Search results

Prediction models are essential tools for transportation agencies to forecast the condition of bridge decks based on available data, and artificial intelligence is paramount for this purpose. This study aims at proposing a bridge deck condition prediction model by assessing various classification and regression algorithms.

The 2019 National Bridge Inventory database is considered for model development. Eight different feature selection techniques, along with their mean and frequency, are used to identify the critical features influencing deck condition ratings. Thereafter, four regression and four classification algorithms are applied to predict condition ratings based on the selected features, and their performances are evaluated and compared with respect to the mean absolute error (MAE).

Classification algorithms outperform regression algorithms in predicting deck condition ratings. Due to its minimal MAE (0.369), the random forest classifier with eleven features is recommended as the preferred condition prediction model. The identified dominant features are superstructure condition, age, structural evaluation, substructure condition, inventory rating, maximum span length, deck area, average daily traffic, operating rating, deck width, and the number of spans.

The proposed bridge deck condition prediction model offers a valuable tool for transportation agencies to plan maintenance and resource allocation efficiently, ultimately improving bridge safety and serviceability.

This study provides a detailed framework for applying machine learning in bridge condition prediction that applies to any bridge inventory database. Moreover, it uses a comprehensive dataset encompassing an entire region, broadening the model’s applicability and representation.

Bridge deterioration is a critical risk to public safety, which mandates regular inspection and maintenance to ensure sustainable transport services. Many models have been developed to aid in understanding deterioration patterns and in planning maintenance actions and fund allocation. This study aims at developing a deep-learning model to predict the deterioration of concrete bridge decks.

Three long short-term memory (LSTM) models are formulated to predict the condition rating of bridge decks, namely vanilla LSTM (vLSTM), stacked LSTM (sLSTM), and convolutional neural networks combined with LSTM (CNN-LSTM). The models are developed by utilising the National Bridge Inventory (NBI) datasets spanning from 2001 to 2019 to predict the deck condition ratings in 2021.

Results reveal that all three models have accuracies of 90% and above, with mean squared errors (MSE) between 0.81 and 0.103. Moreover, CNN-LSTM has the best performance, achieving an accuracy of 93%, coefficient of correlation of 0.91, R2 value of 0.83, and MSE of 0.081.

The study used the NBI bridge inventory databases to develop the bridge deterioration models. Future studies can extend the model to other bridge databases and other applications in the construction industry.

This study provides a detailed and extensive data cleansing process to address the shortcomings in the NBI database. This research presents a framework for implementing artificial intelligence-based models to enhance maintenance planning and a guideline for utilising the NBI or other bridge inventory databases to develop accurate bridge deterioration models. Future studies can extend the model to other bridge databases and other applications in the construction industry.

Implementing the 17 Sustainable Development Goals (SDGs) unarguably demands huge financial investments. However, the United Nations has acknowledged the huge financial gap militating against the implementation of the SDGs worldwide, leading experts to question the possibility of complete implementation of the goals by their terminal dateline of 2030. While the bulk of the finance currently outlaid on the SDGs comes from traditional sources including foreign direct investments (FDIs), there is the need to focus more attention on developing and exploiting impact investments that are more suitable for financing development programmes and projects. In this chapter, the SDG implementation profiles of the 12 Arab West Asia countries concerning the five most targeted SDGs were evaluated and sustainable finance issues were discussed. Secondary data were retrieved from World Bank's DataBank. The data were descriptively analyzed. Based on the profiles generated, debt relief is put forward as a possible impact investment mechanism suitable for funding the SDGs. Specifically, this chapter recommends that outright cancellation of debts based on the debt-for-SGD swap could serve as some of the impact investments needed to boost the global drive for a developed, peaceful, and just world.

This study has conducted exploratory research to understand who should comprise the members of a resilient supply chain for promoting an entrepreneurial ecosystem of a startup project and to determine the mechanisms for the balanced coexistence of all stakeholders. This is necessary to ensure mutual benefits for all stakeholders, each of whom has multidimensional interests. Additionally, this supply chain must be able to withstand any potential disruption risks.

This research has employed a mixed-design approach. In this context, the study conducted an extensive qualitative and quantitative investigation, including 30 interviews and a survey involving 180 potential stakeholders in this supply network, respectively in the capital city of Bangladesh, Dhaka. The analysis of the interviews utilized principles of matrix thinking, while structural equation modeling (SEM) through LISREL was employed to understand cause-and-effect relationships.

Network, platform and governance—these three independent constructs have the potential to contribute to the dependent construct, a resilient supply chain, aimed at promoting an entrepreneurial ecosystem for startup projects. It has been revealed that the management of such projects depends on the rules and regulations within the ecosystem. An excellent governance mechanism is essential for this purpose. To facilitate coexistence, the establishment of a platform is crucial, where cooperation among all members is mandatory.

For practitioners, three distinctive but closely interdependent issues are explored and resolved in this philanthropic study. It has unfolded the elements of any startup project with essential settings.

The identification of the structural dynamics of potential stakeholders within the entrepreneurial ecosystem of startups is largely absent in existing literature. Therefore, there is a need to comprehensively investigate the entire network, including their roles, responsibilities and associations. This study makes a significant and novel contribution to the existing literature. Academics and practitioners alike have ample opportunities to learn from this new aspect of relationships across three distinct areas: the entrepreneurial ecosystem, startup projects and the development of a resilient supply chain.

This paper covers the development of a novel defect model for concrete highway bridges. The proposed defect model is intended to facilitate the identification of bridge’s condition information (i.e. defects), improve the efficiency and accuracy of bridge inspections by supporting practitioners and even machines with digitalised expert knowledge, and ultimately automate the process.

The research design consists of three major phases so as to (1) categorise common defect with regard to physical entities (i.e. bridge element), (2) establish internal relationships among those defects and (3) relate defects to their properties and potential causes. A mixed-method research approach, which includes a comprehensive literature review, focus groups and case studies, was employed to develop and validate the proposed defect model.

The data collected through the literature and focus groups were analysed and knowledge were extracted to form the novel defect model. The defect model was then validated and further calibrated through case study. Inspection reports of nearly 300 bridges in China were collected and analysed. The study uncovered the relationships between defects and a variety of inspection-related elements and represented in the form of an accessible, digitalised and user-friendly knowledge model.

The contribution of this paper is the development of a defect model that can assist inexperienced practitioners and even machines in the near future to conduct inspection tasks. For one, the proposed defect model can standardise the data collection process of bridge inspection, including the identification of defects and documentation of their vital properties, paving the path for the automation in subsequent stages (e.g. condition evaluation). For another, by retrieving rich experience and expert knowledge which have long been reserved and inherited in the industrial sector, the inspection efficiency and accuracy can be considerably improved.

The objective of this study is to examine how emotions play a role in the firm’s reaction to disruptions in the supply chain. Drawing on the upper echelons theory, we evaluate whether managers’ perception of collective emotions (CEs) in the supply environment affects the execution of specific organisational responses (bridging and buffering) to disruptive events. Furthermore, we investigate to what extent companies' own capabilities, such as supply chain resilience, influence this relationship.

A web-based survey was distributed among managers involved in supply chain relationship management (e.g. supply chain or purchasing managers). LinkedIn was used to identify and contact adequate respondents, and 221 valid responses were collected. The proposed theoretical model was empirically tested using structural equation modelling based on partial least squares (PLS-SEM).

Results suggest that emotions can shape a firm's response to supply chain disruptions. In fact, managers are more likely to pursue both bridging and buffering strategies as their perception of CEs increases. However, the intensity and underlying motivations for pursuing each strategy differ.

When CEs are perceived by buyer managers, stronger supply chain resilience incentivises the choice of cooperative practices within existing suppliers, thereby reinforcing pre-existing links. We conclude that combining companies' inherent variables or capabilities with managerial cognition and perceptions can improve our understanding of decision-making processes and buyer–supplier relationships.

Retirement is a preparation for transitioning from one role to another and transitioning to a new stage of life. The deepening aging of the population encourages the policymakers to start the Bridge Employment plan when the society faces the unprecedented challenges of decreasing labor supply, heavier burdens of retirement and slow economic growth. The purpose of this study, the decision model for Bridge Employment has been developed by systematically reviewing the research literature.

A bibliometric analysis was conducted to cover publications on Bridge Employment for Return to Work published from 1994 to 2023, including a total of 1,936 publications collected from the Web of Science and Scopus. The patterns and trends in terms of sources of publications, intellectual structure and major topics were analyzed.

After carefully examining the results of the selected studies, three categories of individual (micro level), organizational (medium level) and contextual (macro level) factors were identified as effective factors on bridge employment and model development. Each of the mentioned factors, along with the legal, financial, managerial, educational-administrative and consulting requirements, form the basis for the development of the model and decision framework for Paul’s employment.

This model can be a basis as a framework for bridge recruitment planning so that organizations can once again use their skills–knowledge–expertise in different jobs and even training younger people.

The work on bridge resilience assessment includes quantitative and qualitative approaches to compare the multiple bridges based on their resilience. But still, the bridge resilience obtained by these assessment approaches is inefficient when prioritising multiple bridges to improve their resilience. Therefore, this study aims to develop a methodology for prioritising the bridges to improve their resilience.

The research methodology follows three sequential phases. In the first phase, criteria importance through intercriteria correlation (CRITIC) technique is used to compute the criteria weights. The criteria considered are age, area, design high flood level, finish road level FRL and resilience index of bridges. While 12 river-crossing bridges maintained by one bridge owner are considered as alternatives. Then, in the second phase, the prioritisation of each bridge is evaluated using five techniques, including technique for order of preference by similarity to ideal solution, VIKOR (in Serbian, Visekriterijumska Optimizacija I Kompromisno Resenje), additive ratio assessment, complex proportional assessment and multi-objective optimisation method by ratio analysis. Finally, in the third phase, the results of all five techniques are integrated using CRITIC and the weighted sum method.

The result of the study enables bridge owners to deal with the particular bridge that requires resilience improvement. The study concluded that it is not enough to consider only the bridge resilience index to improve its resilience. The prioritisation exercise should consider various other criteria that are not preferred during the bridge resilience assessment process.

The proposed methodology is a novel framework based on the existing multi-criteria decision-making (MCDM) techniques for contributing knowledge in the domain of bridge resilience management. It can efficiently overcome the pitfall of decision-making when two bridges have the same resilience index score.

This systematic literature review aims to investigate the application and integration of Industry 4.0 (I4.0) technologies in transportation infrastructure construction projects focusing on sustainability pillars.

The study employs a systematic literature review approach, combining qualitative review and quantitative analysis of 142 academic articles published between 2011 and March 2023.

The findings reveal the dominance of Building Information Modelling (BIM) as a central tool for sustainability assessment, while other technologies such as blockchain and autonomous robotics have received limited attention. The adoption of I4.0 technologies, including Internet of Things (IoT) sensors, Augmented Reality (AR), and Big Data, has been prevalent for data-driven analyses, while Unmanned Aerial Vehicle (UAVs) and 3D printing are mainly being integrated either with BIM or in synergy with Artificial Intelligence (AI). We pinpoint critical challenges including high adoption costs, technical barriers, lack of interoperability, and the absence of standardized sustainability benchmarks.

This research distinguishes itself by not only mapping the current integration of I4.0 technologies but also by advocating for standardization and a synergistic human-technology collaborative approach. It offers tailored strategic pathways for diverse types of transportation infrastructure and different project phases, aiming to significantly enhance operational efficiency and sustainability. The study sets a new agenda for leveraging cutting-edge technologies to meet ambitious future sustainability and efficiency goals, making a compelling case for rethinking how these technologies are applied in the construction sector.