Search results

Accurate and rapid tracking and counting of building materials are crucial in managing on-site construction processes and evaluating their progress. Such processes are typically conducted by visual inspection, making them time-consuming and error prone. This paper aims to propose a video-based deep-learning approach to the automated detection and counting of building materials.

A framework for accurately counting building materials at indoor construction sites with low light levels was developed using state-of-the-art deep learning methods. An existing object-detection model, the You Only Look Once version 4 (YOLO v4) algorithm, was adapted to achieve rapid convergence and accurate detection of materials and site operatives. Then, DenseNet was deployed to recognise these objects. Finally, a material-counting module based on morphology operations and the Hough transform was applied to automatically count stacks of building materials.

The proposed approach was tested by counting site operatives and stacks of elevated floor tiles in video footage from a real indoor construction site. The proposed YOLO v4 object-detection system provided higher average accuracy within a shorter time than the traditional YOLO v4 approach.

The proposed framework makes it feasible to separately monitor stockpiled, installed and waste materials in low-light construction environments. The improved YOLO v4 detection method is superior to the current YOLO v4 approach and advances the existing object detection algorithm. This framework can potentially reduce the time required to track construction progress and count materials, thereby increasing the efficiency of work-in-progress evaluation. It also exhibits great potential for developing a more reliable system for monitoring construction materials and activities.

This study aims to enhance our understanding of employee emotional competence (EEC) in the context of service failure and recovery. Accordingly, the present study investigates the relationship between perceived EEC and customer emotional attachment (CEA) through the mediating role of service recovery satisfaction (RES). Furthermore, the study examines the moderating impact of service failure severity (SFS) on the relationship between perceived EEC and RES.

A self-administered online survey was carried out to collect data. Using a convenience sampling technique, 195 US consumers were recruited from Prolific Academic. To test the hypotheses, this study employed partial least squares structural equation modeling (PLS-SEM).

According to the analysis, perceived EEC impacts CEA directly and indirectly via RES. Additionally, the study finds that consumers reported feeling more emotionally connected to the restaurant when they were satisfied with service recovery. Finally, the study identified that the connection between perceived EEC and RES increases with service failure severity.

This study emphasizes enhancing EEC through organization-wide training to increase customer satisfaction and emotional attachment to the service organization. Furthermore, it underscores the need for comprehensive employee training to categorize service failure severity and formulate appropriate recovery strategies.

The authors believe this is the first RES study to examine perceived EEC’s effect on CEA. By combining the affect infusion and cognitive appraisal theories to examine recovery satisfaction, this study contributes to the existing body of research on service recovery by shedding light on the relationship between perceived EEC and CEA. Furthermore, the study offers preliminary findings indicating an increase in the impact of perceived EEC on RES during high failure severity (SFS).

This paper aims to identify modern construction techniques for affordable housing, such as prefabrication and interlocking systems, that can save time and cost while also providing long-term sustainable benefits that are desperately needed in today's construction industry.

The need for housing is growing worldwide, but traditional construction cannot cater to the demand due to insufficient time. There should be some paradigm shift in the construction industry to supply housing to society. This paper presented a state-of-the-art review of modern construction techniques practiced worldwide and their advantages in affordable housing construction by conducting a systematic literature review and applying the backward snowball technique. The paper reviews modern prefabrication techniques and interlocking systems such as modular construction, formwork systems, light gauge steel/cold form steel construction and sandwich panel construction, which have been globally well practiced. It was understood from the overview that modular construction, including modular steel construction and precast concrete construction, could reduce time and costs efficiently. Further enhancement in the quality was also noticed. Besides, it was observed that light gauge steel construction is a modern phase of steel that eases construction execution efficiently. Modern formwork systems such as Mivan (Aluminium Formwork) have been reported for their minimum construction time, which leads to faster construction than traditional formwork. However, the cost is subjected to the repetitions of the formwork. An interlocking system is an innovative approach to construction that uses bricks made of sustainable materials such as earth that conserve time and cost.

The study finds that the prefabrication techniques and interlocking system have a lot of unique attributes that can enable the modern construction sector to flourish. The study summarizes modern construction techniques that can save time and cost, enhancing the sustainability of construction practices, which is the need of the Indian construction industry in particular.

This study is limited to identifying specific modern construction techniques for time and cost savings, lean concepts and sustainability which are being practiced worldwide.

Modern formwork systems such as Mivan (Aluminium Formwork) have been reported for their minimum construction time which leads to faster construction than traditional formwork.

The need for housing is growing rapidly all over the world, but traditional construction cannot cater to the need due to insufficient time. There should be some paradigm shift in the construction industry to supply housing to society.

This study is unique in identifying specific modern construction techniques for time and cost savings, lean concepts and sustainability which are being practiced worldwide.

Given the growing emphasis among scholars, practitioners and policymakers on financial sustainability, this study aims to explore the applicability of machine learning techniques in predicting the financial performance of microfinance institutions (MFIs).

This study gathered 9,059 firm-year observations spanning from 2003 to 2018 from the World Bank's Mix Market database. To predict the financial performance of MFIs, the authors applied a range of machine learning regression approaches to both training and testing data sets. These included linear regression, partial least squares, linear regression with stepwise selection, elastic net, random forest, quantile random forest, Bayesian ridge regression, K-Nearest Neighbors and support vector regression. All models were implemented using Python.

The findings revealed the random forest model as the most suitable choice, outperforming the other models considered. The effectiveness of the random forest model varied depending on specific scenarios, particularly the balance between training and testing data set proportions. More importantly, the results identified operational self-sufficiency as the most critical factor influencing the financial performance of MFIs.

This study leveraged machine learning on a well-defined data set to identify the factors predicting the financial performance of MFIs. These insights offer valuable guidance for MFIs aiming to predict their long-term financial sustainability. Investors and donors can also use these findings to make informed decisions when selecting their potential recipients. Furthermore, practitioners and policymakers can use these findings to identify potential financial performance vulnerabilities.

This study stands out by using a global data set to investigate the best model for predicting the financial performance of MFIs, a relatively scarce subject in the existing microfinance literature. Moreover, it uses advanced machine learning techniques to gain a deeper understanding of the factors affecting the financial performance of MFIs.

This study addresses tourists' post-consumption perspectives on the impact of online destination experiences and animosity on travel decisions. Developing a framework based on the stimulus-organism-response (SOR) theory, we examine the previously unexplored relationship between post-negative events, online destination brand experience (ODBE), tourists' animosity and destination boycott intentions within the domestic tourism context.

Data from 355 actively engaged domestic travelers in Pakistan who follow destination social media pages (i.e. Instagram and Facebook) was analyzed using structural equation modeling.

The findings reveal that post-negative events ODBE significantly stimulate tourists' animosity, which in turn drives destination boycott intentions. The ODBE indirectly affects boycott intentions through animosity, acting as a partial mediator. The analysis highlights the significance of the users' prior experience levels (novice vs experienced). Multigroup analysis shows that novice visitors are more sensitive to negative online experiences, resulting in stronger animosity than experienced visitors. Animosity significantly drives boycott intentions, particularly among experienced visitors.

This study’s novelty lies in its comprehensive examination of post-negative events, focusing on how the ODBE influences tourists' negative emotions and boycott intentions. These findings offer valuable insights for tourism researchers and destination marketers, underscoring the importance of optimizing post-service failure ODBE strategies for brand repair, online reputation management, digital marketing innovation and customized service recovery to mitigate the impact of negative events.

With the use of increased number of measures and strategies towards mitigating operational carbon emissions, a greater emphasis has now been placed on reducing the resultant embodied carbon (EC). However, the assessment practice seems cumbersome due to variation in data and methodologies. To this end, this study aims to develop a basis that would facilitate early-stage EC assessment for a proposed building.

This study primarily involved a quantitative analysis of 50 Bill of Quantities (BOQs) of two-story house projects. Additional information such as materials, vehicle and plant and equipment used in construction was obtained from technical specifications, industry practiced norms and databases. The EC emission was calculated using basic statistics.

The total EC emission in the construction of a two-storey residential building is equivalent to 0.0607 tCO2e per square feet of Gross Internal Floor Area (GIFA). Concrete is the highest contributor in the material production with 36% of emission in the production stage that is responsible for 94% of total EC. The excavation and earthwork is the highest EC emitter during the material transportation stage (93% of total EC emission in transportation stage). During the construction stage, reinforcement shows the highest emission of 85% of total EC emission in construction. The study concludes that the distribution of carbon emission among elements contributes efficient resource allocation towards achieving sustainability in buildings.

This study provides a basis to forecast the EC emitted during cradle-to-end-of-construction stage of a proposed building. From the implication perspective, it is expected that the basis which the study provides would enable to determine the appropriate carbon tax to account the potential client for his contribution to GHGs.

The aim of this research is to conduct a systematic review of the literature on responsible artificial intelligence (RAI) practices within the domain of AI-based Credit Scoring (AICS) in banking. This review endeavours to map the existing landscape by identifying the work done so far, delineating the key themes and identifying the focal points of research within this field.

A database search of Scopus and Web of Science (last 20 years) resulted in 377 articles. This was further filtered for ABDC listing, and augmented with manual search. This resulted in a final list of 53 articles which was investigated further using the TCCM (Theory, Context, Characteristics and Methodology) review protocol.

The RAI landscape for credit scoring in the banking industry is multifaceted, encompassing ethical, operational and technological dimensions. The use of artificial intelligence (AI) in banking is widespread, aiming to enhance efficiency and improve customer experience. Based on the findings of the systematic literature review we found that past studies on AICS have revolved around four major themes: (a) Advances in AI technology; (b) Ethical considerations and fairness; (c) Operational challenges and limitations; and (d) Future directions and potential applications. The authors further propose future directions in RAI in credit scoring.

Earlier studies have focused on AI in banking, credit scoring in isolation. This review attempts to provide deeper insights, facilitating the development of this key field.

This study aims to determine the effect of replacing a portion of the cement in the concrete mixture with silica fume (SF) on the corrosion resistance of reinforcing bars, the compressive strength of concrete and the tensile strength of hook bars in both corroded and non-corroded external joints of structures. The external beam-column connection was studied because of its critical role in maintaining structural continuity in all three directions and providing resistance to rotation.

In external concrete joints, the bars at the end of the beams are often bent at 90° to form hooks that embed in columns. Owing to the importance of embedding distance and the need to understand its susceptibility to corrosion damage from chloride attack, a series of experiments were conducted on 12 specimens that accurately simulate real-site conditions in terms of dimensions, reinforcement and hook bars. SF was replaced with 10% and 15% of the weight of cement in the concrete mixture. To simulate corrosion, the specimens were subjected to accelerated corrosion in the laboratory by applying a low continuous current of 0.35 mA for 58 days.

The results revealed the effect of SF in improving the compressive strength of concrete, the pullout resistance of the hook bars and the corrosion resistance. In addition, it showed an apparent effect of the corrosion of reinforcing bars in reducing the bonding strength of hook bars with concrete and the effect of SF in improving this strength.

It was noted that the improvement of the results, achieved by replacing 10% of the weight of cement with SF, was significantly close to the results obtained by replacing 15% of the SF. It is recommended that an SF ratio of 10% be adopted to achieve the greatest economic savings.

The purpose of this paper is to examine the use of phragmites australis ash (PAA) in cementitious systems to achieve sustainable construction.

In this paper, the properties of mortar containing PAA as partial cement replacement are determined. The PAA is produced through slow burning in a closed system to minimize the CO₂ emission. A total of four mortar mixes are prepared with PAA replacement levels ranging from 0% to 30% by weight. The water to binder and the proportions of binder to sand are 0.55 and 1:3 by weight, respectively. The properties tested are density, compressive strength, flexural strength, ultrasonic pulse velocity, water absorption by total immersion and capillary rise. Testing is conducted at 1, 7, 28 and 90 days.

While there is a decrease in strength as the amount of PAA increases, there is strong indication of pozzolanic reaction in the presence of PAA. This is in agreement with the results reported by Salvo et al. (2015), where they found noticeable pozzolanic activities in the presence of straw ash, which is rich in SiO₂ and relatively high K₂O content. At 90 days of curing, there is a decrease of 5% in compressive strength at 10% PAA replacement. However, at 20% and 30% replacement, the reduction in compressive strength is 23% and 32%, respectively. The trend in flexural strength and ultrasonic pulse velocity is similar to that in compressive strength. The water absorption by total immersion and capillary rise tends to increase with increasing amounts of PAA in the mix. There seems to be a linear relationship between water absorption and compressive strength at each curing age.

The Phragmites australis plant used in this investigation is obtained from one location and this present a limitation as the type of soil may change the properties. Also one method of slow burning is used. Different burning methods may alter the composition of the PAA.

This outcome of this research will contribute towards sustainable development as it will make use of the waste generated, reduce the amount of energy-intensive cement used in construction and help generate local employment in the area where the Phragmites australis plant grows.

To the best knowledge of the authors, the ash from the Phragmites australis plant has not been used in cementitious system and this research can be considered original as it examines the properties of mortar containing PAA. Also, the process of burning in a closed system using this material.

The purpose of this study is to perform a numerical analysis of fiber-reinforced polymer (FRP) retrofitting in reinforced concrete (RC) joints at high temperatures and predict models using artificial neural networks (ANN). The aim was to gain insights into their structural behavior across a range of loading conditions from room temperature to 800°C. Additionally, the research assessed the efficiency of carbon fiber-reinforced polymer (CFRP), glass fiber reinforced polymer (GFRP) and aramid fiber reinforced polymer (AFRP) strengthening in enhancing the structural performance of the critical sections.

The linear numerical simulations were conducted to evaluate the performance of RC beam-column joints using finite element modelling (FEM) analysis. The ANN model demonstrated exceptional effectiveness in predicting the stiffness of frames with openings, establishing itself as the premier machine learning algorithm for frame stiffness estimation. In the conventional model, 300°C was proven to be an effective temperature approach. Subsequently, maintaining a constant temperature of 300°C, an in-depth analysis of nearly 30 models of three retrofitting techniques was conducted under thermomechanical loading.

The CFRP retrofits yielded 15% less deflection and 30% more stress than the remaining FRPs, and the ANN models predicted the deflection, main stresses, bending moment and shear force. The ANN model results were compared with those of other frequently used models. The R thresholds (R = 0.954, 0.981, 0.986, 0.968, 0.978 and 0.936) for training, testing and validation indicated that the ANN model achieved data variability. The findings indicate that the ANN model is more accurate because of the strong connection between the numerical model and the prediction.

To identify the pinpoint of critical segments within the rehabilitation section and determine the most effective wrapping method among the three laminates.