Computer Applications in Engineering Education最新文献

There has been increased demand for personalized approaches for e-learning that seek to increase the learners' engagement and outcomes over the past years. This has been triggered by the availability of mobile technologies and the exigence for adaptive instructional models that tailor the learning content to the learner's needs and settings. Microlearning, as an emerging paradigm of e-learning, is an original instructional approach that delivers time-efficient content that is provided to learners on demand. Microlearning can benefit a great deal from AI techniques to adapt the learning content to a variety of learners. This study proposes AI-driven personalized microlearning e-courses for higher education, especially for computer science courses. In this study, we develop and evaluate AI algorithms to produce adaptive learning paths for individual students, according to the data from the Open University Learning Analytics Dataset. Unlike existing approaches that rely on static, one size fits all instructional platforms, AI algorithms learn dynamically, predict and react to specific student needs to a fidelity of over 98% as shown in the experiments done in this study where their performance reached 98.96% accuracy, 99% precision and 99% F1-Score, and actually point to the use of highly tailored learning experiences to enhance both engagement and academic success. This contribution to the body of research on AI applications in education and on the potential for AI in improving personalized learning in computer courses is pointed out. Additionally, the study paves the way to embed adaptive microlearning strategies within current Virtual Learning Environments to address the individual learning requirements of students in today's digital classrooms.

This study presents procedures and guidelines for using the popular Dynamic Geometry Software (DGE) GeoGebra to create highly interactive simulations of mechanisms and robots towards educational and research purposes. The goal is to introduce and demonstrate the tool to develop self-explanatory constructions designed to present important topics, namely, the spatial posture, the graphical solution of the position analysis of mechanisms of serial and parallel manipulators, the Denavit-Hartenberg (DH) proximal convention, the homogeneous transformation matrices, and the hypothetical closure link method for serial manipulators. Seven constructions are illustrated: the interactive coordinate system construction, the 1-degree of freedom (DOF) position analysis of a spherical four-bar mechanism, the inverse analysis of a 4-DOF Schönflies parallel platform with three universal-prismatic-universal legs, and four constructions for the 6-DOF General Electric P60 (GE-P60) serial robot. The first of these four constructions deals with the direct position analysis via the graphical method. The second one offers a detailed explanation of the DH parameters. The third one uses the DH parameters to obtain the homogeneous transformation matrices for solving its direct position analysis. Finally, the fourth construction solves the hypothetical closure link and the inverse position analysis of the serial robot. The results are interactive computer simulations accessible via hyperlinks, encouraging users to explore the constructions, to use them as a cornerstone for their own constructions, and enhance the topics comprehension. The authors envision these simulations as an effective tool to communicate the knowledge about mechanisms and robots.

This paper offers a comparative study for topology optimization (TO) with quadrilateral family elements, for example, 4-noded (Q4), 8-noded (Q8), and 9-noded (Q9) elements for diverse problems. MATLAB codes are developed with Q8 and Q9 elements for three distinct design problems involving different physics, wherein we provide straightforward and efficient methods for generating connectivity matrices and for determining elemental stiffness matrices in terms of Poisson's ratio for these elements. To demonstrate the relative performances, the paper presents (i) Compliance minimization for stiff structures subjected to constant forces, (ii) Compliance minimization for load-bearing structures under design-dependent pressure loads, (iii) Compliant mechanism problems focused on maximizing desired output deformation. A volume constraint is applied to all problems. Q8 and Q9 finite elements produce optimized designs free of checkerboard patterns. Sensitivity and density filtering schemes are incorporated to ensure a minimum feature size of the optimized designs. An outline for implementing a Heaviside projection filter is also provided for achieving optimized solutions close to binary (0-1). The presented exhaustive comparative study, accompanied by codes and supporting materials, serves as both an educational tool for academia and a valuable resource for those new to the field. The relevant codes are included in the appendices.

Educational disparity in math performance remains a persistent challenge. With the development of AI, there is growing attention on educational data mining. This study applies explainable machine learning to uncover the complex factors contributing to the math performance gap between secondary-school boys and girls. Data from the Program for International Student Assessment, covering Hong Kong, Macao, Taipei, Singapore, Japan, and Korea (17,566 males and 16,929 females), underwent rigorous preprocessing and feature selection. Prediction models for boys and girls were constructed and optimized separately. The Shapley Additive Explanations method was used to explain the models and reveal key influences. Boys’ performance is mainly influenced by expected career status, math anxiety, and the number of math teachers. For girls, key factors are math self-efficacy, family economic, social, and cultural status, and competency grouping in math lessons. This comprehensive analysis explores student, family, and school factors affecting math performance and advances the application of explainable machine learning in educational data mining.

Students with strong Computational Thinking (CT) skills possess a unique ability to analyze problems, devise efficient solutions, and navigate the intricacies of a rapidly evolving digital landscape. Given the conceptual overlapping between CT skills and engineering design competencies, engineering design processes provide students with a context for applying and developing CT skills. However, how to promote students to develop CT skills through pedagogical design in engineering education needs further research, especially in the formal higher education context. To address this gap, we constructed a model and designed a course that supports students in applying CT (i.e., decomposition, pattern recognition, abstraction, algorithm design, and troubleshooting/debugging) skills during multiple engineering design iterations. We collected 13 group design reports from 62 undergraduate students regarding their efforts in designing and solving mazes over three design iterations by applying CT skills. Using mixed methods, we examined what and how CT skills were demonstrated in the group reports, and what changes groups made between design iterations and why. We found that the participants demonstrated five CT skills with differing frequencies and needed more support in troubleshooting. When making changes between design iterations, groups mainly considered enabling users to apply CT skills, avoiding hard coding, adjusting the complexity of the mazes, considering design constraints to meet engineering design requirements, and enhancing user experience. The findings underscore the pressing need to equip students with the ability to navigate and resolve intricacies, particularly in troubleshooting, and groups' abilities to consider various elements when making engineering design decisions.

This study presents a novel modular package developed in Visual Basic for Applications (VBA) that integrates into a macro-enabled MS Excel workbook. This package creates a three-dimensional coordinate system within the spreadsheet, allowing users to model various physics problems efficiently. Designed for users with basic knowledge of MS Excel and fundamental physics knowledge, the package enables rapid model development without the need for programming experience. Users can add vectors to the coordinate system, which can be transformed into other mathematical objects. The package features specialized cells that function as coordinates or time variables. It has been rigorously tested and includes 25 fundamental examples in disciplines such as electrodynamics, mechanics, thermodynamics, optics, and mathematics. This tool significantly simplifies the modeling process and provides an accessible approach to solving complex physics problems.

The rapid advancements in digital technologies such as artificial intelligence (AI), virtual reality (VR), augmented reality (AR), mixed reality (MR), extended reality (XR), and the internet of things (IoT) have revolutionized various sectors, including education. Metaverse, a convergence of these transformative technologies, offers immersive, personalized, and interactive experiences, making it a powerful tool in modern education. This paper explores the Metaverse's role in enhancing education by examining its architecture, types, and components while addressing practical implementation challenges, and follows a structured review protocol to ensure a comprehensive analysis, including systematic research, paper selection, and a critical examination of relevant studies from reputable databases such as Google Scholar, IEEE Xplore, ACM, and Springer. The research objectives focus on evaluating the Metaverse's applications in education, ethical challenges, technological limitations, and potential strategies for sustainable integration. Key research questions address the need for Metaverse adoption in education, its benefits, challenges, and future directions. The Metaverse cultivates essential skills such as empathy, ethical reasoning, and effective communication by providing students with customized, immersive learning environments. However, ethical concerns, technical barriers, and infrastructural costs pose significant obstacles to its widespread adoption. It discusses strategies to solve these barriers, explores applications in distance learning, and proposes future research directions to create scalable and sustainable educational models in the Metaverse. Through this structured inquiry, the paper establishes the Metaverse as a transformative force in education, blending technological innovation with instructional advancement.