Computer Applications in Engineering Education最新文献

3D CAD modeling technology has become an essential tool for product design across various industries, including machinery, aerospace, automotive, architecture, and healthcare. Consequently, numerous educational institutions offer training programs and certification exams to enhance and evaluate the modeling proficiency of 3D CAD system users. However, the manual grading process currently employed in 3D CAD modeling exams reveals several limitations, such as excessive time and effort, and challenges in maintaining consistency in evaluations. In mechanical CAD systems, in particular, users can create the same model using different features, making precise grading criteria essential. Additionally, the lack of self-directed learning capabilities among learners has emerged as a pressing issue, highlighting the need for more effective educational solutions. To address these challenges, this study introduces CADuBoost, an automated grading and feedback system for 3D CAD modeling education in mechanical engineering. CADuBoost compares student-submitted 3D CAD models with reference models through a comprehensive evaluation framework that processes both geometric and non-geometric data. Shape evaluation is conducted using neutral formats such as STEP and STL through point cloud comparison, multi-view image analysis, and dimensional accuracy measurement. Non-geometric evaluation is performed by extracting and analyzing design history and constraint information via the 3D CAD system's API. Furthermore, by providing visual feedback through color-coded geometric differences and detailed design history analysis, the system delivers personalized feedback that effectively fosters self-directed learning. The effectiveness of CADuBoost was validated through experiments in real educational settings, showing possibilities to improving students' modeling proficiency and self-directed learning abilities. This system is expected to enhance instructors' efficiency and improve the overall quality of education.

Human advancement hinges on the capacity to acquire knowledge and engage with complex ideas. Education, therefore, plays a pivotal role in shaping cognitive and societal growth. However, the increasing commercialization of education has raised significant concerns regarding declining academic standards, reduced student performance, and escalating unemployment. To address these systemic challenges, this study proposes a machine learning-based framework for predicting and evaluating Course Learning Outcomes (CLOs) and Program Learning Outcomes (PLOs) in an undergraduate engineering context. The proposed model analyzes historical academic records to investigate the influence of midterm and final assessments on overall grade performance and CLO/PLO attainment. Results indicate that CLO 1 has consistently achieved approximately 90% success over the past 2 academic years, a trend expected to persist based on predictive insights. These findings offer actionable guidance for academic departments to implement targeted interventions, such as scenario-based evaluations, to enhance student learning outcomes. By leveraging Python-based machine learning techniques, institutions can scale their data-driven assessment strategies and reinforce evidence-based educational practices. This study contributes to the growing field of AI-enhanced education, offering practical implications for improving academic quality and institutional decision-making.

Artificial intelligence (AI) is increasingly recognized as a vital tool in electrical engineering, offering automation, error reduction, and enhanced accessibility. However, its adoption has lagged compared to other fields, highlighting a need for a comprehensive examination of its applications and challenges. This study systematically reviews AI applications in electrical engineering, classifying research findings to uncover progress, challenges, and opportunities. It aims to identify trends, gaps, and implications to guide future research and practical applications. A systematic literature review (SLR) was conducted, analyzing studies published between 2014 and 2024. Fifty-seven publications meeting inclusion criteria were categorized into five themes: AI algorithms, power engineering, smart grid technologies, electric vehicle systems, and AI integration. The review revealed growing interest in AI applications within electrical engineering, with a significant rise in publications, particularly from China. AI algorithms demonstrated broad applicability and versatility across various domains, highlighting their potential for innovation. Additionally, there is a considerable opportunity for developing and applying frameworks to test AI innovations in electrical engineering. AI integration in electrical engineering has advanced significantly in areas such as power engineering, smart grid technologies, and electric vehicle systems. However, substantial untapped potential remains, particularly in developing frameworks for testing AI innovations. This review underscores the importance of global research efforts and identifies promising directions for advancing AI applications in electrical engineering research and practice.

The soil arching effect is a key concept in soil mechanics education. It is widely recognized as an important principle in geotechnical engineering, characterized by stress redistribution due to relative soil displacement, which impacts the safety and stability of geotechnical structures. Despite advances in classical theories and numerical methods, the complexity of models and formulas still presents significant challenges for students and engineers in understanding and application. To address this challenge, this study introduces a practical and educational solution by developing a computer-aided calculation platform for the soil arching effect, designed by Hunan Provincial Engineering Research Center of Advanced Technology and Intelligent Equipment for Underground Space Development in Hunan University, aimed at enhancing soil mechanics education through an intuitive MATLAB graphical user interface. The primary contribution of this study is the development of a platform that integrates seven theoretical models, enabling users to calculate key parameters, such as the soil arching ratio, by inputting soil properties and unloading width. The platform features real-time data visualization and interactivity, allowing users to easily select models, input parameters, and obtain results quickly, thereby facilitating comparative analysis across different theoretical frameworks. Compared to conventional teaching methods, the platform simplifies complex calculations and deepens students’ understanding of the soil arching effect. Results from student surveys indicate a remarkable improvement in comprehension and analytical skills, with high satisfaction regarding the platform's usability and educational value.

Machine learning (ML) has the potential to enhance educational predictive analytics, but its adoption is limited by the programming expertise required to develop models. Traditional ML tools require coding skills, which makes them inaccessible to educators and researchers without computational backgrounds. Existing no-code platforms lack affordability and accessibility. This study addresses this gap by developing and validating a no-code ML builder to enable non-programmers to build, evaluate, and deploy ML models. Design and development research approach was adopted in the study. It utilizes Python-based tools such as Streamlit and scikit-learn. The tool underwent expert validation and comparative performance testing against Google Colab using datasets from Kaggle, consisting of 5000 and 2392 student performance records. The results show that the no-code ML builder, which is accessible at nextml.streamlit.app achieved a predictive performance comparable to coded models. A minor performance gap was observed in some algorithms, with Logistic Regression achieving an accuracy of 63.88% compared to 73.28% in Google Colab. Experts in educational technology and computer science rated the tool highly for usability, with mean scores ranging from 4.33 to 4.57. 71% of evaluators found it suitable for educational datasets, and 56% endorsed its ability to handle students' data sets. The study concludes that the tool bridges the accessibility gap in the application of ML in education while maintaining competitive model performance. It recommends that Institutions adopt no-code tools. Future research should focus on incorporating more complex algorithms.

Large Language Models (LLMs) are transforming several aspects of our lives, including text and code generation. Their potential as “copilots” in computer programming is significant, yet their effective use is not straightforward. Even experts may have to generate multiple prompts before getting the desired output, and the code generated may contain bugs that are difficult for novice programmers to identify and fix. Although some prompting methods have been shown to be effective, the primary approach still involves a trial-and-error process. This study explores mechanical engineering students' experiences after engaging with ChatGPT to generate code for the Finite Element Analysis (FEA) course, aiming to provide insights into integrating LLMs into engineering education. The course included a scaffolded progression for students to develop an understanding of MATLAB programming and the implementation of FEA algorithms. After that, the students engaged with ChatGPT to automatically generate a similar code and reflected on their experiences of using this tool. We designed this activity guided by the productive failure framework: since LLMs do not necessarily produce correct code from a single prompt, students would need to use these failures to give feedback, potentially increasing their own understanding of MATLAB coding and FEA. The results suggest that while students find ChatGPT useful for efficient code generation, they struggle to: (1) understand a more sophisticated algorithm compared to what they had experienced in class; (2) find and fix bugs in the generated code; (3) learn about disciplinary concepts while they are also trying to fix the code; and (4) identify effective prompting strategies to instruct the ChatGPT how to complete the task. While LLMs show promise in supporting coding tasks for both professionals and students, using them requires strong background knowledge. When integrated into disciplinary courses, LLMs do not replace the need for effective pedagogical strategies. Our approach involved implementing a use-modify-create sequence, culminating in a productive failure activity where students engaged in conversations with the LLM encountered desirable difficulties. Our findings suggest that students faced challenges in trying to get a correct working code for FEA, and felt like they were teaching the model, which in some cases, led to some frustration. Thus, future research should explore additional forms of support and guidance to address these issues.

Traditional methods for teaching Internet-of-things (IoT) in engineering education often lack interactivity and hands-on engagement, limiting skill development. This study explores Augmented Reality (AR) based learning environment as a solution, enabling students to visualize real-time data flows, interact with virtual components, and configure IoT systems in a risk-free setting. Using tools like Unity 3D, Blender, Vuforia SDK, and Arduino IDE, an AR-based framework is developed and tested against traditional methods. The results show increased student engagement, knowledge retention, and skill acquisition, with a System Usability Score of 82.00%. The paper presents the framework's design, usability assessment, and comparative evaluation, highlighting AR's potential to enhance IoT education. It is observed that the proposed AR-based framework improves the skill retention by 36% over the traditional method. Further, the performance comparison of proposed method with traditional method is evaluated in terms of students' engagement, learning speed, and user satisfaction. In the end, the limitations of proposed study are addressed, and the future directions are presented.