Search results

This paper aims to examine how gender differences influence students’ reactions to the use of the annotatable multimedia e-reader (AME). To reach this aim, we develop an AME where various annotation tools are provided to help students learn English in-class and after-class.

An empirical study was conducted with 63 fifth-grade students from an elementary school. A pre-test and post-test were used to identify their prior knowledge and learning achievement, respectively. A questionnaire was applied to identify participants’ perceptions towards the AME.

The results show that students’ post-test scores are significantly related to after-class behaviour, instead of in-class behaviour. Females prefer to use the text annotation and teachers’ voice, but it is voice annotation that is beneficial to improve their learning achievement. Conversely, males prefer to use the text-to-speech only, but it is text annotation that is helpful to improve their learning achievement. Additionally, the ease of use affects males’ intention to use the AME to learn English after-class while it has no effects on females.

This study not only shows the importance of gender differences but also demonstrates the essence of after-class learning behaviour. More importantly, a framework is proposed to support designers to develop e-readers that can accommodate the preferences of females and males.

In the fabric manufacturing industry, various unfavorable factors, including machine fault and yarn breakage, can easily cause fabric defects and affect product quality, begetting huge economic losses to enterprises. Thus, automatic fabric defect detection systems have become an important development direction. Herein, the most common defects in the fabric production process, like ribbon yarn, broken yarn, cotton ball, holes, yarn shedding and stains, are detected. Current fabric defect detection systems afford low detection accuracy and a high missed detection rate for small target fabric defects. Therefore, this study proposes deep learning technology for automatically detecting fabric defects by improving the YOLOv5s target detection algorithm. The improved algorithm is termed YOLOv5s-4SCK, which can effectively detect fabric defects. This study aims to discuss the aforementioned issues.

Specifically, based on the YOLOv5s algorithm, first, the structure of YOLOv5s is modified to add a small target detection layer, fully utilize deep and shallow features and reduce the missed detection rate of small target fabric defects. Second, the integration of CARAFE upsampling enables the effective retention of feature information and maintenance of a certain computational efficiency, thereby improving the detection accuracy. Finally, the K-Means++ clustering algorithm is used to analyze the position of the center point of the prior box to better obtain the anchor box and improve the average accuracy and evaluation index of detection.

The research results show that the YOLOv5s-4SCK algorithm increases the accuracy by 4.1% and the detection speed by 2 f.s-1 compared to the original YOLOv5s algorithm, and it effectively improves the original YOLOv5s problem of high missed detection rate of small targets.

The YOLOv5s-4SCK proposed in this paper can effectively reduce the missed detection rate of fabric defects, improve the detection efficiency and has certain industrial value.

The proposed algorithm can quickly identify fabric defects, effectively improving the detection rate. In the future, the proposed algorithm will be applied in the actual industry.

Automatic fabric defect detection reduces the manpower of inspectors, and the proposed YOLOv5s-4SCK algorithm is also suitable for other recognition fields.

The proposed YOLOv5s-4SCK algorithm has been tested using real cloth to ensure its accuracy, and its performance is better than the original YOLOv5s algorithm.

The purpose of this study is to study the pitting caused by Ca-Al-O-S composite inclusions of low-alloy steel in 3 Wt.% NaCl solution and 0.01M NaHSO3 solution.

The corrosion in 0.01M NaHSO3 was much weaker than in 3 Wt.% NaCl 3D display of the pitting formation and development process that has been calculated using scanning electron microscope (SEM) and laser scanning confocal microscopy (LSCM). In addition, a corrosion mechanism of pitting formation by galvanic interaction of composite inclusion and base metal has been proposed.

Results show that in immersion test, metal base around inclusions was dissolved due to corrosion. Corrosion on the metal base closer to inclusions was more severe.

A corrosion mechanism of pitting formation by galvanic interaction of composite inclusion and base metal has been proposed.

The purpose of this paper is to understand the process of failure of scale and the corrosion resistance of scale to the substrate in an atmospheric environment.

The corrosion behaviour of X65 pipeline steel with different types of oxide scale was analysed using the natural environment exposure corrosion test, scanning electron microscopy analysis, electrochemical corrosion polarization curve test and other methods in a warehouse environment.

The results of this research show that one type of oxide scale, which is rough, has an uneven microstructure, and exhibits weak adhesion to the matrix, does not protect the substrate from corrosion. Conversely, the uniform, dense oxide scale, which exhibits strong adhesion to the matrix, provides effective protection to the steel. However, as the corrosion develops, the corrosion rate of the substrate tends to accelerate, especially when the structure of the oxide scale is damaged to a certain extent.

The corrosion mechanism of the oxide scale on hot rolled steel in an atmospheric environment has been proposed.

This paper aims to report on a study that used the practice theory lens to understand how Chinese ethnic culture influences restaurant workers' learning through engagement in everyday work practices.

A multiple case study approach was used. Data were collected from semi-structured interviews and site observations. Thematic analysis was conducted to identify how workers learnt the sayings, doings and relatings in their workplaces.

The findings show that the ethnic culture of the participants influences and enriches their learning in practice settings such as small Chinese restaurants.

The understandings presented here need to be verified through more research in different regions and nations. In addition, cross-cultural studies on other ethnic restaurants may contribute to deeper understandings of the influences of ethnic culture on practice-based learning.

The research contributes to understanding the influence of ethnic culture on practice-based learning.

The understandings gained from the findings of this study form a useful basis for curriculum development and instructional design of training programmes for practice-based as well as work-integrated-learning components of vocational curriculum. Furthermore, awareness of the strengths of the ethnic culture is of interest to owner/managers of small Chinese restaurants to afford supportive learning environments for workers.

Workers' unsafe behavior is the main cause of construction safety accidents, thereby highlighting the critical importance of behavior-based management. To compensate for the limitations of computer vision in tackling knowledge-intensive issues, semantic-based methods have gained increasing attention in the field of construction safety management. Knowledge graph provides an efficient and visualized method for the identification of various unsafe behaviors.

This study proposes an unsafe behavior identification framework by integrating computer vision and knowledge graph–based reasoning. An enhanced ontology model anchors our framework, with image features from YOLOv5, COCO Panoptic Segmentation and DeepSORT integrated into the graph database, culminating in a structured knowledge graph. An inference module is also developed, enabling automated the extraction of unsafe behavior knowledge through rule-based reasoning.

A case application is implemented to demonstrate the feasibility and effectiveness of the proposed method. Results show that the method can identify various unsafe behaviors from images of construction sites and provide mitigation recommendations for safety managers by automated reasoning, thus supporting on-site safety management and safety education.

Existing studies focus on spatial relationships, often neglecting the diversified spatiotemporal information in images. Besides, previous research in construction safety only partially automated knowledge graph construction and reasoning processes. In contrast, this study constructs an enhanced knowledge graph integrating static and dynamic data, coupled with an inference module for fully automated knowledge-based unsafe behavior identification. It can help managers grasp the workers’ behavior dynamics and timely implement measures to correct violations.

This study builds on a conceptual model by integrating AI features – Perceived intelligence (PIN) and anthropomorphism (PAN) – while extending expectation confirmation theory (ECT) factors – interaction quality (IQU), confirmation (CON), and customer experience (CSE) – to evaluate the continued intention to use (CIU) of AI-enabled digital banking services.

Data were collected through an online questionnaire administered to 390 digital banking customers in India. The data were further analysed, and the presented hypotheses were evaluated using partial least squares structural equation modelling (PLS-SEM).

The research indicates that perceived intelligence and anthropomorphism predict interaction quality. Interaction quality significantly impacts expectation confirmation, consumer experience, and the continuous intention to use digital banking services powered by AI technology. AI design will become a fundamental factor; thus, all interactions should be user-friendly, efficient, and reliable, and the successful implementation of AI in digital banking will largely depend on AI features.

This study is the first to demonstrate the effectiveness of an AI-ECT model for AI-enabled Indian digital banks. The user continuance intention to use digital banking in the context of AI has not yet been studied. These findings further enrich the literature on AI, digital banking, and information systems by focusing on the AI's Intelligence and Anthropomorphism variables in digital banks.

This study aimed to explore the impact of Artificial Intelligence (AI) characteristics, namely Perceived Animacy (PAN), perceived intelligence (PIN), and perceived anthropomorphism (PAI), on user satisfaction (ESA) and continuous intentions (CIN) by integrating Expectation Confirmation Theory (ECT), with a particular focus on Generation Y and Z.

Using a quantitative method, the study collected 495 data from Gen Y (204) and Z (291) respondents who were users of digital banking apps through structured questionnaires that were analysed using PLS-SEM. The latter helped investigate the driving forces of AI characteristics and user behavioural intentions as well as reveal generation-specific features of digital banking engagement.

The study revealed that PAN and PIN have significant positive effects on the anthropomorphic perceptions of digital banking apps, which in turn increases perceived usefulness, satisfaction, and continuous intentions. In particular, the influence of these AI attributes varies across generations; Gen Y’s loyalty is mostly based on the benefits derived from AI features, whereas Gen Z places a greater value on the anthropomorphic factor of AI. This marked a generational shift in the demand for digital banking services.

The specificity of Indian Gen Y and Z users defines the scope of this study, suggesting that demographic and geographical boundaries can be broadened in future AI-related banking research.

The results have important implications for bank executive officers and policymakers in developing AI-supported digital banking interfaces that appeal to the unique tastes of millennial customers, thus emphasising the importance of personalising AI functionalities to enhance user participation and loyalty.

This study enriches the digital banking literature by combining AI attributes with ECT, offering a granular understanding of AI’s role in modulating young consumers' satisfaction and continuance intentions. It underscores the strategic imperative of AI in cultivating compelling and loyalty-inducing digital banking environments tailored to the evolving expectations of Generations Y and Z.