Search results

This study aims to use regression Least-Square Support Vector Machine (LS-SVM) as a probabilistic model to determine the factor of safety (FS) and probability of failure (PF) of anisotropic soil slopes.

This research uses machine learning (ML) techniques to predict soil slope failure. Due to the lack of analytical solutions for measuring FS and PF, it is more convenient to use surrogate models like probabilistic modeling, which is suitable for performing repetitive calculations to compute the effect of uncertainty on the anisotropic soil slope stability. The study first uses the Limit Equilibrium Method (LEM) based on a probabilistic evaluation over the Latin Hypercube Sampling (LHS) technique for two anisotropic soil slope profiles to assess FS and PF. Then, using one of the supervised methods of ML named LS-SVM, the outcomes (FS and PF) were compared to evaluate the efficiency of the LS-SVM method in predicting the stability of such complex soil slope profiles.

This method increases the computational performance of low-probability analysis significantly. The compared results by FS-PF plots show that the proposed method is valuable for analyzing complex slopes under different probabilistic distributions. Accordingly, to obtain a precise estimate of slope stability, all layers must be included in the probabilistic modeling in the LS-SVM method.

Combining LS-SVM and LEM offers a unique and innovative approach to address the anisotropic behavior of soil slope stability analysis. The initiative part of this paper is to evaluate the stability of an anisotropic soil slope based on one ML method, the Least-Square Support Vector Machine (LS-SVM). The soil slope is defined as complex because there are uncertainties in the slope profile characteristics transformed to LS-SVM. Consequently, several input parameters are effective in finding FS and PF as output parameters.

This paper aims to present a predictive model approach to estimate the tensile behavior of polylactic acid (PLA) under uncertainty using the fused deposition modeling (FDM) and American Society for Testing and Materials (ASTM) D638’s Types I and II test standards.

The prediction approach combines artificial neural network (ANN) and finite element analysis (FEA), Monte Carlo simulation (MCS) and experimental testing for estimating tensile behavior for FDM considering uncertainties of input parameters. FEA with variance-based sensitivity analysis is used to quantify the impacts of uncertain variables, resulting in determining the significant variables for use in the ANN model. ANN surrogates FEA models of ASTM D638’s Types I and II standards to assess their prediction capabilities using MCS. The developed model is applied for testing the tensile behavior of PLA given probabilistic variables of geometry and material properties.

The results demonstrate that Type I is more appropriate than Type II for predicting tensile behavior under uncertainty. With a training accuracy of 98% and proven presence of overfitting, the tensile behavior can be successfully modeled using predictive methods that consider the probabilistic nature of input parameters. The proposed approach is generic and can be used for other testing standards, input parameters, materials and response variables.

Using the proposed predictive approach, to the best of the authors’ knowledge, the tensile behavior of PLA is predicted for the first time considering uncertainties of input parameters. Also, incorporating global sensitivity analysis for determining the most contributing parameters influencing the tensile behavior has not yet been studied for FDM. The use of only significant variables for FEA, ANN and MCS minimizes the computational effort, allowing to simulate more runs with reduced number of variables within acceptable time.

This study aims to review recent advances towards the implementation of ANN and NLP applications during the budgeting phase of the construction process. During this phase, construction companies must assess the scope of each task and map the client’s expectations to an internal database of tasks, resources and costs. Quantity surveyors carry out this assessment manually with little to no computer aid, within very austere time constraints, even though these results determine the company’s bid quality and are contractually binding.

This paper seeks to compile applications of machine learning (ML) and natural language processing in the architectural engineering and construction sector to find which methodologies can assist this assessment. The paper carries out a systematic literature review, following the preferred reporting items for systematic reviews and meta-analyses guidelines, to survey the main scientific contributions within the topic of text classification (TC) for budgeting in construction.

This work concludes that it is necessary to develop data sets that represent the variety of tasks in construction, achieve higher accuracy algorithms, widen the scope of their application and reduce the need for expert validation of the results. Although full automation is not within reach in the short term, TC algorithms can provide helpful support tools.

Given the increasing interest in ML for construction and recent developments, the findings disclosed in this paper contribute to the body of knowledge, provide a more automated perspective on budgeting in construction and break ground for further implementation of text-based ML in budgeting for construction.

Factors like bid price, submission time, and number of bidders influence the procurement process in public projects. These factors and the award criteria may impact the project’s financial compliance. Predicting budget compliance in construction projects has been traditionally challenging, but Machine Learning (ML) techniques have revolutionised estimations.

In this study, Portuguese Public Procurement Data (PPPData) was utilised as the model’s input. Notably, this dataset exhibited a substantial imbalance in the target feature. To address this issue, the study evaluated three distinct data balancing techniques: oversampling, undersampling, and the SMOTE method. Next, a comprehensive feature selection process was conducted, leading to the testing of five different algorithms for forecasting budget compliance. Finally, a secondary test was conducted, refining the features to include only those elements that procurement technicians can modify while also considering the two most accurate predictors identified in the previous test.

The findings indicate that employing the SMOTE method on the scraped data can achieve a balanced dataset. Furthermore, the results demonstrate that the Adam ANN algorithm outperformed others, boasting a precision rate of 68.1%.

The model can aid procurement technicians during the tendering phase by using historical data and analogous projects to predict performance.

Although the study reveals that ML algorithms cannot accurately predict budget compliance using procurement data, they can still provide project owners with insights into the most suitable criteria, aiding decision-making. Further research should assess the model’s impact and capacity within the procurement workflow.

Previous research predominantly focused on forecasting budgets by leveraging data from the private construction execution phase. While some investigations incorporated procurement data, this study distinguishes itself by using an imbalanced dataset and anticipating compliance rather than predicting budgetary figures. The model predicts budget compliance by analysing qualitative and quantitative characteristics of public project contracts. The research paper explores various model architectures and data treatment techniques to develop a model to assist the Client in tender definition.

This study addresses the gap in understanding text analytics within the service domain, focusing on new service development to provide insights into key research themes and trends in text analytics approaches to service development. It explores the benefits and challenges of implementing these approaches and identifies potential research opportunities for future service development. Importantly, this study offers insights to assist service providers to make data-driven decisions for developing new services and optimising existing ones.

This research introduces the hybrid thematic analysis with a systematic literature review (SLR-TA). It delves into the various aspects of text analytics in service development by analysing 124 research papers published from 2012 to 2023. This approach not only identifies key practical applications but also evaluates the benefits and difficulties of applying text analytics in this domain, thereby ensuring the reliability and validity of the findings.

The study highlights an increasing focus on text analytics within the service industry over the examined period. Using the SLR-TA approach, it identifies eight themes in previous studies and finds that “Service Quality” had the most research interest, comprising 42% of studies, while there was less emphasis on designing new services. The study categorises research into four types: Case, Concept, Tools and Implementation, with case studies comprising 68% of the total.

This study is groundbreaking in conducting a thorough and systematic analysis of a broad collection of articles. It provides a comprehensive view of text analytics approaches in the service sector, particularly in developing new services and service innovation. This study lays out distinct guidelines for future research and offers valuable insights to foster research recommendations.

The purpose of this study is to identify the causative factors of metro construction safety accidents, analyze the correlation between accidents and causative factors and assist in developing safety management strategies for improving safety performance in the context of the Chinese construction industry.

To achieve these objectives, 13 types and 48 causations were determined based on 274 construction safety accidents in China. Then, 204 cause-and-effect relationships among accidents and causations were identified based on data mining. Next, network theory was employed to develop and analyze the metro construction accident causation network (MCACN).

The topological characteristics of MCACN were obtained, it is both a small-world network and a scale-free network. Controlling critical causative factors can effectively control the occurrence of metro construction accidents. Degree centrality strategy is better than closeness centrality strategy and betweenness centrality strategy.

In practice, it is very difficult to quantitatively identify and determine the importance of different accidents and causative factors. The weights of nodes and edges are failed to be assigned when constructing MCACN.

This study provides a theoretical basis and feasible management reference for construction enterprises in China to control construction risks and reduce safety accidents. More safety resources should be allocated to control critical risks. It is recommended that safety managers implement degree centrality strategy when making safety-related decisions.

This paper establishes the MCACN model based on data mining and network theory, identifies the properties and clarifies the mechanism of metro construction accidents and causations.

Finite element (FE) analysis can be used for both design and verification of components. In the case of 3D-printed materials, a proper characterization of properties, accounting for anisotropy and raster angles, can help develop efficient material models. This study aims to use compression tests to characterize short carbon-reinforced PA12 made by fused filament fabrication (FFF) and to model its behaviour by the FE method.

In this work, the authors focus on compression tests, using post-processed specimens to overcome external defects introduced by the FFF process. The material’s elastoplastic mechanical behaviour is modelled by an elastic stiffness matrix, Hill’s anisotropic yield criterion and Voce’s isotropic hardening law, considering the stacking sequence of raster angles. A FE analysis is conducted to reproduce the material’s compressive behaviour through the LS-DYNA software.

The proposed model can capture stress values at different deformation levels and peculiar aspects of deformed shapes until the onset of damage mechanisms. Deformation and damage mechanisms are strictly correlated to orientation and raster angle.

The paper aims to contribute to the understanding of 3D-printed material’s behaviour through compression tests on bulk 3D-printed material. The methodology proposed, enriched with an anisotropic damage criterion, could be effectively used for design and verification purposes in the field of 3D-printed components through FE analysis.

This study draws on neoclassical and behavioural economics theories to provide an empirical insight into the effect of knowledge, costs, and social norms on damp-proofing residential buildings in Ghana.

This study used the quantitative approach involving survey data. A sample size of 242 participants was involved in the study. Applying principal component analysis on the responses from the participants, an index for damp-proofing, cost, knowledge, and social norms was derived. After generating the indexes, the ordinary least squares (OLS) regression was applied to estimate the impact of knowledge, costs, and social norms on damp-proofing.

The results from the OLS regression revealed that knowledge has a significant positive effect on damp-proofing while costs and social norms have significant negative effect on damp-proofing in Ghana. This study, therefore, concludes that although neoclassical economic factors such as knowledge and cost affect behaviour (damp-proofing), behavioural factors such as social norms also matter.

The outcome of this study calls for policymakers to consider putting in place measures that increase knowledge and promote the use of damp-proofing techniques during the construction of buildings. In addition, the study calls for scholars to partake in collaborative research amongst disciplines such as economics, psychology, and the construction industry in order to provide more innovative solutions, the key of which is finding innovative ways to damp proof buildings.

This study is original in its context as it draws on neoclassical and behavioural economics theories to provide an empirical insight into the effect of knowledge, costs, and social norms on damp-proofing of residential buildings in Ghana. This is an area that has received less attention in the areas of building biology and building pathology globally.

Experts may adjust their assessments through communication and mutual influence, and this dynamic evolution relies on the spread of internal trust relationships. Due to differences in educational backgrounds and knowledge experiences, trust relationships among experts are often incomplete. To address such issues and reduce decision biases, this paper proposes a probabilistic linguistic multi-attribute group decision consensus model based on an incomplete social trust network (InSTN).

In this paper, we first define the new trust propagation operators based on the operations of Probability Language Term Set (PLTS) with algebraic t-conorm and t-norm, which are combined with trust aggregation operators to estimate InSTN. The adjustment coefficients are then determined through trust relations to quantify their impact on expert evaluation. Finally, the particle swarm algorithm (PSO) is used to optimize the expert evaluation to meet the consensus threshold.

This study demonstrates the feasibility of the method through the selection of treatment plans for complex cases. The proposed consensus model exhibits greater robustness and effectiveness compared to traditional methods, mainly due to the effective regulation of trust relations in the decision-making process, which reduces decision bias and inconsistencies.

This paper introduces a novel probabilistic linguistic multi-attribute swarm decision consensus model based on an InSTN. It proposes a redefined trust propagation and aggregation approach to estimate the InSTN. Moreover, the computational efficiency and decision consensus accuracy of the proposed model are enhanced by using PSO optimization.

Recognizing the importance of Robo-advisors in digital financial services, this paper aims to analyse the users’ perception and acceptability of artificial intelligence (AI) in digital investment solutions using an extended “Technology Acceptance Model” (TAM).

The model is tested using 454 online valid responses received from Indian Fintech users via direct path analysis, mediation and moderation.

The study’s findings show that trust, perceived usefulness and perceived risk all significantly impact users’ attitudes towards Robo-advisors. In contrast, ease of use and social influence did not impact users’ attitudes statistically. Furthermore, the results indicate that their attitudes and ease of use influence users’ intentions to adopt Robo-advisors. Moreover, the moderation effect of gender partly supports the overall model. Specifically, in the path between attitudes and their antecedents, gender plays a role in influencing the relationships among these variables. This aligns with preliminary research in the field, providing additional insight into how gender may moderate the factors influencing users’ attitudes and intentions regarding Robo-advisory services.

This research study also reveals that trust, perceived risk, ease of use and demographic factors influence the adoption of Robo-advisory services. It is functional, but its sample selection is not probabilistic and overly emphasizes gender. Future research should use probabilistic sampling, other demographic factors and experience and situational factors. Also, it is necessary to examine how convenient and satisfying it is to communicate with service providers. Filling these gaps will improve the knowledge of consumer behaviour in the context of Fintech adoption and develop the current research.

This study posits that perceived usefulness, trust, perceived risk and ease of use remain core determinants of adopting Robo-advisory services. So, to improve the level of trust of users, it is necessary to develop security measures, data clarity and quality and customer support. Enhancing ease of use by incorporating better interface gestures is always beneficial for increasing the number of users and their level of satisfaction. As identified in previous studies, practical solutions will be achieved by pursuing the increased use of technology while leveraging AI for personal services and minimizing perceived risks, which will strengthen more advanced security measures as well as sufficiently clear communication.

The paper aims to extend the TAM by incorporating measures of trust and social influence to identify the factors that drive the adoption of Robo-advisors. In doing so, the paper may contribute to developing a more comprehensive understanding of the factors that shape consumers’ attitudes and intentions towards these technologies. Moreover, the paper appears to examine the moderating effect of gender on attitude and its predictors, which could provide insights into how gender characteristics may impact the adoption of Robo-advisors.