Computer Applications in Engineering Education最新文献

Immersive Virtual Reality (IVR) creates a highly immersive learning environment for learners. Exploring learning behavior patterns and effectiveness across various information processing modes in IVR experiments helps understand how IVR affects learning effectiveness. This paper focuses on VR experiments in the field of mechanical engineering from the perspective of cognitive style. By comparing the performance of learners with different cognitive styles in both immersive and non-immersive VR experiments, covariance analysis, moderation effect analysis, and lagged sequence analysis are used to analyze learners' knowledge retention and skill transfer abilities, learning behavior patterns, and explore the moderating effect of cognitive style. The study found that: (1) Compared to non-immersive virtual experiments, IVR experiments are more effective in enhancing the abilities of knowledge retention and skill transfer. (2) Cognitive styles moderate the impact of IVR experiments on learning effectiveness. (3) Field-independent learners exhibited more operational behaviors, enhancing their visual experience and information processing in the IVR environment, which significantly improved their learning outcomes. In contrast, field-dependent learners displayed more auxiliary behaviors, which affected their sense of presence, suppressed their positive emotions, and consequently inhibited the improvement of their learning effectiveness. These findings highlight the moderating effect of cognitive style on learning outcomes in IVR experiments, and provide insights for educators to design learner-centered activities and establish personalized learning paths to meet diverse needs.

In engineering education contexts, students in database programming courses within the College of Informatics and Engineering often encounter challenges when transforming problem statements into executable code in technology-enhanced programming environments, which often diminishes their self-efficacy. To address this issue, this study introduces the Problem-to-Code Teaching Framework (PCTF), an instructional model that integrates the Function/Pattern-Oriented Teaching Method with supporting scaffolding activities. The PCTF was implemented in an 18-week PL/SQL course with 45 undergraduates at a university of science and technology in Taiwan, conducted in a technology-enhanced environment using Oracle 19c databases and SQL IDE tools. Using a convergent mixed-methods design, programming self-efficacy was measured at three time points and analyzed with linear mixed-effects regression, while 16 semi-structured interviews captured students' perceptions of conceptual, procedural, and feedback scaffolds. Results indicated a steady increase in programming self-efficacy across the semester, with the compensatory effect among students starting at lower levels. Deep learning approaches showed a strong, positive association, whereas the surface approach was not reliably associated. Qualitative findings indicated that multilayered scaffolds were perceived as supporting confidence and persistence by clarifying problem abstraction and solution modeling, structuring the problem-to-code conversion process, and providing timely feedback. Overall, the PCTF represents a context-bounded yet structurally transferable, technology-enhanced instructional framework that bridges problem analysis and code implementation, contributing to technology-integrated data-centric engineering programming education.

Ensuring equitable access to cybersecurity expertise has become increasingly critical, considering the growing complexity of digital threats. As educators are tasked with delivering instruction in areas such as computer fraud prevention and network security, there is a pressing need for adaptive, data-informed professional development systems that can support individualized learning paths. To address this challenge, this study proposes an adaptive deep reinforcement learning framework for optimizing personalized teacher development path planning in cybersecurity education. Two enhanced models are introduced: an improved Deep Q-Network (DQN) that integrates a multi-layer perceptron, a cubic dynamic reward function, and an adaptive exploration strategy; and a PER-D3QN model that combines dueling double deep Q-learning (D3QN) and prioritized experience replay (PER) to mitigate Q-value overestimation and accelerate convergence. Experimental evaluation using real-world teacher data demonstrates that the improved DQN achieved average performance scores up to 0.36, compared to 0.054–0.068 for the traditional DQN. Moreover, the PER-D3QN model outperformed the ERDQN baseline, attaining an average reward of 4.738 versus 2.021, and an average score of 2.799 after 6000 training rounds, compared to 1.946 for ERDQN, indicating that network update speed has also been significantly improved. This research not only helps to enhance teachers' professional knowledge and technical application ability in the field of network security, but also provides scientific methodological support for educational institutions to ensure that they are aligned with changing security threats. Furthermore, this study emphasizes the importance of interdisciplinary cooperation and encourages experts from computer science, education, and psychology to work.

Although grading is one of the most time-consuming things teachers do, it gives students feedback on how hard they worked to complete an assignment and provides teachers with an evaluation of how well students understood the course material. It is relatively difficult to grade coding assignments since it involves reviewing student-written computer code, giving each student individualized feedback, and allocating partial credit in a fair and consistent manner. Because of its relative simplicity and the abundance of tools and command libraries available, MATLAB is being used in many colleges across the world. In 2018, MathWorks introduced the “MATLAB Grader” system, which allowed instructors to design their own assignment questions requiring students to write a script or a function. This system has many attractive features, such as the ability to allow multiple attempts, with grading done instantly online after each submission to help students improve their code for the next attempt. This paper introduces the MATLAB Smart Assignment Grader (MSAG) system, which includes features absent in MATLAB Grader, such as adaptive grading, plagiarism suspicion flagging, and a partial credit option. To foster the advantages of both grading systems for consistent, adaptive, and fair grading of coding assignments, this paper also proposes an approach to integrating MATLAB Grader with MSAG.

The rapid evolution of Industry 4.0 necessitates that engineering education equips students with skills that bridge traditional instrumentation and modern data-driven analytics. This paper addresses this need by presenting a comprehensive project-based learning module that fuses LabVIEW-based virtual instrumentation with machine learning (ML) for teaching industrial condition monitoring. Implemented in a senior-level undergraduate course, the module tasks student teams with diagnosing the health of an industrial fan. Using the NI ELVIS educational platform instrumented with an accelerometer, students acquire real-time vibration data. A key innovation is the seamless integration of LabVIEW, used for data acquisition and visualization, with a Python-based Convolutional Neural Network (CNN) model, which classifies the fan's condition (normal, minor, or severe malfunction) and rotational speed. The technical implementation achieved high classification accuracy (exceeding 95% on test data) and low inference latency (approximately 0.1 s), demonstrating the feasibility of real-time ML deployment. Pedagogically, the project provided an authentic, interdisciplinary learning experience, enhancing student understanding of vibration analysis, sensor integration, and the practical application of deep learning. The module successfully demonstrates a scalable framework for incorporating AI into engineering laboratories, effectively preparing students for roles that require synthesizing physical system knowledge with intelligent algorithm deployment.

Engineering education is a cornerstone of national development in the Maldives, driving technological progress and supporting essential infrastructure growth. However, the steady decline in student enrolment in engineering programs has become a growing concern. This research examines the key factors influencing students' interest in engineering by analyzing responses from students, faculty, and the public. Using data analysis techniques such as descriptive statistics, correlation, regression, and predictive modelling, a total of 48 factors were evaluated, of which 15 emerged as the most influential. These include financial support, career awareness, and the relevance of the curriculum to industry needs. The predictive model demonstrated strong reliability, achieving 75% accuracy, an F1-score of 80%, and an R² value of 0.89. The analysis showed that financial barriers (mean = 4.76 ± 0.98), limited awareness (95.6%), and insufficient industry exposure (87.6%) were the most significant challenges. Other issues, such as inadequate employer sponsorship, job market uncertainty, and gender imbalance, also contribute to low enrolment. Based on these insights, the research recommends introducing scholarship programs, updating curricula to reflect current industry standards, and strengthening collaboration between academia and employers. The findings offer practical guidance for policymakers to make engineering education in the Maldives more accessible, relevant, and capable of preparing a skilled workforce for future national needs.