 European Conference on Computing in Construction","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130261259","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
It is proposed that the application of real-time monitoring technologies requires an integration and mutual adjustment of planning and control processes as well, for the automation to be effective. An approach for integrating planning, monitoring and control is presented, and demonstrated in examples of schedule and safety control. Similar solutions can also be developed in other domains. The introduction of automated monitoring technologies can thus lead to future research that will revolutionize planning and control processes, and construction management in general.
{"title":"What does \"real-time\" project control really mean?","authors":"S. Isaac","doi":"10.35490/EC3.2019.141","DOIUrl":"https://doi.org/10.35490/EC3.2019.141","url":null,"abstract":"It is proposed that the application of real-time monitoring technologies requires an integration and mutual adjustment of planning and control processes as well, for the automation to be effective. An approach for integrating planning, monitoring and control is presented, and demonstrated in examples of schedule and safety control. Similar solutions can also be developed in other domains. The introduction of automated monitoring technologies can thus lead to future research that will revolutionize planning and control processes, and construction management in general.","PeriodicalId":126601,"journal":{"name":"Proceedings of the 2019 European Conference on Computing in Construction","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130659241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Building Information Modelling (BIM) processes imply an intensive use of information. Nevertheless, several studies revealed critical issues in the data quality of information models. While some studies presented interesting works in the evaluation of model quality with reference to IFC. The analysis of the data quality issues in native models remains a research gap as well as the understanding of where these issues are generated. This research proposes an analysis of four information models to evaluate and classify data quality issues according to three dimensions, i.e. accuracy, coherence and completeness. Results highlighted user behaviours and/or technological limitations in real-world applications.
{"title":"Building information models are dirty","authors":"C. Mirarchi, A. Pavan","doi":"10.35490/EC3.2019.180","DOIUrl":"https://doi.org/10.35490/EC3.2019.180","url":null,"abstract":"Building Information Modelling (BIM) processes imply an intensive use of information. Nevertheless, several studies revealed critical issues in the data quality of information models. While some studies presented interesting works in the evaluation of model quality with reference to IFC. The analysis of the data quality issues in native models remains a research gap as well as the understanding of where these issues are generated. This research proposes an analysis of four information models to evaluate and classify data quality issues according to three dimensions, i.e. accuracy, coherence and completeness. Results highlighted user behaviours and/or technological limitations in real-world applications.","PeriodicalId":126601,"journal":{"name":"Proceedings of the 2019 European Conference on Computing in Construction","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128738197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Using Virtual Reality to model wayfinding behaviour","authors":"I. Ewart","doi":"10.35490/EC3.2019.210","DOIUrl":"https://doi.org/10.35490/EC3.2019.210","url":null,"abstract":"","PeriodicalId":126601,"journal":{"name":"Proceedings of the 2019 European Conference on Computing in Construction","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129385780","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Workforce health and safety (H&S) in the construction sector is a global concern. The construction sector has one of the highest fatal injury rates in both the developed and the developing world (Kassem et al., 2017). Efforts to improve the H&S performance in the construction sector are plentiful. However, until recently studies have mainly focused on H&S issues on the construction site. Facilities management and in particular the operation and maintenance of built assets has a much higher rate of injury and illness when compared to all other fields of employment (Wetzel and Thabet, 2018). More effort should be dedicated to address H&S risks at this stage. Safety learning and training, as a proactive strategy to improve the H&S performance of the construction sector, has received significant attention in recent years. Studies proposing new approaches for H&S learning and training have proposed a number of approaches that are characterized by a varying degree of 'virtualisation' ranging from pure reality, through augmented and mixed reality, to full virtual reality. While the degree of 'virtualisation' of the proposed approaches is an important variable to consider, the extent of 'personalisation' enabled by such approaches is key. Personalisation in learning and training refer to experiences which are tailored to the specific needs of the individual according the job role and to the specific characteristics of the context (company or otherwise) in which the individual is required to complete his/her tasks.This emerging trend is being driven by innovators on both the demand side (e.g. forward-looking clients and operators innovating in health H&S learning and training to meet ambitious H&S performance) and on the supply side (e.g. specialised learning and training providers, and technology providers). This paper presents the outcome from the first stage of a study aiming to develop an individualised training solution for the construction and facilities management (FM) domain.
建筑行业的劳动力健康和安全(H&S)是一个全球关注的问题。建筑业是发达国家和发展中国家致命伤害率最高的行业之一(Kassem et al.， 2017)。改善建筑行业卫生与安全绩效的努力很多。然而，直到最近，研究主要集中在建筑工地的卫生与安全问题。与所有其他就业领域相比，设施管理，特别是建筑资产的运营和维护，伤害和疾病的发生率要高得多(Wetzel和Thabet, 2018)。在这个阶段，应该投入更多的精力来解决健康与安全风险。安全学习和培训作为提高建筑行业健康安全绩效的积极策略，近年来受到了极大的关注。研究提出了H&S学习和培训的新方法，提出了许多以不同程度的“虚拟化”为特征的方法，从纯粹的现实到增强和混合现实，再到完全的虚拟现实。虽然所提出的方法的“虚拟化”程度是一个需要考虑的重要变量，但由这些方法实现的“个性化”程度是关键。学习和培训中的个性化是指根据个人的具体需求，根据个人需要完成其任务的环境(公司或其他)的具体特征量身定制的经验。这一新兴趋势是由需求方(例如，前瞻性客户和运营商在卫生与安全学习和培训方面进行创新，以实现雄心勃勃的卫生与安全绩效)和供应方(例如，专业学习和培训提供者以及技术提供者)的创新者推动的。本文介绍了一项旨在为建筑和设施管理(FM)领域开发个性化培训解决方案的研究的第一阶段的结果。
{"title":"Operation and and maintenance of built assets: A pathway towards individualised training experiences","authors":"James Wakefield, M. Kassem","doi":"10.35490/EC3.2019.237","DOIUrl":"https://doi.org/10.35490/EC3.2019.237","url":null,"abstract":"Workforce health and safety (H&S) in the construction sector is a global concern. The construction sector has one of the highest fatal injury rates in both the developed and the developing world (Kassem et al., 2017). Efforts to improve the H&S performance in the construction sector are plentiful. However, until recently studies have mainly focused on H&S issues on the construction site. Facilities management and in particular the operation and maintenance of built assets has a much higher rate of injury and illness when compared to all other fields of employment (Wetzel and Thabet, 2018). More effort should be dedicated to address H&S risks at this stage. Safety learning and training, as a proactive strategy to improve the H&S performance of the construction sector, has received significant attention in recent years. Studies proposing new approaches for H&S learning and training have proposed a number of approaches that are characterized by a varying degree of 'virtualisation' ranging from pure reality, through augmented and mixed reality, to full virtual reality. While the degree of 'virtualisation' of the proposed approaches is an important variable to consider, the extent of 'personalisation' enabled by such approaches is key. Personalisation in learning and training refer to experiences which are tailored to the specific needs of the individual according the job role and to the specific characteristics of the context (company or otherwise) in which the individual is required to complete his/her tasks.This emerging trend is being driven by innovators on both the demand side (e.g. forward-looking clients and operators innovating in health H&S learning and training to meet ambitious H&S performance) and on the supply side (e.g. specialised learning and training providers, and technology providers). This paper presents the outcome from the first stage of a study aiming to develop an individualised training solution for the construction and facilities management (FM) domain.","PeriodicalId":126601,"journal":{"name":"Proceedings of the 2019 European Conference on Computing in Construction","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123072064","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
I. Krystallis, E. Papadonikolaki, G. Locatelli, O. Iuorio
The adoption of Building Information Modelling (BIM) which offers integrated software and processes for digital delivery, is becoming imperative for the UK construction industry. Literature thus far is unclear if the benefits claimed by the industry are exaggerated for commercial reasons. Our exploratory study investigates how the benefits of adopting BIM can be quantified. The findings reported through a focus group of industry experts specialising in digital innovation offers a reality check at project/firm/sector level to scrutinize the benefits and costs of BIM. The key results offer four areas the construction sector could further investigate to report monetary benefits and costs of BIM. The study thus provides insight into how businesses can develop a robust but adaptable methodology for capturing BIM costs and benefits.
{"title":"Towards a methodology for quantifying the benefits of BIM","authors":"I. Krystallis, E. Papadonikolaki, G. Locatelli, O. Iuorio","doi":"10.35490/EC3.2019.138","DOIUrl":"https://doi.org/10.35490/EC3.2019.138","url":null,"abstract":"The adoption of Building Information Modelling \u0000(BIM) which offers integrated software and processes \u0000for digital delivery, is becoming imperative for the UK \u0000construction industry. Literature thus far is unclear if \u0000the benefits claimed by the industry are exaggerated \u0000for commercial reasons. Our exploratory study \u0000investigates how the benefits of adopting BIM can be \u0000quantified. The findings reported through a focus \u0000group of industry experts specialising in digital \u0000innovation offers a reality check at project/firm/sector \u0000level to scrutinize the benefits and costs of BIM. The \u0000key results offer four areas the construction sector \u0000could further investigate to report monetary benefits \u0000and costs of BIM. The study thus provides insight into \u0000how businesses can develop a robust but adaptable \u0000methodology for capturing BIM costs and benefits.","PeriodicalId":126601,"journal":{"name":"Proceedings of the 2019 European Conference on Computing in Construction","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124759318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Building information models of Mechanical, Electrical and Plumbing (MEP) systems are generally characterized by redundant information and a high density of components with irregular shapes. MEP information models, compared with those of other disciplines such architectural and structural, have (i) an extremely larger number of components, (ii) more complex and significant interrelations with other engineering domains, and (iii) more spatial constraints in general, especially when addressing design changes due to restrictions by other systems. Consequently, they require large storage spaces and are not conducive for exchange and interchange purposes. The geometric optimization of MEP information models can play a significant role in facilitating model exchange and handover by increasing the efficiency of their storage, transmission and display. To date, the body of knowledge on geometric optimization of MEP information models is still very limited. This paper aims to address this knowledge and technical gap as follows.
{"title":"Geometric optimization of mechanical electrical and plumbing (MEP) information models","authors":"Zhen-Zhong Hu, Shuang Yuan, M. Kassem","doi":"10.35490/EC3.2019.230","DOIUrl":"https://doi.org/10.35490/EC3.2019.230","url":null,"abstract":"Building information models of Mechanical, Electrical and Plumbing (MEP) systems are generally characterized by redundant information and a high density of components with irregular shapes. MEP information models, compared with those of other disciplines such architectural and structural, have (i) an extremely larger number of components, (ii) more complex and significant interrelations with other engineering domains, and (iii) more spatial constraints in general, especially when addressing design changes due to restrictions by other systems. Consequently, they require large storage spaces and are not conducive for exchange and interchange purposes. The geometric optimization of MEP information models can play a significant role in facilitating model exchange and handover by increasing the efficiency of their storage, transmission and display. To date, the body of knowledge on geometric optimization of MEP information models is still very limited. This paper aims to address this knowledge and technical gap as follows.","PeriodicalId":126601,"journal":{"name":"Proceedings of the 2019 European Conference on Computing in Construction","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124477999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nowadays, construction planning practices, whether conducted by human planners or artificial intelligence (AI) systems, rely heavily on manually elaborated descriptions of construction means and methods. As part of envisioning a new planning system that automatically learns construction knowledge from previous projects’ schedules, this paper introduces Part-of-Activity (POA) Tagging: a construction-specific word-category disambiguation method for decoding the constructional functionalities encoded in activity names. These functionalities represent the roles each token, i.e. word, in an activity name plays in understanding that activity from a construction point of view. The model is built using Bidirectional Long Short Term Memory Recurrent Neural Networks (BI-LSTM RNN). After training on a manually annotated dataset of more than 7000 activities, the model achieved a token accuracy of ~92%. The significance of this method lies in its ability to allow an AI System to decipher construction schedules. This schedule understanding opens the door for further applications such as the automated elaboration of weekly work plans and alignment of master schedules to weekly work plans.
{"title":"Automatic Understanding of Construction Schedules: Part-of-Activity Tagging","authors":"Fouad Amer, M. Golparvar-Fard","doi":"10.35490/EC3.2019.196","DOIUrl":"https://doi.org/10.35490/EC3.2019.196","url":null,"abstract":"Nowadays, construction planning practices, whether conducted by human planners or artificial intelligence (AI) systems, rely heavily on manually elaborated descriptions of construction means and methods. As part of envisioning a new planning system that automatically learns construction knowledge from previous projects’ schedules, this paper introduces Part-of-Activity (POA) Tagging: a construction-specific word-category disambiguation method for decoding the constructional functionalities encoded in activity names. These functionalities represent the roles each token, i.e. word, in an activity name plays in understanding that activity from a construction point of view. The model is built using Bidirectional Long Short Term Memory Recurrent Neural Networks (BI-LSTM RNN). After training on a manually annotated dataset of more than 7000 activities, the model achieved a token accuracy of ~92%. The significance of this method lies in its ability to allow an AI System to decipher construction schedules. This schedule understanding opens the door for further applications such as the automated elaboration of weekly work plans and alignment of master schedules to weekly work plans.","PeriodicalId":126601,"journal":{"name":"Proceedings of the 2019 European Conference on Computing in Construction","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121795318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","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：