Search results

The practice of artificial intelligence (AI) is increasingly being promoted by technology developers. However, its adoption rate is still reported as low in the construction industry due to a lack of expertise and the limited reliable applications for AI technology. Hence, this paper aims to present the detailed outcome of experimentations evaluating the applicability and the performance of AI object detection algorithms for construction modular object detection.

This paper provides a thorough evaluation of two deep learning algorithms for object detection, including the faster region-based convolutional neural network (faster RCNN) and single shot multi-box detector (SSD). Two types of metrics are also presented; first, the average recall and mean average precision by image pixels; second, the recall and precision by counting. To conduct the experiments using the selected algorithms, four infrastructure and building construction sites are chosen to collect the required data, including a total of 990 images of three different but common modular objects, including modular panels, safety barricades and site fences.

The results of the comprehensive evaluation of the algorithms show that the performance of faster RCNN and SSD depends on the context that detection occurs. Indeed, surrounding objects and the backgrounds of the objects affect the level of accuracy obtained from the AI analysis and may particularly effect precision and recall. The analysis of loss lines shows that the loss lines for selected objects depend on both their geometry and the image background. The results on selected objects show that faster RCNN offers higher accuracy than SSD for detection of selected objects.

The results show that modular object detection is crucial in construction for the achievement of the required information for project quality and safety objectives. The detection process can significantly improve monitoring object installation progress in an accurate and machine-based manner avoiding human errors. The results of this paper are limited to three construction sites, but future investigations can cover more tasks or objects from different construction sites in a fully automated manner.

This paper’s originality lies in offering new AI applications in modular construction, using a large first-hand data set collected from three construction sites. Furthermore, the paper presents the scientific evaluation results of implementing recent object detection algorithms across a set of extended metrics using the original training and validation data sets to improve the generalisability of the experimentation. This paper also provides the practitioners and scholars with a workflow on AI applications in the modular context and the first-hand referencing data.

Over the past two decades, the hub location domain has witnessed remarkable growth, yet no prior study reviewed and synthesised problem formulation and solution methodologies to address real-life challenges.

The current study conducts a comprehensive bibliometric literature review to develop a thematic framework that describes and presents hub location problems. The work employs cluster, bibliometric, and social network analyses to delve into the essential themes.

Key themes include cooperation, coopetition, sustainability, reshoring, and dynamic demand, contributing to the complex challenges in today’s hub location problems. As the first work in this field, the study serves as a valuable single-source reference, providing scholars and industry practitioners with key insights into the evolution of hub location research, prominent research clusters, influential authors, leading countries, and crucial keywords.

Findings have significant implications since they highlight the current state of hub location research and set the stage for future endeavours. Specifically, by identifying prominent research clusters, scholars can explore promising directions to push the boundaries of knowledge in this area.

This work is a valuable resource for scholars in this domain and offers practical insights for industry practitioners seeking to understand the hub location problems. Overall, the study’s holistic approach provides a solid foundation for advancing future research work in the hub location field.

One of the practical issues in the area of location and allocation is the location of the hub. In recent years, exchange rates have fluctuated sharply for a number of reasons such as sanctions against the country. Natural disasters that have occurred in recent years caused delays in hub servicing. The purpose of this study is to develop a mathematical programming model to minimize costs, maximize social responsibility and minimize fuel consumption so that in the event of a disruption in the main hub, the flow of materials can be directed to its backup hub to prevent delays in flow between nodes and disruptions in hubs.

A multi-objective mathematical programming model is developed considering uncertainty in some parameters, especially cost as fuzzy numbers. In addition, backup hubs are selected for each primary hub to deal with disruption and natural disasters and prevent delays. Then, a robust possibilistic method is proposed to deal with uncertainty. As the hub location-allocation problem is considered as NP-Hard problems so that exact methods cannot solve them in large sizes, two metaheuristic algorithms including a non-dominated sorting genetic algorithm non-dominated sorting genetic algorithm (NSGA-II) and multi-objective particle swarm optimization (MOPSO) are applied to tackle the problem.

Numerical results show the proposed model is valid. Also, they demonstrate that the NSGA-II algorithm outperforms the MOPSO algorithm.

The proposed model was implemented in one of the largest food companies in Iran, which has numerous products manufactured in different cities, to seek the hub locations. Also, due to several reasons such as road traffic and route type the difference in the rate of fuel consumption between nodes, this model helps managers and decision-makers to choose the best locations to have the least fuel consumption. Moreover, as the hub set up increases the employment rate in that city and has social benefits as it requires hiring some staff.

This paper investigates the hub location problem considering backup hubs with multiple objective functions to deal with disruption and uncertainty. Also, this study examines how non-hub nodes are assigned to hub nodes.

Since the first automated container terminal (ACT) was introduced at Europe Container Terminals Delta Terminal in Port Rotterdam back in the year 1992, a lot of research had been done to improve the management of ACT. However, up until recently, the number of literature available still appeared scarce. Hence, this paper aims to review the collection of literature about ACT to generate an exhaustive summary to answer the formulated review question in this study.

Preferred reporting items for systematic reviews and meta-analyses to narrow down the search parameters of literature retrieved so that only relevant articles were only selected. The systematic literature reviews were applied to analyse the content of the articles retrieved to determine its journal ranking, research findings and timeline of publications.

The adoption of ACT technology by container terminal operators could increase the terminal efficiency in productivity, cost reduction and environmental sustainability. Owing to global environmental awareness, the research trend of container terminal field and container terminal operator in the terminal design is much more environmentally friendly oriented.

The limited numbers of experts in the management of ACT are causing challenges in data collections.

The analysis of the global ACT trend could help academicians and industrial investors to review the revolution timeline of maritime technology in port and shipping that is happening rapidly.

The analysis of timeline and collective literature leads to the propose of the conceptual framework to determine the relationship between increased productivity, cost reduction and environmentally sustainable.