•Various strategies have been proposed for short-term building energy predictions.•Three inference approaches have been exploited for multi-step ahead predictions.•Advanced techniques have been ...utilized for the development of recurrent models.•Model performance is evaluated based on prediction accuracy and computation loads.•The results can provide valuable insights for developing deep recurrent models.
Accurate and reliable building energy predictions can bring significant benefits for energy conservations. With the development in smart buildings, massive amounts of building operational data are being collected and available for analysis. It is desired to develop big data-driven methods to fully realize the potential of building operational data in energy predictions. This paper investigates the usefulness of advanced recurrent neural network-based strategies for building energy predictions. Each strategy presents unique characteristics at two levels. At the high level, three inference approaches are used for generating short-term predictions, including the recursive approach, the direct approach and the multi-input and multi-output (MIMO) approach. At the low level, the state-of-the-art techniques are utilized for recurrent model development, such as the use of one-dimensional convolutional operations, bidirectional operations, and different types of recurrent units. The performance of different strategies has been assessed from different perspectives based on real building operational data. The research results help to bridge the knowledge gap between building professionals and advanced big data analytics. The insights obtained can be used as guidelines and references for developing advanced deep recurrent models for short-term building energy predictions.
The main disease that decreases the manufacturing of natural rubber is tapping panel dryness (TPD). To solve this problem faced by a large number of rubber trees, it is recommended to observe TPD ...images and make early diagnosis. Multi-level thresholding image segmentation can extract regions of interest from TPD images for improving the diagnosis process and increasing the efficiency. In this study, we investigate TPD image properties and enhance Otsu's approach. For a multi-level thresholding problem, we combine the snake optimizer with the improved Otsu's method and propose SO-Otsu. SO-Otsu is compared with five other methods: fruit fly optimization algorithm, sparrow search algorithm, grey wolf optimizer, whale optimization algorithm, Harris hawks optimization and the original Otsu's method. The performance of the SO-Otsu is measured using detail review and indicator reviews. According to experimental findings, SO-Otsu performs better than the competition in terms of running duration, detail effect and degree of fidelity. SO-Otsu is an efficient image segmentation method for TPD images.
With updated equipment and maturing technology, the applications of augmented and virtual reality (AR/VR) technologies in the architecture, engineering, and construction (AEC) industry are receiving ...increasing attention rapidly. Especially in education and training, an increasing number of researchers have started to implement AR/VR technologies to provide students or trainees with a visual, immersive, and interactive environment. In this article, a systematic review of AR/VR technologies for education and training in the AEC industry is conducted. First of all, through comprehensive analysis, 82 related studies are identified from two databases, namely Scopus and Web of Science. Secondly, the VOSviewer is used to analyze the current status of AR/VR for education and training in the AEC industry. Thirdly, the identified studies are classified into different categories according to their application domains by qualitative analysis. Fourthly, after a further filtering, 17 out of the 82 studies are included in the meta-analysis to quantify the actual impact of AR/VR. The results indicate that there are some limitations in the applications of AR/VR for education and training in the AEC industry. Finally, to further explore the reasons for the existence of limitations, the 82 studies are summarized to analyze the current challenges of AR/VR for education and training in the AEC industry. This study also provides insights into future trends in AR/VR for education and training in the AEC industry.
Psoriatic arthritis (PsA) is a chronic, systemic, immune-mediated inflammatory disease causing cutaneous and musculoskeletal inflammation that affects 25% of patients with psoriasis. Current methods ...for evaluating PsA disease activity are not accurate enough for precision medicine. A metabolomics-based approach can elucidate psoriatic disease pathogenesis, providing potential objective biomarkers. With the hypothesis that serum metabolites are associated with skin disease activity, we aimed to identify serum metabolites associated with skin activity in PsA patients. We obtained serum samples from patients with PsA (n = 150) who were classified into mild, moderate and high disease activity groups based on the Psoriasis Area Severity Index. We used solid-phase microextraction (SPME) for sample preparation, followed by data acquisition via an untargeted liquid chromatography—mass spectrometry (LC-MS) approach. Disease activity levels were predicted using identified metabolites and machine learning algorithms. Some metabolites tentatively identified include eicosanoids with anti- or pro-inflammatory properties, like 12-Hydroxyeicosatetraenoic acid, which was previously implicated in joint disease activity in PsA. Other metabolites of interest were associated with dysregulation of fatty acid metabolism and belonged to classes such as bile acids, oxidized phospholipids, and long-chain fatty acids. We have identified potential metabolites associated with skin disease activity in PsA patients.
As end-products of the intersection between the genome and environmental influences, metabolites represent a promising approach to the discovery of novel biomarkers for diseases. However, many ...potential biomarker candidates identified by metabolomics studies fail to progress beyond analytical validation for routine implementation in clinics. Awareness of the challenges present can facilitate the development and advancement of innovative strategies that allow improved and more efficient applications of metabolite-based markers in clinical settings. This minireview provides a comprehensive summary of the pre-analytical factors, required analytical validation studies, and kit development challenges that must be resolved before the successful translation of novel metabolite biomarkers originating from research. We discuss the necessity for strict protocols for sample collection, storage, and the regulatory requirements to be fulfilled for a bioanalytical method to be considered as analytically validated. We focus especially on the blood as a biological matrix and liquid chromatography coupled with tandem mass spectrometry as the analytical platform for biomarker validation. Furthermore, we examine the challenges of developing a commercially viable metabolomics kit for distribution. To bridge the gap between the research lab and clinical implementation and utility of relevant metabolites, the understanding of the translational challenges for a biomarker panel is crucial for more efficient development of metabolomics-based precision medicine.
Prefabricated steel box girders (SBGs) are widely adopted in bridge engineering due to their light weight and low lifecycle cost. To smoothly assemble SBG components on a construction site, it is ...necessary to inspect their geometric quality and ensure that all the as-is SBG components have the correct dimensions. However, the traditional inspection method is time-consuming and error-prone. This study developed a non-contact geometric quality assessment technique based on 3D laser scanning to accurately assess the locations and dimensions of SBG components. First, a robust normal-based region-growing algorithm was developed to divide the SBG components into segments with different labels. The scanned data related to the T ribs were then extracted through the proposed subtraction algorithm after the identification of the steel cabin. Lastly, the required items for geometric quality inspection were calculated based on the extracted as-is SBG components. The feasibility of the proposed geometric quality assessment method was validated through a real SBG project. Field test results showed that the developed inspection technique could assess the geometric quality of prefabricated SBG components in a more accurate and efficient manner compared to traditional measurement approaches.
Passive design of green buildings has three benefits: economy, ecology and society. At present, there is no authoritative definition of social benefits at home and abroad, so it is very difficult to ...evaluate and measure. Based on Maslow’s hierarchy of needs, economic and sociological theories, 5 first-level indicators and 20 second-level indicators of social benefit evaluation system for passive design of green buildings are obtained. In addition, the structural equation model was built by “AMOS” to analyze and compare these influencing factors. The research results showed that: Among the five latent variables, Environmental Effect is the most significant, followed by Sustainability, Economic Development Potential, Overall Measurement and People Oriented. And there is a significant positive impact between the latent variables. Among the secondary indicators, “Urban environment”, “Enterprise investment environment”, “Ecological environment policy”, “Industrial scale and openness” and “Thermal comfort” are the main influencing indicators. Finally, some suggestions were put forward to provide reference for the evaluation of social benefit of related projects in the future.
Reverse logistics (RL) is crucial for construction and demolition (C&D) waste management. In practice, information sharing (IS) is considered as an effective means to strengthen the coordination ...among stakeholders, so as to deliver in time, reduce costs, and address the mismatch between demand and supply of RL. However, the adoption of IS in RL of C&D waste is dissatisfactory due to various barriers, and these barriers inevitably affect each other. Furthermore, the interrelationships among barriers systematically affect the significance of each barrier in the adoption of IS because a particular barrier could present significant challenges to IS through its interrelationship with other barriers. Prior studies have explored strategies to remove these barriers, but few analyzed their complex interrelationships. To fill the gap, this study aims to identify the major barriers systematically and to analyze their hierarchical relationships by using interpretive structural modeling (ISM) and Matrice d’Impacts Croisés Multiplication Appliquée à un Classement (MICMAC). To start with, a total of 23 preliminary barriers were identified through relevant literatures. Then, 14 major barriers were screened out and the adjacency matrix was established through the feedback from the 11 experts. The corresponding reachability matrix was obtained with Python software, and a hierarchical structure was developed to further analysis. These major barriers were classified into multiple categories based on the calculation of driving power and dependence power. Meanwhile, the findings reveal that lack of certainty in market environment, lack of trust among stakeholders, and lack of government support are the three most important barriers negatively influencing the IS in RL of C&D waste. This study helps scholars understand the intricate relationships between barriers and also provides an effective way to combine ISM and MICMAC techniques. Also, it provides valuable references for project managers to understand the priorities of barriers and to allocate appropriate resources to mitigate the major barriers.
•Information sharing is crucial for the reverse logistics of construction and demolition.•Market environment, trust, and government support are crucial factors affecting the information sharing in reverse logistics.•Fourteen major barriers are structured in a hierarchy of four distinct levels.•Barrier importance is described from perspectives of driving and dependence power.
The explosive growth of green building (GB) research over the past few decades has posed great challenges for researchers to effectively grasp the holistic GB research status. This paper presents a ...text mining based method to identify the key research topics and trends from the existing abundant GB research publications. In total, 2421 articles are retrieved from the Web of Science core database. Subsequently, three mutually integrated text mining techniques, including the latent Dirichlet allocation (LDA) modeling, Word2vec, and community network analysis, are employed for knowledge discovery. Results show that the number of GB research topics increased from 1990 to 2020, while design optimization and energy efficient measures have always been the research hotspots. The identified research themes are further categorized into nine general research areas, including GB design, energy saving, GB rating system, life cycle evaluation, incentive and hindrances, post-occupancy evaluation, GB technologies, GB market, and management aspects of GB. Based on the revealed emerging research themes in recent ten years, three research directions are further proposed, such as green building market, employment of digital technologies, and safety risks in GB projects. This research provides an applicable quantitative method to efficiently identify the research topics from the extensive research publications and establishes a comprehensive knowledge framework of the GB research status at different stages.