Search results

In response to the navigation challenges faced by coal mine tunnel inspection robots in semistructured underground intersection environments, many current studies rely on structured map-based planning algorithms and trajectory tracking techniques. However, this approach is highly dependent on the accuracy of the global map, which can lead to deviations from the predetermined route or collisions with obstacles. To improve the environmental adaptability and navigation precision of the robot, this paper aims to propose an adaptive navigation system based on a two-dimensional (2D) LiDAR.

Leveraging the geometric features of coal mine tunnel environments, the clustering and fitting algorithms are used to construct a geometric model within the navigation system. This not only reduces the complexity of the navigation system but also optimizes local positioning. By constructing a local potential field, there is no need for path-fitting planning, thus enhancing the robot’s adaptability in intersection environments. The feasibility of the algorithm principles is validated through MATLAB and robot operating system simulations in this paper.

The experiments demonstrate that this method enables autonomous driving and optimized positioning capabilities in harsh environments, with high real-time performance and environmental adaptability, achieving a positioning error rate of less than 3%.

This paper presents an adaptive navigation system for a coal mine tunnel inspection robot using a 2D LiDAR sensor. The system improves robot attitude estimation and motion control accuracy to ensure safe and reliable navigation, especially at tunnel intersections.

The environmental deterioration has become one of the most economically consequential and charged topics. Numerous scholars have examined the driving factors failing to consider the structural breaks. This study aims to explore sustainability using the per capita ecological footprints (EF) as an indicator of environmental adversities and controlling the resources rent [(natural resources (NR)], labor capital (LC), urbanization (UR) and per capita economic growth [gross domestic product (GDP)] of China.

Through the analysis of the long- and short-run effects with an autoregressive distributed lag model (ARDL), structural break based on BP test and Granger causality test based on vector error correction model (VECM), empirical evidence is provided for the policies formulation of sustainable development.

The long-run equilibrium between the EF and GDP, NR, UR and LC is proved. In the long run, an environmental Kuznets curve (EKC) relationship existed, but China is still in the rising stage of the curve; there is a positive relationship between the EF and NR, indicating a resource curse; the UR is also unsustainable. The LC is the most favorable factor for sustainable development. In the short term, only the lagged GDP has an inhibitory effect on the EF. Besides, all explanatory variables are Granger causes of the EF.

A novel attempt is made to examine the long-term equilibrium and short-term dynamics under the prerequisites that the structural break points with its time and frequencies were examined by BP test and ARDL and VECM framework and the validity of the EKC hypothesis is tested.

The defect detection problem of color-patterned fabric is still a huge challenge due to the lack of manual defect labeling samples. Recently, many fabric defect detection algorithms based on feature engineering and deep learning have been proposed, but these methods have overdetection or miss-detection problems because they cannot adapt to the complex patterns of color-patterned fabrics. The purpose of this paper is to propose a defect detection framework based on unsupervised adversarial learning for image reconstruction to solve the above problems.

The proposed framework consists of three parts: a generator, a discriminator and an image postprocessing module. The generator is able to extract the features of the image and then reconstruct the image. The discriminator can supervise the generator to repair defects in the samples to improve the quality of image reconstruction. The multidifference image postprocessing module is used to obtain the final detection results of color-patterned fabric defects.

The proposed framework is compared with state-of-the-art methods on the public dataset YDFID-1(Yarn-Dyed Fabric Image Dataset-version1). The proposed framework is also validated on several classes in the MvTec AD dataset. The experimental results of various patterns/classes on YDFID-1 and MvTecAD demonstrate the effectiveness and superiority of this method in fabric defect detection.

It provides an automatic defect detection solution that is convenient for engineering applications for the inspection process of the color-patterned fabric manufacturing industry. A public dataset is provided for academia.

This study aims to discover the factors which influence user satisfaction levels and their continuous use intention (CUI) of academic library social media, and then considers how to promote and improve further work on library social media to reduce user churn and increase user satisfaction.

An updated DeLone and McLean information systems success (D&M ISS) model and the expectation confirmation model for information systems continuance (ECM-ISC) with new variables of emotions are used to examine the factors which influence user satisfaction levels and CUI of academic library social media through 445 questionnaires. Partial least squares structural equation modelling was used to analyse the data and presented in tables.

The results show that information quality, system quality and emotions affect user satisfaction and CUI, and reveal that emotions can affect that most obviously.

The WeChat public platform is mainly used in China, so the study only focuses on Chinese academic libraries. There are still limitations on the settings of observed variables which cannot cover all the causes of users’ positive and negative emotions. In addition, although the respondents of this questionnaire can represent academic library users, 445 samples are still fairly low in contrast to the great number of academic library WeChat public platform users.

This study integrates ECM-ISC and D&M ISS models, adds positive and negative emotions as new variables, to broaden the application scope of these models, and demonstrates the applicability of these two models in the fields of researching academic library social media, expanding and deepening related theories above. This also provides practical reference for academic libraries on how to improve user satisfaction and CUI of academic library social media and academic library WeChat public platforms, promoting the development of academic library social media.

In prior literature, online endorsement system allowing the users to “like” or “dislike” shared information is found very useful in information filtering and trust elicitation in most social networks. This paper shows that such systems could fail in the context of investment communities due to several psychological biases.

This study develops a series of regression analyses to model the “like”/“dislike” voting process and whether or not such endorsement distinguishes between valuable information and noise. Trading simulations are also used to validate the practical implications of the findings.

The main findings of this research are twofold: (1) in the context of investment communities, online endorsement system fails to signify value-relevant information and (2) bullish information and “wisdom over the past event” information receive more “likes” and fewer “dislikes” on average, but they underperform in stock market price discovery.

This study demonstrates that biased endorsement may lead to the failure of the online endorsement system as information gatekeeper in investment communities. Two underlying mechanisms are proposed and tested. This study opens up new research opportunities to investigate the causes of biased endorsement in online environment and motivates the development of alternative information filtering systems.

Purchase conversion prediction aims to improve user experience and convert visitors into real buyers to drive sales of firms; however, the total conversion rate is low, especially for e-retailers. To date, little is known about how e-retailers can scientifically detect users' intents within a purchase conversion funnel during their ongoing sessions and strategically optimize real-time marketing tactics corresponding to dynamic intent states. This study mainly aims to detect a real-time state of the conversion funnel based on graph theory, which refers to a five-class classification problem in the overt real-time choice decisions (RTCDs)—click, tag-to-wishlist, add-to-cart, remove-from-cart and purchase—during an ongoing session.

The authors propose a novel graph-theoretic framework to detect different states of the conversion funnel by identifying a user's unobserved mindset revealed from their navigation process graph, namely clickstream graph. First, the raw clickstream data are identified into individual sessions based on a 30-min time-out heuristic approach. Then, the authors convert each session into a sequence of temporal item-level clickstream graphs and conduct a temporal graph feature engineering according to the basic, single-, dyadic- and triadic-node and global characteristics. Furthermore, the synthetic minority oversampling technique is adopted to address with the problem of classifying imbalanced data. Finally, the authors train and test the proposed approach with several popular artificial intelligence algorithms.

The graph-theoretic approach validates that users' latent intent states within the conversion funnel can be interpreted as time-varying natures of their online graph footprints. In particular, the experimental results indicate that the graph-theoretic feature-oriented models achieve a substantial improvement of over 27% in line with the macro-average and micro-average area under the precision-recall curve, as compared to the conventional ones. In addition, the top five informative graph features for RTCDs are found to be Transitivity, Edge, Node, Degree and Reciprocity. In view of interpretability, the basic, single-, dyadic- and triadic-node and global characteristics of clickstream graphs have their specific advantages.

The findings suggest that the temporal graph-theoretic approach can form an efficient and powerful AI-based real-time intent detecting decision-support system. Different levels of graph features have their specific interpretability on RTCDs from the perspectives of consumer behavior and psychology, which provides a theoretical basis for the design of computer information systems and the optimization of the ongoing session intervention or recommendation in e-commerce.

To the best of the authors' knowledge, this is the first study to apply clickstream graphs and real-time decision choices in conversion prediction and detection. Most studies have only meditated on a binary classification problem, while this study applies a graph-theoretic approach in a five-class classification problem. In addition, this study constructs temporal item-level graphs to represent the original structure of clickstream session data based on graph theory. The time-varying characteristics of the proposed approach enhance the performance of purchase conversion detection during an ongoing session.

Challenges associated with ensuring the accuracy and reliability of cost estimation of highway construction bid items are of significant interest to state highway transportation agencies. Even with the existing research undertaken on the subject, the problem of inaccurate estimation of highway bid items still exists. This paper aims to assess the accuracy of the cost estimation methods employed in the selected studies to provide insights into how well they perform empirically. Additionally, this research seeks to identify, synthesize and assess the impact of the factors affecting highway unit prices because they affect the total cost of highway construction costs.

This paper systematically searched, selected and reviewed 105 papers from Scopus, Google Scholar, American Society of Civil Engineers (ASCE), Transportation Research Board (TRB) and Science Direct (SD) on conceptual cost estimation of highway bid items. This study used content and nonparametric statistical analyses to determine research trends, identify, categorize the factors influencing highway unit prices and assess the combined performance of conceptual cost prediction models.

Findings from the trend analysis showed that between 1983 and 2019 North America, Asia, Europe and the Middle East contributed the most to improving highway cost estimation research. Aggregating the quantitative results and weighting the findings using each study's sample size revealed that the average error between the actual and the estimated project costs of Monte-Carlo simulation models (5.49%) performed better compared to the Bayesian model (5.95%), support vector machines (6.03%), case-based reasoning (11.69%), artificial neural networks (12.62%) and regression models (13.96%). This paper identified 41 factors and was grouped into three categories, namely: (1) factors relating to project characteristics; (2) organizational factors and (3) estimate factors based on the common classification used in the selected papers. The mean ranking analysis showed that most of the selected papers used project-specific factors more when estimating highway construction bid items than the other factors.

This paper contributes to the body of knowledge by analyzing and comparing the performance of highway cost estimation models, identifying and categorizing a comprehensive list of cost drivers to stimulate future studies in improving highway construction cost estimates.

This paper aims to analyse the current state of research to identify the link between Lean Manufacturing and Industry 4.0 (I4.0) technologies to map out different research themes, to uncover research gaps and propose key recommendations for future research, including lessons to be learnt from the integration of lean and I4.0.

A systematic literature review (SLR) is conducted to thematically analyse and synthesise existing literature on Lean Manufacturing–I4.0 integration. The review analysed 60 papers in peer-reviewed journals.

In total, five main research themes were identified, and a thematic map was created to explore the following: the relationship between Lean Manufacturing and I4.0; Lean Manufacturing and I4.0 implication on performance; Lean Manufacturing and I4.0 framework; Lean Manufacturing and I4.0 integration with other methodologies; and application of I4.0 technologies in Lean Manufacturing. Furthermore, various gaps in the literature were identified, and key recommendations for future directions were proposed.

The integration of Lean Manufacturing and I4.0 will eventually bring many benefits and offers superior and long-term competitive advantages. This research reveals the need for more analysis to thoroughly examine how this can be achieved in real life and promote operational changes that ensure enterprises run more sustainably.

The development of Lean Manufacturing and I4.0 integration is still in its infancy, with most articles in this field published in the past two years. The five main research themes identified through thematic synthesis are provided in the original contribution. This provides scholars better insight into the existing literature related to Lean Manufacturing and I4.0, further contributing to defining clear topics for future research opportunities. It also has important implications for industrialists, who can develop more profound and richer knowledge than Lean and I4.0, which would, in turn, help them develop more effective deployment strategies and have a positive commercial impact.

This study aims to explore the relationship between experience layoffs and employees’ work engagement. Drawing on the psychological contract theory, we examine the parallel mediating role of cognitive and affective job insecurity, along with the moderating role of perceived organisational support.

The hypotheses were tested based on data collected from 737 employees of companies in various industries in China in an online survey.

The results showed the significant effect of experiencing layoffs on employees’ work engagement through cognitive and affective job insecurity, and the effect was stronger when perceived organisational support was lower. The moderated mediation effect mainly occurred through affective job insecurity but not cognitive job insecurity.

This study deepens the understanding of the mechanism of the negative effect of experiencing layoffs and the boundaries of its impact from a psychological contract breach perspective. By analysing the mediating role of cognitive and affective job insecurity, we have enhanced our understanding of the exchange-based mechanism of employees after experiencing layoffs. By examining the moderating role of perceived organisational support, we reveal the important role of supportive behaviours of organisations in mitigating the negative effects of experiencing layoffs.

During the forming process, aluminum alloy sheets develop various types of textures and are subjected to cyclic loading as structural components, resulting in fatigue damage. This study aims to develop polycrystalline models with different orientation distributions and incorporate suitable fatigue indicator parameters to investigate the effect of orientation distribution on the mechanical properties of Al-7.02Mg-1.78Zn alloys under cyclic loading.

In this study, a two-dimensional polycrystalline model with 150 equiaxed grains was constructed based on optical microscope images. Subsequently, six different orientation distributions were assigned to this model. The fatigue indicator parameter of strain energy dissipation is utilized to analyze the stress response and fatigue crack driving force in polycrystalline models with different orientation distributions subjected to cyclic loading.

The study found that orientation distribution significantly influences fatigue crack initiation. Orientation distributions with a larger average Schmid factor exhibit reduced stress response and lower fatigue indicator parameters. Locations with a larger average Schmid factor experience greater plastic deformation and present a higher risk for fatigue crack initiation. RVE with a single orientation undergoes more rotation to reach cyclic steady state under cyclic loading due to the ease of deformation transfer.

Currently, there are no reports in the literature on the calculation of fatigue crack initiation for Al-Mg-Zn alloys using the crystal plasticity finite element method. This study presents a novel strategy for simulating the response of Al-7.02Mg-1.78Zn materials with different orientation distributions under symmetric strain cyclic loading, providing valuable references for future research.