Search results

The purpose of this study is to identify the factors that influence the willingness of Saudi Arabian students from four universities in Saudi Arabia, to adopt learning management systems (LMSs). This will be accomplished by using two popular technology acceptance models unified theory of acceptance and use of technology (UTAUT) and theory of planned behavior (TPB).

In total, 445 undergraduates from four Saudi educational institutions participate in filling out the study questionnaire. To investigate the correlations between the variables, the study used structural equation modeling for data analysis.

The results of the study show that effort expectancy (EE), subjective norm (SN), attitude toward behavior (ATB) and perceived behavioral control (PBC) are found to be substantially connected with their intentions to use (ITU) LMSs. The findings also show that there is a strong relationship between students’ intentions and their actual use of LMSs.

Like many studies, this research has some limitations. The primary limitation is that the findings of the study cannot be extrapolated to other settings since the report’s analysis and investigation were limited to four Saudi universities. Therefore, to generalize the study’s findings, similar research needs to be conducted in other Gulf and similar cultural universities.

The integrated model identifies key factors that influence the intent of Saudi Arabian students to use LMS, including EEs, social influence, ATB and PBC. This model can help develop solutions for the obstacles that prevent students from using LMS. The findings can be used to provide assistance to increase the likelihood of LMS acceptance as part of the educational experience. The model may also inspire further research on this topic in the Gulf nations, particularly in Saudi Arabia.

As none of the relevant studies conducted previously in Saudi Arabia has integrated the two models to study the students’ ITU LMSs, this study combines two major theories, TPB and UTAUT, in the context of Saudi Arabia, contributing to the field of technology use in education by expanding empirical research and providing a thorough understanding of the challenges associated with the use of LMS in Saudi universities. This study should be viewed as filling a crucial gap in the field. Moreover, this integrated model, using more than one theoretical perspective, brings a thorough comprehension of the barriers that hinder students’ adoption of LMSs in the academic context in Saudi Arabia and thus assists in making effective decisions and reaching viable solutions.

A rise in productivity is associated with higher profits, competitiveness and the sustainability of an industry and a nation. Recent studies highlight inadequate labour supervision and training facilities as the main causes of productivity-related challenges among construction enterprises. This study aims to evaluate the construction supervisors' capabilities in applying the required elements of work practices for enhancing the performance and productivity of construction operations using a case study.

A new construction supervisory training programme was developed through comprehensive sequential processes, and 64 construction supervisors underwent training . Marking guides with different levels of descriptions/standards were developed through consultations with experts and literature reviews, and the supervisors' capabilities were assessed under 64 competency elements of 12 competency units.

The findings show a clear cross-section of all the required competencies of construction supervisors with various levels of standards/descriptions, leading to a new generalised guideline that helps to comprehend what degrees of skills can be taken into account in supervision attributes. Statistical tests and expert reviews were used to ensure the generalisability of the research applications and the reliability of the results.

Despite the study findings being limited to the Sri Lankan construction industry, its applicability could create considerable impacts on the current/future practices of the construction sector in developing countries as well as other developing industries.

The study adds new characteristics and values to construction supervision practices that can be remarkable in encouraging construction supervision to drive the sustainability of construction practices. The study findings are significant in decision-making/planning procedures related to technical comprehension, industry training, scientific documentation, adherence to workforce employment constraints and job outputs. This paper describes the further extensive implications and future scopes of the study elaborately.

This study addresses the knowledge gap in the industry related to the development of protocols and application methodologies necessary to track their performance. The study opens a new window that inflows knowledge attributes to the industry sector along with the necessary comparison of the relevant competency elements to predict/comprehend what levels of capabilities can be theoretically considered and practically applied in supervision characteristics.

Errors are increasingly recognized as beneficial to the learning process and are more frequently integrated into training curriculums. Despite this growing interest, the work carried out so far offers little evidence highlighting the psychological qualities implicit in learning from error. By focussing on the role of specific trainee’s attributes [i.e. learning goal orientation (LGO) motivation to learn and metacognition], this study aims to better understand the reasons why some trainees benefit more (than others) from being confronted with errors during training.

A total of 142 trainees took part in this study by participating in a training on interviewing techniques that also exposed them to various committable errors, and by completing questionnaires at two different times (i.e. before and after training).

Results of bootstrap regression analysis highlights three main findings: LGO is positively linked to learning from errors; a significant portion of the link between LGO and learning from error is explained by motivation to learn and metacognition; and these effects are presented in the form of a double-mediated model which suggests two different explanatory pathways (i.e. motivational and cognitive).

To the best of the authors’ knowledge, this study is among the first to offer insight on the psychological attributes influencing learning from errors and to bring forward the role of two underlying mechanism that are linked to this specific type of learning. It also invites researchers and practitioners to reflect on the best ways to make use of errors in training and promote the value of personal attributes on trainees’ learning experience.

This paper provides practical advice for archaeologists and heritage specialists wishing to use ML approaches to identify archaeological features in high-resolution satellite imagery (or other remotely sensed data sources). We seek to balance the disproportionately optimistic literature related to the application of ML to archaeological prospection through a discussion of limitations, challenges and other difficulties. We further seek to raise awareness among researchers of the time, effort, expertise and resources necessary to implement ML successfully, so that they can make an informed choice between ML and manual inspection approaches.

Automated object detection has been the holy grail of archaeological remote sensing for the last two decades. Machine learning (ML) models have proven able to detect uniform features across a consistent background, but more variegated imagery remains a challenge. We set out to detect burial mounds in satellite imagery from a diverse landscape in Central Bulgaria using a pre-trained Convolutional Neural Network (CNN) plus additional but low-touch training to improve performance. Training was accomplished using MOUND/NOT MOUND cutouts, and the model assessed arbitrary tiles of the same size from the image. Results were assessed using field data.

Validation of results against field data showed that self-reported success rates were misleadingly high, and that the model was misidentifying most features. Setting an identification threshold at 60% probability, and noting that we used an approach where the CNN assessed tiles of a fixed size, tile-based false negative rates were 95–96%, false positive rates were 87–95% of tagged tiles, while true positives were only 5–13%. Counterintuitively, the model provided with training data selected for highly visible mounds (rather than all mounds) performed worse. Development of the model, meanwhile, required approximately 135 person-hours of work.

Our attempt to deploy a pre-trained CNN demonstrates the limitations of this approach when it is used to detect varied features of different sizes within a heterogeneous landscape that contains confounding natural and modern features, such as roads, forests and field boundaries. The model has detected incidental features rather than the mounds themselves, making external validation with field data an essential part of CNN workflows. Correcting the model would require refining the training data as well as adopting different approaches to model choice and execution, raising the computational requirements beyond the level of most cultural heritage practitioners.

Improving the pre-trained model’s performance would require considerable time and resources, on top of the time already invested. The degree of manual intervention required – particularly around the subsetting and annotation of training data – is so significant that it raises the question of whether it would be more efficient to identify all of the mounds manually, either through brute-force inspection by experts or by crowdsourcing the analysis to trained – or even untrained – volunteers. Researchers and heritage specialists seeking efficient methods for extracting features from remotely sensed data should weigh the costs and benefits of ML versus manual approaches carefully.

Our literature review indicates that use of artificial intelligence (AI) and ML approaches to archaeological prospection have grown exponentially in the past decade, approaching adoption levels associated with “crossing the chasm” from innovators and early adopters to the majority of researchers. The literature itself, however, is overwhelmingly positive, reflecting some combination of publication bias and a rhetoric of unconditional success. This paper presents the failure of a good-faith attempt to utilise these approaches as a counterbalance and cautionary tale to potential adopters of the technology. Early-majority adopters may find ML difficult to implement effectively in real-life scenarios.

Unlike many high-profile reports from well-funded projects, our paper represents a serious but modestly resourced attempt to apply an ML approach to archaeological remote sensing, using techniques like transfer learning that are promoted as solutions to time and cost problems associated with, e.g. annotating and manipulating training data. While the majority of articles uncritically promote ML, or only discuss how challenges were overcome, our paper investigates how – despite reasonable self-reported scores – the model failed to locate the target features when compared to field data. We also present time, expertise and resourcing requirements, a rarity in ML-for-archaeology publications.

The purpose of this paper is to highlight the key technical challenges that derive from the recently proposed European Artificial Intelligence Act and specifically, to investigate the applicability of the requirements that the AI Act mandates to high-risk AI systems from the perspective of AI security.

This paper presents the main points of the proposed AI Act, with emphasis on the compliance requirements of high-risk systems. It matches known AI security threats with the relevant technical requirements, it demonstrates the impact that these security threats can have to the AI Act technical requirements and evaluates the applicability of these requirements based on the effectiveness of the existing security protection measures. Finally, the paper highlights the necessity for an integrated framework for AI system evaluation.

The findings of the EU AI Act technical assessment highlight the gap between the proposed requirements and the available AI security countermeasures as well as the necessity for an AI security evaluation framework.

AI Act, high-risk AI systems, security threats, security countermeasures.

This study aims to examine the relationships among structured-on-the job training (ST), mentoring, job rotation and the work environment factors on tacit knowledge transfer from training.

This study used quantitative research techniques to examine the causal relationships among the key study variables. A questionnaire-based survey has developed to evaluate the research model by drawing a convenience sample includes 239 employees working in the Arab Potash Company located in Jordan. Surveyed data were examined following the structural equation modeling procedures.

The results revealed that adapting of the ST, mentoring and job rotation in industrial firms had direct effect on the employees’ abilities to learn and transfer tacit knowledge from training to the actual work, and how these learning strategies strengthen employees’ abilities in solving work problems, improving customers’ satisfaction and quality of products and services. As well as, it affirmed the strong direct effect of work environment factors such as supervisor and peer support on the employees’ abilities to learning and transferring tacit knowledge to their jobs. However, this study showed that work environment factors have no significant mediating role on the relationship among ST, mentoring, job rotation and the employees’ abilities to learn and transfer tacit knowledge to their jobs.

The study results are opening the doors for future studies to examine the relationships among the methods of training and learning in the workplace, the work environment factors and tacit knowledge transfer from training to the jobs as prerequisites for improving the employees and organization performance. These results would be validated by conducting future research, examining larger samples of industrial companies to give more accurate data and clear explanations to the relationships among the study variables. It also suggests to replace the characteristics of work environment (supervisor support and peer support) by trainees’ characteristics (self-efficacy and career commitment) to give a better understanding to the relationships among the key study variables.

With regard to improving the employees’ competency while doing their jobs, this study developed a conceptual framework that guides managers to recognize the importance of ST, mentoring and job rotation in increasing the employees’ learning together; and giving them the chance to use the new learned experiences and knowledge to improve the organization performance and its competitive advantage. This study helps managers build a positive work environment that encourages social interaction, respect and mutual interest among employees, and increases their sense of responsibility for learning and transferring skills and knowledge to the jobs.

The training methods in the workplace go beyond immediate work performance to act as a promising tool make employees’ learning more easily and faster, and help them to transfer and retain new skills and knowledge, adapt with changing environments, build stronger relationships with stakeholders and at the same time, make the organizations ensure that employees comply with their societal goals.

The authors have noticed that large portions of the studies on training and human resources development neglected the role effect of (ST, mentoring and job rotation) on the tacit knowledge transfer from training to the jobs. Hence, these gaps in researches have motivated to develop a theoretical model that helps to examine the relationship between the two constructs. This study also suggests to examine the mediating role effects of work environment factors on the relationships among (ST, mentoring and job rotation) and tacit knowledge transfer, as well as it extends to examine the mediating role of work environment factors on transferring knowledge to jobs, attributed to the demographic variables such as gender, age, work experience and education level.

Crack detection of pavement is a critical task in the periodic survey. Efficient, effective and consistent tracking of the road conditions by identifying and locating crack contributes to establishing an appropriate road maintenance and repair strategy from the promptly informed managers but still remaining a significant challenge. This research seeks to propose practical solutions for targeting the automatic crack detection from images with efficient productivity and cost-effectiveness, thereby improving the pavement performance.

This research applies a novel deep learning method named TransUnet for crack detection, which is structured based on Transformer, combined with convolutional neural networks as encoder by leveraging a global self-attention mechanism to better extract features for enhancing automatic identification. Afterward, the detected cracks are used to quantify morphological features from five indicators, such as length, mean width, maximum width, area and ratio. Those analyses can provide valuable information for engineers to assess the pavement condition with efficient productivity.

In the training process, the TransUnet is fed by a crack dataset generated by the data augmentation with a resolution of 224 × 224 pixels. Subsequently, a test set containing 80 new images is used for crack detection task based on the best selected TransUnet with a learning rate of 0.01 and a batch size of 1, achieving an accuracy of 0.8927, a precision of 0.8813, a recall of 0.8904, an F1-measure and dice of 0.8813, and a Mean Intersection over Union of 0.8082, respectively. Comparisons with several state-of-the-art methods indicate that the developed approach in this research outperforms with greater efficiency and higher reliability.

The developed approach combines TransUnet with an integrated quantification algorithm for crack detection and quantification, performing excellently in terms of comparisons and evaluation metrics, which can provide solutions with potentially serving as the basis for an automated, cost-effective pavement condition assessment scheme.

Since stock return and volatility matters to investors, this study proposes to incorporate the textual sentiment of annual reports in stock price crash risk prediction.

Specific sentences gathered from management discussions and their subsequent analyses are tokenized and transformed into numeric vectors using textual mining techniques, and then the Naïve Bayes method is applied to score the sentiment, which is used as an input variable for crash risk prediction. The results are compared between a collection of predictive models, including linear regression (LR) and machine learning techniques.

The experimental results find that those predictive models that incorporate textual sentiment significantly outperform the baseline models with only accounting and market variables included. These conclusions hold when crash risk is proxied by either the negative skewness of the return distribution or down-to-up volatility (DUVOL).

It should be noted that the authors' study focuses on examining the predictive power of textual sentiment in crash risk prediction, while other dimensions of textual features such as readability and thematic contents are not considered. More analysis is needed to explore the predictive power of textual features from various dimensions, with the most recent sample data included in future studies.

The authors' study provides implications for the information value of textual data in financial analysis and risk management. It suggests that the soft information contained within annual reports may prove informative in crash risk prediction, and the incorporation of textual sentiment provides an incremental improvement in overall predictive performance.

Studies highlight that poor labour supervision and inadequate labour training facilities are the primary factors that result in labour skill shortages and productivity-related challenges among construction firms. This study aims to assess the construction supervisors’ abilities in providing work-based training elements and evaluating labour skills in construction.

A construction supervisory training programme was newly designed with a set of labour training exercises using comprehensive approaches. A total of 64 construction supervisors were trained to deliver the labour training components for more than 250 labourers working on 23 construction projects in Sri Lanka. The supervisors’ competencies were assessed using a detailed marking guide developed through expert discussions and literature reviews.

The results show the detailed cross-section of a wide range of competencies of the construction supervisors in providing labour training elements with the levels of standards/descriptions. The generalisability of the study applications and the reliability of the results were ensured using statistical tests and expert reviews. The findings further describe the impacts of the well-improved competencies of construction supervisors on labour working patterns and work outputs.

Though the study findings were limited to the Sri Lankan construction sector, the study applications can have a considerable impact on the current/future practices of the construction sector in developing countries as well as other developing industries.

The study outcomes may contribute to a rapid increase in the number of construction supervisors becoming certified assessors of National Vocational Qualifications up to certain levels. This paper describes the further extensive implications and future scopes of the study elaborately.

The study adds new characteristics and values to construction supervision practices that can be remarkable in achieving higher levels of performance and productivity in labour operations. Importantly, the study contributes to adorning the job role of construction supervisors with the title of “labour training expert”.

This study proposes a collaborative federated learning (CFL) framework to address personal data transmission and retention issues for artificial intelligence (AI)-enabled video surveillance in public spaces.

This study examines specific challenges for long-term people monitoring in public spaces and defines AI-enabled video surveillance requirements. Based on the requirements, this study proposes a CFL framework to gradually adapt AI models’ knowledge while reducing personal data transmission and retention. The framework uses three different federated learning strategies to rapidly learn from different new data sources while minimizing personal data transmission and retention to a central machine.

The findings confirm that the proposed CFL framework can help minimize the use of personal data without compromising the AI model's performance. The gradual learning strategies help develop AI-enabled video surveillance that continuously adapts for long-term deployment in public spaces.

This study makes two specific contributions to advance the development of AI-enabled video surveillance in public spaces. First, it examines specific challenges for long-term people monitoring in public spaces and defines AI-enabled video surveillance requirements. Second, it proposes a CFL framework to minimize data transmission and retention for AI-enabled video surveillance. The study provides comprehensive experimental results to evaluate the effectiveness of the proposed framework in the context of facial expression recognition (FER) which involves large-scale datasets.