检索结果-内蒙古大学图书馆

Source Code Error Understanding Using BERT for Multi-Label Classification

IEEE ACCESS 2025年 13卷 3802-3822页

作者： Amin, Md Faizul Ibne Watanobe, Yutaka Rahman, Md Mostafizer Shirafuji, Atsushi Univ Aizu Grad Dept Comp & Informat Syst Aizu Wakamatsu Fukushima 9658580 Japan Tulane Univ Dept Comp Sci New Orleans LA 70118 USA

programming is an essential skill in computer science and across a wide range of engineering disciplines. However, errors, often referred to as 'bugs' in code, can be challenging to identify and rectify for both students learning to program and experienced professionals. Understanding, identifying, and effectively addressing these errors are critical aspects of programming education and software development. To aid in understanding and classifying these errors, we propose a multi-label error classification approach for source code using fine-tuned BERT models (BERT_Uncased and BERT_Cased). The models achieved average classification accuracies of 90.58% and 90.80%, exact match accuracies of 48.28% and 49.13%, and weighted F1 scores of 0.796 and 0.799, respectively. Precision, Recall, Hamming Loss, and ROC-AUC metrics further evaluate the effectiveness of our models. Additionally, we employed several combinations of large language models (CodeT5, CodeBERT) with machine learning classifiers (Decision Tree, Random Forest, Ensemble Learning, ML-KNN), demonstrating the superiority of our proposed approach. These findings highlight the potential of multi-label error classification to advance programming education, software engineering, and related research fields.

关键词： programming programming profession Codes Multi label classification Accuracy Education Transformers Measurement Computer bugs Data models Multi-label classification BERT CodeT5 CodeBERT decision tree random forest ML-KNN ensemble learning data analysis educational big data error classification learning analytics programming learning software engineering

来源：评论

学校读者我要写书评

暂无评论

Formal Concept Analysis of Students' Solutions on Computational Thinking Game

引用

IEEE TRANSACTIONS ON EDUCATION 2025年第1期68卷 20-32页

作者： Gunis, Jan Snajder, L'ubomir Antoni, L'ubomir Elias, Peter Kridlo, Ondrej Krajci, Stanislav Pavol Jozefafrik Univ Kosice Inst Comp Sci Fac Sci Kosice 04001 Slovakia Slovak Acad Sci Math Inst Kosice 04001 Slovakia

Contribution: We present a framework for teachers to investigate the relationships between attributes of students' solutions in the process of problem solving or computational thinking. We provide visualization and evaluation techniques to find hidden patterns in the students' solutions which allow teachers to predict the specific behavior of students or to prevent some student mistakes or misconceptions in advance or further pedagogical intervention. Background: Formal concept analysis is a method of unsupervised Machine Learning that applies mathematical lattice theory to organize data based on objects and their shared attributes. Several fuzzy extensions of formal concept analysis have a great potential to visualize and evaluate students' solutions, to categorize the solutions into overlapping biclusters (formal concepts) or to generate the attribute implications between extracted attributes. Research Question: Does formal concept analysis describe the various solutions and the relationships between the extracted attributes of students' solutions in the educational and computational thinking game Light-Bot? Methodology: Targeting the evaluation of 64 students' solutions in the Light-Bot game, we construct the formal contexts of the extracted attributes. We apply formal concept analysis to construct the concept lattices from two binary formal contexts and to generate attribute implications and their fuzzy counterparts to find the dependencies between the extracted attributes. Findings: The results of our paper provide a description of various students' solutions which are visualized in the concept lattices. 1) Regarding the concept lattice of binary formal contexts, we obtained the characterization of the largest biclusters which includes a description of the largest group of similar solutions. 2) The attribute implications mainly reveal the characterization of similar solutions, e.g., with a higher count of executed commands in solutions. 3) Using fuzzy attribute

关键词： Games Formal concept analysis Education Lighting programming profession Lattices Robots Attribute implications formal concept analysis light-bot visualization

来源：评论

学校读者我要写书评

暂无评论

Engaging Students in Audiovisual Coding Through Interactive MATLAB GUIs

引用

IEEE ACCESS 2025年 13卷 8158-8168页

作者： Cuevas, Carlos Cortes, Carlos Garcia, Narciso Univ Politecnicade Madrid UPM Informat Proc & Telecommun Ctr IPTC Grp Tratamiento Imagenes GTI Madrid 28040 Spain Univ Politecnicade Madrid UPM ETSI Telecomunicac Madrid 28040 Spain

Traditional educational methods in higher education, such as lectures and hands-on exercises, often struggle to fully engage students or address the complexities inherent in audiovisual signal coding. This gap underscores the need for innovative educational tools that not only foster deeper understanding but also enhance student engagement within the university setting. Effective evaluation of these tools requires comprehensive assessment of both learning outcomes and user experience. This study introduces three novel graphical user interface applications designed to strengthen foundational knowledge in audio, image, and video signal coding. These interactive tools, specifically developed for use in university courses, allow students to experiment with various coding techniques, providing hands-on experience that bridges theoretical concepts and practical application. Furthermore, we propose a robust methodology to evaluate the effectiveness of these tools in improving learning outcomes. The tools, developed using MATLAB, were integrated into a computer vision course and assessed through a combination of pre- and post-tests, the System Usability Scale, and the Evaluation Tool for Learning Quality. Results indicate a significant improvement in student knowledge and positive feedback regarding the usability and educational value of the tools. These findings suggest that the interactive nature of the tools not only enhances knowledge retention but also boosts student engagement, offering a valuable complement to traditional educational methods in higher education.

关键词： Image coding Graphical user interfaces Education MATLAB Quantization (signal) Audio coding Usability Visualization Signal to noise ratio programming profession Audiovisual coding graphical tools interactive learning MATLAB GUI student engagement teaching effectiveness

来源：评论

学校读者我要写书评

暂无评论

Automated Code Assessment and Feedback: A Comprehensive Model for Improved programming Education

引用

IEEE ACCESS 2025年 13卷 56642-56658页

作者： Parvathy, R. Thushara, M. G. Kannimoola, Jinesh M. Amrita Vishwa Vidyapeetham Amrita Sch Comp Dept Comp Sci & Engn Amritapuri 690525 Kerala India Amrita Vishwa Vidyapeetham Amrita Sch Comp Dept Comp Sci & Applicat Amritapuri 690525 Kerala India

programming skills are essential in nearly every job today. To prepare students for the growing demand for programming expertise, they must be proficient in coding. This poses a challenge for educators who must ensure students are well-equipped to meet these demands. In Today's time, most of the schools and universities have introduced advanced curricula and syllabi with programming courses, thus an effective and conventional model to evaluate the codes submitted by students in a timely manner is very much required. Traditional grading systems were often slow, biased, and lacked the ability to provide meaningful feedback, which is crucial for student improvement. This study proposes an extensive automated code assessment and feedback model that addresses these issues and provides timely feedback to students. The model evaluates different aspects of the codes like originality, accuracy, structure, and syntax. By using the Abstract Syntax Tree (AST) analysis for code structure, plagiarism detection, and syntax error identification, the model offers an improved approach to evaluating student's coding skills. To evaluate the model, a group of 60 engineering students participated, and the model demonstrated a 40% increase in grading efficiency, reducing grading time while maintaining quality. The feedback on scores provided students with valuable insights about their understanding of programming concepts. This model not only supports skill development through actionable feedback but also promotes larger educational goals of accessibility and inclusivity by offering a sustainable solution for quality learning.

关键词： Codes programming profession Syntactics Encoding Education Accuracy Semantics Plagiarism Testing Sustainable development Automated assessment code evaluation plagiarism detection programming education student feedback sustainable education

来源：评论

学校读者我要写书评

暂无评论

A 1.1 V-Programmable Metal-Fuse Technology With Current-Mode programming and Program-Guarantee Technique in 28 nm CMOS Technology

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2025年第2期72卷 685-693页

作者： Fan, Philex Ming-Yan Chen, Chen-An Wang, Chih-Hao Ko, Hsiang-Yu Natl Cheng Kung Univ Dept Elect Engn Tainan 70101 Taiwan Natl Cheng Kung Univ Hierarch Green Energy Mat Hi GEM Res Ctr Tainan 70101 Taiwan Natl Cheng Kung Univ Dept Elect Engn Tainan 70101 Taiwan

The first 1.1V-programmable metal-fuse technology in 28nm CMOS technology is reported in this work. The prototyped 1Kb-memory array featuring a 12.4 mu m(2) 1T1R bit cell adopts the proposed current-mode programming (CMP) scheme. The CMP scheme achieves a record low programming voltage of 1.1V, surpassing the programming voltages (>= 1.6V) required by prior metal-fuse CMOS and FinFET technologies. To ensure successful programming, a closed-loop detector (CLD) employing an on-chip hysteresis comparator detects resistance transition in bit cells during programming. Preliminary experiments demonstrate that the proposed CMP scheme along with CLD achieves a 100% of yield after programming 960 bits at room temperature. Under various programming conditions, the combination of CMP and CLD demonstrates programming robustness, with resistance ratios before and after programming equal to and greater than three orders of magnitude. The measured results suggest a promising method for mitigating over-stress issues associated with high programming voltages used in prior art.

关键词： Fuses Metals programming profession Circuits Resistance CMOS technology Clamps Fans Detectors Mass production Metal fuse one-time-programmable ROM (OTP-ROM) low voltage nonvolatile memory reliability

来源：评论

学校读者我要写书评

暂无评论

Examining the Usability of the Moirai Serious Game Authoring Platform

引用

IEEE TRANSACTIONS ON GAMES 2025年第1期17卷 235-241页

作者： Torres, Andrei Kapralos, Bill Dubrowski, Adam Ontario Tech Univ maxSIMhealth Grp Oshawa ON L1G 0C5 Canada

Despite the be benefits of serious games and their growing popularity across many educational contexts, they generally have have fixed scenarios that cannot be easily modified, leading to predictable and dull experiences that can reduce user engagement. We recently introduced Moirai, a novel, no-code serious games authoring platform that allows educators with limited (if any) programming experience to use a diagram-based interface to create new modifications and customize serious game scenarios focused on decision and communication skills development. In this article, we describe a usability study that saw medical educators with limited programming knowledge create a predefined serious game scenario using Moirai. Results indicate a high degree of usability and revealed various changes that can be made to improve Moirai.

关键词： Games Usability Authoring systems Visualization programming profession Education Standards Healthcare education no-code scenario editor serious games virtual simulation

来源：评论

学校读者我要写书评

暂无评论

Competency-Based Hybrid Learning: A Modern Approach to Teaching programming and Digital Technologies Subjects

引用

IEEE ACCESS 2025年 13卷 54892-54919页

作者： Kucera, Erik Haffner, Oto Slovak Univ Technol Bratislava Fac Elect Engn & Informat Technol Bratislava 84104 Slovakia

The COVID-19 pandemic prompted the global education sector to experiment with various forms of online learning as institutions rapidly transitioned to remote formats. This article presents a comprehensive overview of a competency-based hybrid learning methodology, developed and implemented during the pandemic. In addition to detailing the methodology itself, the article also shares the experiences of educators at the authors' institution, who observed significant improvements in educational outcomes, surpassing even pre-pandemic standards. The methodology highlights the limitations of directly replicating traditional in-person instruction in an online format using existing materials and approaches. Instead, it advocates for carefully designed adaptations tailored to the digital environment, leveraging asynchronous components, interactive tools, and newly created e-learning resources to optimize effectiveness. This approach also requires increased interaction between educators and students beyond scheduled classes, ensuring timely support and guidance. Although this methodology may not suit all course types, it has proven particularly effective in advanced information and communication technologies (ICT) and digital technology subjects, such as programming, artificial intelligence, digital or electronic marketing, video editing, 3D engine work, etc. The positive student feedback further underscores the potential of this model to enhance educational quality and outcomes in these domains.

关键词： Hybrid learning Education programming profession programming Pandemics Engineering education Electronic learning Training Focusing COVID-19 online learning blended learning digital technologies ICT modern teaching training

来源：评论

学校读者我要写书评

暂无评论

A Flexibility Scheduling Method for Distribution Network Based on Robust Graph DRL Against State Adversarial Attacks

引用

JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY 2025年第2期13卷 514-526页

作者： Yin, Ziyang Wang, Shouxiang Zhao, Qianyu Tianjin Univ Key Lab Smart Grid Minist Educ Tianjin 300072 Peoples R China

In the context of large-scale photovoltaic integration, flexibility scheduling is essential to ensure the secure and efficient operation of distribution networks (DNs). Recently, deep reinforcement learning (DRL) has been widely applied to scheduling problems. However, most methods neglect the vulnerability of DRL to state adversarial attacks such as load redistribution attacks, significantly undermining its security and reliability. To this end, a flexibility scheduling method is proposed based on robust graph DRL (RoGDRL). A flexibility gain improvement model considering temperature-dependent resistance is first proposed, which considers weather factors as additional variables to enhance the precision of flexibility analysis. Based on this, a state-adversarial two-player zero-sum Markov game (SA-TZMG) model is proposed, which converts the robust DRL scheduling problem into a Nash equilibrium problem. The proposed SA-TZMG model considers the physical constraints of state attacks that guarantee the maximal flexibility gain for the defender when confronted with the most sophisticated and stealthy attacker. A two-stage RoGDRL algorithm is proposed, which introduces the graph sample and aggregate (Graph-SAGE) driven soft actor-critic to capture the complex feature about the neighbors of nodes and their properties via inductive learning, thereby solving the Nash equilibrium policies more efficiently. Simulations based on the modified IEEE 123-bus system demonstrates the efficacy of the proposed method.

关键词： Optimal scheduling Costs Training Resistance Computational modeling Scheduling Robustness programming profession Distribution networks Accuracy Distribution network photovoltaic flexibility scheduling deep reinforcement learning cyber attack

来源：评论

学校读者我要写书评

暂无评论

Applying the Block-Based programming Language ALICE for Developing programming Competencies in University Students

引用

IEEE ACCESS 2025年 13卷 21471-21485页

作者： Vinueza-Morales, Mariuxi Cardenas-Cobo, Jesennia Cabezas-Quinto, Jessica Vidal-Silva, Cristian Univ Estatal Milagro Fac Ciencias Ingn Milagro 091050 Ecuador Univ Talca Escuela Ingn Desarrollo Videojuegos & Real Virtual Fac Ingn Talca 3460000 Chile

The information society is part of modern life, and algorithmic thinking and programming are relevant to everybody, regardless of educational background. Today's world needs professionals with computing competencies. Higher education programming classes usually use text-based programming languages to develop programming competencies, usually without success for all students. Traditional programming languages consider syntax barriers that complicate their adoption and usefulness for students. Block-based programming languages such as SCRATCH and ALICE permit the development of programming competencies without text coding and syntax restrictions to solve that issue. There are different research works on SCRATCH experiences, but not many experiences on how to use ALICE overall in higher education. This article aims to evaluate the effectiveness of the ALICE programming language in enhancing programming learning outcomes for university students and addressing the limited number of empirical studies of ALICE in higher education contexts. The research involved a literature review to provide a theoretical foundation, followed by an experimental phase that involved two groups: the control group, which followed the traditional programming instruction method with a text-based programming language, and the experimental group, which used the block-based ALICE environment. The experimental group achieved better results with an average score of 80, while the control group scored 65 points on a 100-point scale. The results obtained highlight the effectiveness of the ALICE environment in supporting the programming learning process for first-level Software Engineering university students.

关键词： programming programming profession Education Computer languages Java Syntactics Problem-solving programming environments Object oriented programming Surveys programming competencies programming teaching programming learning block-based programming language ALICE

来源：评论

学校读者我要写书评

暂无评论

MagicItem: Dynamic Behavior Design of Virtual Objects With Large Language Models in a Commercial Metaverse Platform

引用

IEEE ACCESS 2025年 13卷 19132-19143页

作者： Kurai, Ryutaro Hiraki, Takefumi Hiroi, Yuichi Hirao, Yutaro Perusquia-Hernandez, Monica Uchiyama, Hideaki Kiyokawa, Kiyoshi Cluster Inc Shinagawa Tokyo 1410031 Japan Nara Inst Sci & Technol Grad Sch Sci & Technol Ikoma Nara 6300192 Japan Cluster Metaverse Lab Shingawa Tokyo 1410031 Japan Univ Tsukuba Inst Lib Informat & Media Sci Tsukuba Ibaraki 3058550 Japan

To create rich experiences in virtual reality (VR) environments, it is essential to define the behavior of virtual objects through programming. However, programming in 3D spaces requires a wide range of background knowledge and programming skills. Although Large Language Models (LLMs) have provided programming support, they are still primarily aimed at programmers. In metaverse platforms, where many users inhabit VR spaces, most users are unfamiliar with programming, making it difficult for them to modify the behavior of objects in the VR environment easily. Existing LLM-based script generation methods for VR spaces require multiple lengthy iterations to implement the desired behaviors and are difficult to integrate into the operation of metaverse platforms. To address this issue, we propose a tool that generates behaviors for objects in VR spaces from natural language within Cluster, a metaverse platform with a large user base. By integrating LLMs with the Cluster Script provided by this platform, we enable users with limited programming experience to define object behaviors within the platform freely. We have also integrated our tool into a commercial metaverse platform and are conducting online experiments with 63 general users of the platform. The experiments show that even users with no programming background can successfully generate behaviors for objects in VR spaces, resulting in a highly satisfying system. Our research contributes to democratizing VR content creation by enabling non-programmers to design dynamic behaviors for virtual objects in metaverse platforms.

关键词： Metaverse Codes Three-dimensional displays Natural languages Aerospace electronics Web servers Usability programming profession Hands Large-language model low-code programming metaverse platform virtual reality virtual reality

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：