Purpose This paper aims to Test the capabilities/accuracies of four deep learning pre trained convolutional neural network (CNN) models to detect and classify types of highway cracks, as well as developing a new CNN model to maximize the accuracy at different learning rates. Design/methodology/approach A sample of 4,663 images of highway cracks were collected and classified into three categories of cracks, namely, “vertical cracks,” “horizontal and vertical cracks” and “diagonal cracks,” subsequently, using “Matlab” to classify the sample to training (70%) and testing (30%) to apply the four deep learning CNN models and compute their accuracies. After that, developing a new deep learning CNN model to maximize the accuracy of detecting and classifying highway cracks and testing the accuracy using three optimization algorithms at different learning rates. Findings The accuracies result of the four deep learning pre-trained models are above the averages between top-1 and top-5 and the accuracy of classifying and detecting the samples exceeded the top-5 accuracy for the pre-trained AlexNet model around 3% and by 0.2% for the GoogleNet model. The accurate model here is the GoogleNet model as the accuracy is 89.08% and it is higher than AlexNet by 1.26%. While the computed accuracy for the new created deep learning CNN model exceeded all pre-trained models by achieving 97.62% at a learning rate of 0.001 using Adam’s optimization algorithm. Practical implications The created deep learning CNN model will enable users (e.g. highway agencies) to scan a long highway and detect types of cracks accurately in a very short time compared to traditional approaches. Originality/value A new deep learning CNN-based highway cracks detection was developed based on testing four pre-trained CNN models and analyze the capabilities of each model to maximize the accuracy of the proposed CNN.
Purpose This study aims to present a comprehensive review, critical analysis and implications of the augmented reality (AR) application and implementation in the construction industry arena and demonstrate the gaps along with the future research agenda. Design/methodology/approach The construction industry has been under pressure to improve its productivity, quality and sustainability. However, the conventional methods and technologies cannot respond to this industry's ever-growing demands while emerging and innovative technologies such as building information modelling, artificial intelligence (AI), virtual reality (VR) and AR have emerged and can be used to address this gap. AR application has been acknowledged as one of the most impactful technologies in the construction digitalization process. However, a comprehensive understanding of the AR application, its areas of effectiveness and overarching implications in a construction project life cycle remain vague. Therefore, this study uses an integration of systematic literature review and thematic analysis techniques to identify the phases of a construction project life cycle in which AR is the most effective, the current issues and problems of the conventional methods, the augmented parameters, the immediate effects of using AR on each phase and, eventually, the overall influence of AR on the entire project. Nvivo qualitative data analysis software was used to code, categorize and create themes from the collected data. The result of data analysis was used to develop four principal frameworks of the AR applications – design and constructability review session; construction operation; construction assembly; and maintenance and defect inspection and management – and the gap analysis along with the future research agenda. Findings The findings of this study indicated that the application of AR can be most effective in the following four stages of a project life cycle: design and constructability review session; construction operation; construction assembly; and site management and maintenance, including site management and defect inspection. The results also showed that the application of AR technology in the construction industry can align and address building industry objectives by various elements such as: reducing project costs through the application of digital technologies, saving time, meeting deadlines and reduction in project delays through integrated, live scheduling and increased safety and quality of the construction work and workers. Research limitations/implications One of the main limitations of this study was the lack of materials and resources on the downfalls and shortcomings of using immersive technologies, AR, in the construction project life cycle. In addition, most of the reviewed papers were focused on the experiments with simulations and in the lab environment, rather than real experiments in real construction sites and projects. This may cause limitations and inaccuracy of the collected and reported data. Practical implications The results of this study indicated that the application of AR technology in construction industry can align and address building industry objectives by various elements such as: reducing project costs through the application of digital technologies; saving time; meeting deadlines and reduction in project delays through integrated, live scheduling; and increased safety and quality of the construction work and workers. Social implications Application of AR in the various stages of a project life cycle can increase the safety and quality of the construction work and workers. Originality/value The reviewed literature indicated that substantial research and studies are yet to be done, to demonstrate the full capacity and impact of these emerging technologies in the field. The collected data and literature indicate that amongst the digital technologies, AR is one of the least researched topics in the field. Therefore, this study aims to examine the application of AR in construction projects’ life cycle to identify the stages and practices of a project life cycle where AR and its capabilities can be exploited and to identify the respective problems and issues of the conventional methods and the ways in which AR can address those shortcomings. Furthermore, this study focuses on identifying the overall outcome of AR applications in a construction project in terms of cost and time efficiency, process precision and safety.
PurposeThe business benefits envisaged for BIM represent the main criteria for decision-making about BIM implementation – or shy away from BIM. Despite the significance, traditional evaluation techniques have difficulty to capture “the true value” of BIM from multiple levels and dimensions – as an effective evaluation method is supposed to. This study aims to identify the significant factors that affect BIM return on investment (ROI), develop an integrated model for companies and examine the influence of intangible returning factors of BIM on the rate of BIM implementation.Design/methodology/approachA cluster sampling technique was used; 92 questionnaires completed by Australian architecture, engineering and construction small- and medium-sized enterprises (SMEs) provided the basis to identify and analyse the key measurable returning factors, value drivers and strategic benefits associated with BIM ROI.FindingsApplying the PLS-SEM technique, findings reveal that a lack of reliable quantification methods for the ROI factors associated with BIM significantly affects the organisation's commitments to implement BIM. In essence, the failure to adequately identify and assess these benefits could result in the system not being appropriately implemented and supported by executive sponsors, who give priority to hard and tangible ROI measurements.Practical implicationsThe outcome of this study would be of direct appeal to policymakers, industry professionals and the academic community alike, in providing data-informed insight into the intersection between the implementation of BIM and the concept of ROI. Findings would provide a springboard for further research into using ROI factors to increase BIM implementation. Though the findings are directly applicable and contextualised for Australia, they provide lessons and offer a blueprint for similar studies in other countries and settings. That is, regardless of the context, findings raise awareness and provide a point of reference for the quantification of intangible returning factors rather than the tangible returning factors, as one of the first studies in its kind.Originality/valueThe study provides original insight in drawing attention to an untapped area for research in BIM implementation, namely BIM ROI. Apart from raising awareness around BIM ROI, the study is novel in providing a quantified model that establishes the links and level of impacts of various factors associated with BIM ROI. Findings of this study, particularly add value to the body of knowledge related to the business implications associated with BIM implementation in the context of Australian SMEs, while providing lessons for other countries and settings.
Objectives: GrandSchools is a new concept which co-locates retirement villages with secondary schools in one physical environment. Designed to enhance the health and well-being of both younger and older generations, this intergenerationalshared campus model promotes intergenerational inclusivity and active learning and living. In this paper, we explore stakeholder experts' perceptions of current opportunities and impediments to this proposed intergenerational learning and living model. Methods:A qualitative study reporting on findings from an industry seminar (n = 50) and key interviews (n = 10) from stakeholders in education, health, higher education, the management and operation of retirement villages, and design firms.Results: Three key themes summarised participants' assessment of the value, risks and what needs to change in order for intergenerational living and learning to become a reality. Conclusions:By bringing younger and older generations together in one shared campus location, GrandSchools is a novel idea to promote intergenerational inclusivity, enhancing the health and well-being of our whole community.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.