期刊文献+
任意字段
题名或关键词
题名
关键词
摘要
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息
共找到191篇文章
< 1 2 … 10 >
每页显示 20 50 100
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
显示方式：
QIMIG:A Quantum-Inspired Evolutionary Framework for Software Library Migration 认领 引用
1
作者 Yun Liu Jinghua Zhao +3 位作者 Liang Ma Zijie Huang Lizhi Cai Jianxin Ge 《Computers, Materials & Continua》 SCIE EI 2026年第9期795-812,共18页
Automated library migration reduces refactoring costs but challenges traditional evolutionary algorithms,which often suffer from premature convergence and poor recall in sparse,complex API mapping spaces.To address th... Automated library migration reduces refactoring costs but challenges traditional evolutionary algorithms,which often suffer from premature convergence and poor recall in sparse,complex API mapping spaces.To address this,we propose QIMIG,a multi-objective optimization framework integrating quantum-inspired encoding with quality-aware and greedy heuristic filtering.QIMIG utilizes a probabilistic Q-bit representation to maintain population diversity and avoid local optima.Simultaneously,its heuristic components leverage historical usage context to filter semantic noise and guide the search toward valid mappings.Evaluated on 9 real-world migration rules derived from 57,447 open-source projects,QIMIG statistically significantly outperforms state-of-the-art baselines such as UNSGA-III.The framework achieves a global mean F1-score of 0.92,exceeding the best-performing baseline by an absolute margin of 0.05,and demonstrates strong stability in resolving complex mapping structures. 展开更多
关键词 Library migration API mapping search-based software engineering quantum-inspired evolutionary algorithm multi-objective optimization
暂未订购 下载PDF
Exploring Reform Strategies for Software Engineering Talent Development Models in the AI Era 认领 引用
2
作者 Linying Jiang Guibing Guo +1 位作者 Jianzhe Zhao Xiaochun Yang 《计算机教育》 2026年第3期95-100,共6页
The rapid development of artificial intelligence(AI)has placed significant pressure on universities to rethink how they train software engineering students.Tools like GitHub Copilot can now generate basic code in seco... The rapid development of artificial intelligence(AI)has placed significant pressure on universities to rethink how they train software engineering students.Tools like GitHub Copilot can now generate basic code in seconds.This raises important questions:What is the value of traditional programming education?What role should instructors play when AI becomes a powerful teaching assistant?How should the goals of software engineering programs change as companies increasingly use AI to handle coding tasks?This paper explores the key challenges AI brings to software engineering education and proposes practical strategies for updating talent development models to meet these changes. 展开更多
关键词 Artificial intelligence Software engineering education Talent development Reform strategies
暂未订购 下载PDF
Developing Innovation Capacity in Graduate Software Engineering Practice Through Newquality Productive Forces 认领 引用
3
作者 Ting Cai Tianyuan Yin +2 位作者 Yuxin Wu Shan Lin Zhiwei Ye 《计算机教育》 2026年第3期220-229,共10页
The rapid development of new-quality productive forces(NQPF)has intensified the demand for high-level innovative talent.As a representative of NQPF,generative artificial intelligence(GenAI)offers powerful tools to res... The rapid development of new-quality productive forces(NQPF)has intensified the demand for high-level innovative talent.As a representative of NQPF,generative artificial intelligence(GenAI)offers powerful tools to reshape talent cultivation but also presents significant challenges,including skill hollowing,ethical risks,and a growing disconnect between education and industry needs.Currently,graduate-level software engineering education struggles with outdated curricula and insufficient alignment with practical demands.In this paper,we propose a dual-core collaborative framework driven by“GenAI technology”and“industry demand”.Under this framework,we design a four-dimensional capability development path to enhance graduate students’innovation in software engineering practice.This path focuses on①scientific research innovation,②engineering problem-solving,③cross-domain collaborative evolution,and④ethical risk governance.The proposed approach promotes a shift from traditional knowledge transfer to human-machine collaborative innovation,aligning talent cultivation with the demands of the NQPF. 展开更多
关键词 New-quality productive forces GenAI Graduate student Software engineering Innovation ability
暂未订购 下载PDF
Research on the Construction of a software engineering course knowledge graph empowered by the Xhang AI teaching assistant 认领 引用
4
作者 Xuefei Huang Yiming Gai +3 位作者 Ying Li Hao Sheng Da Yang Yingying Zhang 《计算机教育》 2026年第6期221-228,共8页
In view of the needs and challenges of digital transformation in the field of education under the background ofªnew engineeringº,this paper analyzes how to improve the teaching efficiency of software enginee... In view of the needs and challenges of digital transformation in the field of education under the background ofªnew engineeringº,this paper analyzes how to improve the teaching efficiency of software engineering course programming and realize personalized guidance through the large language models,and proposes to use the multi-channel feedback optimization technology of Xhang AI assistant to extract and construct the multimodal knowledge graph of the adaptive course,and realize the personalized fine-tuning of the model combined with the private data collaborative sharing platform,so as to enhance the accuracy and applicability of the knowledge graph of software engineering course.The automatic construction and updating of curriculum knowledge graph based onªXhang AI assistantºcan cover a wider range of educational courses and fields,and promote the development of intelligent and digital education. 展开更多
关键词 Xhang AI assistant Large language model Multimodal knowledge graph Digital strategy Software engineering
暂未订购 下载PDF
Exploration and Practice of School-Enterprise Cooperation Model of Software Engineering Majors from Multi-Perspectives 认领 引用
5
作者 Linpeng Zhong Yong Liao 《计算机教育》 2026年第3期38-46,共9页
Promoting the integration of industry and education and deepening school-enterprise cooperation in talent cultivation and collaborative innovation are long-term goals of higher education.This paper systematically anal... Promoting the integration of industry and education and deepening school-enterprise cooperation in talent cultivation and collaborative innovation are long-term goals of higher education.This paper systematically analyzes the multiple perspectives,practical challenges,and implementation paths of in-depth school-enterprise cooperation.Based on the typical case of school-enterprise cooperation at the School of Information and Software Engineering,University of Electronic Science and Technology of China(UESTC),this paper explores the innovative practices of in-depth school-enterprise cooperation in talent cultivation,scientific research,and faculty construction.It also explores a multi-party collaborative mechanism from the perspectives of universities,enterprises,students,and the government.By policy guidance,resource integration,and benefit sharing,this mechanism achieves in-depth integration of industry and education,providing references and examples for further development of school-enterprise cooperation in the new era. 展开更多
关键词 Software engineering School-enterprise cooperation Integration of industry and education Collaborative talent cultivation Multi-perspective analysis
暂未订购 下载PDF
PCER:A dynamic feedback model for optimizing graduate student training in software engineering 认领 引用
6
作者 Bangchao Wang Yuyang Dai +2 位作者 Hongyan Wan Xinrong Hu Xiong Wei 《计算机教育》 2026年第6期330-342,共13页
Under the national innovation-driven development strategy and the emerging need for new engineering education,the cultivation of high-quality software engineering talent faces increasingly stringent requirements.To ad... Under the national innovation-driven development strategy and the emerging need for new engineering education,the cultivation of high-quality software engineering talent faces increasingly stringent requirements.To address critical challenges in the current graduate training model at regional universities,including fragmented undergraduate-to-graduate transition,ambiguous competency development pathways,and structural deficiencies in teaching resources,this paper proposes a novel PCER(Plan-Carry Out-Evaluate-Refine)dynamic feedback model for software engineering graduate education.The PCER framework establishes phased training objectives,develops an adaptive multi-level resource repository,and implements a multidimensional evaluation mechanism.Empirical results demonstrate that the model significantly enhances students'academic innovation capabilities and engineering practice competencies,providing a replicable reform path for the cultivation of software engineering talents.The PCER approach offers a transferable solution for engineering education reform,particularly for institutions facing similar resource constraints and quality improvement challenges. 展开更多
关键词 Software engineering Training model Graduate education Teaching resources
暂未订购 下载PDF
Educational practice in software engineering empowered by generative AI and virtual humans 认领 引用
7
作者 Yingying Zhang Runze Liu +5 位作者 Hao Sheng Xudong Li Ying Li Haogang Zhu Da Yang Xuefei Huang 《计算机教育》 2026年第6期213-220,共8页
The rapid advancement of information technology catalyzes the digital transformation of education,urging the education sector to adapt to technological changes actively.Focusing on the dual-engine drive of large model... The rapid advancement of information technology catalyzes the digital transformation of education,urging the education sector to adapt to technological changes actively.Focusing on the dual-engine drive of large models and digital human technologies,we innovate across multiple dimensions to reconstruct the software engineering curriculum system.We build multimodal teaching frameworks and personalized learning paths to break through traditional limitations,establish a digital and intelligent course resource supermarket for precise service supply,integrate smart classrooms with blended learning to reshape teaching spaces,and create an all-process digital and intelligent evaluation system to revolutionize assessment and feedback mechanisms.By deeply integrating intelligent technologies into the entire education process,we enhance software engineering course quality and offer new ideas and practical pathways for educational reform. 展开更多
关键词 Large language models Digital human technology Digital education Software engineering
暂未订购 下载PDF
Unrestricted AI assistants hinder learning:A three-year longitudinal study in software engineering education 认领 引用
8
作者 Botao Wang Jing Luo Xinnian Wang 《计算机教育》 2026年第6期355-359,共5页
The rapid integration of AI programming assistants(AIPAs)into education raises critical questions about their impact on student learning.This study conducts an exploratory three-year longitudinal quasi-experiment in a... The rapid integration of AI programming assistants(AIPAs)into education raises critical questions about their impact on student learning.This study conducts an exploratory three-year longitudinal quasi-experiment in an introductory software engineering course,comparing a cohort with unrestricted AI access(n=21)against two control cohorts without AI(n=24).Results show a significant performance decline in the AI-assisted group,with a mean final examination score(M=58.8)over 20 points lower than the control groups'stable baseline(M=79.2),a statistically significant difference(p<0.001).This suggests that unguided AI use may encourageªcognitive offloadingº,bypassing critical thinking and leading to superficial learning.The performance gap widens with diverse,high-order examination tasks,where AI-dependent students struggle in closedbook settings.The study concludes that the educational potential of AI requires careful integration with pedagogical guardrails,which serves as a cognitive scaffold rather than an answer machine,pending further validation. 展开更多
关键词 Software engineering education AI-assisted learning Quasi-experimental study Cognitive offloading Academic performance Pedagogy
暂未订购 下载PDF
Economic value and management pathways of China-Europe software engineering education cooperation under the belt and road initiative 认领 引用
9
作者 Xinyue Liu Xiao Zheng Zhiwei Ye 《计算机教育》 2026年第6期272-279,共8页
Amid the in-depth advancement of the Belt and Road Initiative and the rapid development of the global digital economy,cross-border cooperation in software engineering education between China and Europe has emerged as ... Amid the in-depth advancement of the Belt and Road Initiative and the rapid development of the global digital economy,cross-border cooperation in software engineering education between China and Europe has emerged as a pivotal strategy for enhancing regional digital economic competitiveness.This paper aims to systematically analyze the promotion mechanisms of such cooperation and its impact on regional digital economic development.It will also explore key management issues,including intellectual property protection and the mutual recognition of standards within cross-border educational collaborations.Furthermore,the paper will propose strategies for enhancing international industrial competitiveness through educational partnerships.The research seeks to provide both theoretical and practical insights to deepen China-Europe cooperation in software engineering education and unlock the full potential of the digital economy. 展开更多
关键词 The Belt and Road Initiative China-Europe software engineering education Crossborder Digital economy Intellectual property Standardization Industrial competitiveness
暂未订购 下载PDF
Artificial intelligence empowering software engineering education:Opportunities,challenges,and future prospects 认领 引用
10
作者 Chunwei Tian Hengxin Qiu +1 位作者 Qi Zhu Jianfang Hu 《计算机教育》 2026年第6期292-301,共10页
As a core field of information technology,the quality of software engineering education directly impacts the development of the future software industry.Current pedagogy,however,faces critical challenges including rap... As a core field of information technology,the quality of software engineering education directly impacts the development of the future software industry.Current pedagogy,however,faces critical challenges including rapid knowledge obsolescence,inadequate practical skill development,limited personalization,and complex assessment.This paper systematically explores AI's transformative potential in this domain,proposing an application framework that addresses content innovation,skill cultivation,and assessment optimization.We critically analyze implementation opportunities while addressing technical constraints,pedagogical adaptations,and ethical considerations.The contribution of this paper lies in providing a macroscopic and forwardlooking theoretical analysis framework,which offers references for in-depth research and practice of AI in the field of software engineering education. 展开更多
关键词 Artificial intelligence Software engineering education Teaching reform Practical skills Learning assessment
暂未订购 下载PDF
Research and Implementation of the Academic Development Monitoring System for High-quality Software Engineering Talents 认领 引用
11
作者 Kun Niu Kaiyang Zhang +5 位作者 Tan Yang Hui Gao Hongfeng Gu Ting Diao Jing Li Honglin Fu 《计算机教育》 2026年第3期199-209,共11页
Traditional grade-centered evaluation models are inadequate for high-quality software engineering talents in the digital and AI era.This study develops an academic development monitoring system to address shortcomings... Traditional grade-centered evaluation models are inadequate for high-quality software engineering talents in the digital and AI era.This study develops an academic development monitoring system to address shortcomings in dynamics,interdisciplinary integration,and industry adaptability.It builds a multi-dimensional dynamic model covering seven core dimensions with quantitative scoring,non-linear weighting,and DivClust grouping.An intelligent platform with real-time monitoring,early warning,and personalized recommendations integrates AI like multi-modal fusion and large-model diagnosis.The“monitoring-warning-improvement”loop helps optimize training programs,support personalized planning,and bridge talent-industry gaps,enabling digital transformation in software engineering education evaluation. 展开更多
关键词 Software engineering talents Academic development monitoring Multi-dimensional dynamic evaluation Intelligent monitoring platform AI-driven evaluation Industry adaptability
暂未订购 下载PDF
OSSerCopilot:An LLM-driven Tutoring System for Fostering Open Source Competency in Software Engineering Education 认领 引用
12
作者 Xin Tan Jingyi Tan +4 位作者 Weimiao Ren Keqing Fan Xiao Long Fang Liu Li Zhang 《计算机教育》 2026年第3期119-129,共11页
In the context of large language model(LLM)reshaping software engineering education,this paper presents OSSerCopilot,a LLM-based tutoring system designed to address the critical challenge faced by newcomers(especially... In the context of large language model(LLM)reshaping software engineering education,this paper presents OSSerCopilot,a LLM-based tutoring system designed to address the critical challenge faced by newcomers(especially student contributors)in open source software(OSS)communities.Leveraging natural language processing,code semantic understanding,and learner profiling,the system functions as an intelligent tutor to scaffold three core competency domains:contribution guideline interpretation,project architecture comprehension,and personalized task matching.By transforming traditional onboarding barriers-such as complex contribution documentation and opaque project structures-into interactive learning journeys,OSSerCopilot enables newcomers to complete their first OSS contribution more easily and confidently.This paper highlights how LLM technologies can redefine software engineering education by bridging the gap between theoretical knowledge and practical OSS participation,offering implications for curriculum design,competency assessment,and sustainable OSS ecosystem cultivation.A demonstration video of the system is available at http://gffzz6169854dd1504498sqpqok0w6ofbp6vvn.ffgz.tsg.suse.edu.cn/articles/media/OSSerCopilot_Introduction_mp4/29510276. 展开更多
关键词 Software engineering education Open source software education Intelligent tutoring systems Newcomer onboarding Large language models AI-driven educational tools OSS contribution
暂未订购 下载PDF
Research and Practice of a New Training Model for Software Engineering Courses Based on Generative AI and OBE Concepts 认领 引用
13
作者 Shengshai Zhang Xiaodong Yu +1 位作者 Jianhui Jiang Lixiao Zhang 《计算机教育》 2026年第3期139-147,共9页
With the advent of the AI era,how can students effectively utilize generative AI large models to assist in course learning?At the same time,how can teachers utilize generative AI tools and the teaching concept of OBE ... With the advent of the AI era,how can students effectively utilize generative AI large models to assist in course learning?At the same time,how can teachers utilize generative AI tools and the teaching concept of OBE to stimulate students’innovative consciousness and teamwork ability,enabling students to identify some problems in a certain industry or field and creatively propose feasible solutions,and truly achieve the cultivation of new models in software engineering course teaching with the assistance of generative AI tools?This paper presents research and practice on a new model for cultivating software engineering courses that integrates generative AI and OBE,introduces the specific process of teaching reform and practice,and finally explains the achievements of teaching reform. 展开更多
关键词 Generative AI OBE Software engineering Teaching reform
暂未订购 下载PDF
OBE-based design pattern for software engineering education:An empirical study 认领 引用
14
作者 Runkun Zhang Mingyu Tang +1 位作者 Renyu Yang Yilong Yang 《计算机教育》 2026年第6期343-354,共12页
In response to the problem that students'feedback on software engineering courses does not meet expectations,this paper focuses on analyzing the problems of the existing fundamentals of software engineering course... In response to the problem that students'feedback on software engineering courses does not meet expectations,this paper focuses on analyzing the problems of the existing fundamentals of software engineering courses and the corresponding experimental and practical training courses.Based on the concept of outcome-based education,combined with previous course teaching practices,student course feedback,and new experimental and practical training course design methods provided by the online teaching platform,this paper elaborates on how to modify the corresponding course syllabus and training program,explains the achievements of the curriculum reform,and discusses the software engineering course reform pattern based on the common problems of students. 展开更多
关键词 Outcome-based education Software engineering Software engineering education
暂未订购 下载PDF
AI-generated code detection for software engineering education:Benchmarks and a real-world case study 认领 引用
15
作者 Hang Gao Jiajia Wu +3 位作者 Xinqi Yang Rongbo Xiao Mingming Liu Mengting Hu 《计算机教育》 2026年第6期312-321,共10页
The rise of artificial intelligence(AI)has advanced automated code generation.At the same time,it has raised new concerns about academic integrity in software engineering education.Previous studies have explored AI-ge... The rise of artificial intelligence(AI)has advanced automated code generation.At the same time,it has raised new concerns about academic integrity in software engineering education.Previous studies have explored AI-generated code detection using pre-trained code models.However,systematic evaluations across different types of models are still limited.This study presents a two-part empirical investigation.We benchmark four representative pre-trained models,including two language models(BERT and Ro BERTa)and two code models(Code BERT and Uni Xcoder),on AI-generated code detection tasks using Java and Python datasets.Results show that Uni Xcoder achieves the best overall detection performance.Pre-trained language models also demonstrate robustness under certain post-processing conditions.From an overall perspective,robust detection of AI-generated code remains an unresolved challenge in software engineering education.We further apply the best-performing detector to real-world student programming assignments collected from 2021 to 2024.Trend analysis reveals patterns that align with the increasing adoption of generative AI tools in student submissions.Our findings highlight both the strengths and limitations of current detectors.They also demonstrate the potential of such tools for monitoring generative AI usage in software engineering education.Our code and data are released at http://gffzz188fe103f8f1460asqpqok0w6ofbp6vvn.ffgz.tsg.suse.edu.cn/gaohangcodes/AIGCode Detect Benchmark. 展开更多
关键词 AI-generated code detection Pre-trained models Software engineering education
暂未订购 下载PDF
A Multi-Role AI Agent for Project-Driven Teaching Practice in Software Engineering 认领 引用
16
作者 Yan Yan Runxia Ding +1 位作者 Hui Zhang Wanjun Wang 《Journal of Contemporary Educational Research》 2026年第7期219-224,共6页
To address the pain points in traditional software engineering teaching, such as disconnected learning scenarios and limited effectiveness of project-driven teaching, this study designs and implements a multi-role AI ... To address the pain points in traditional software engineering teaching, such as disconnected learning scenarios and limited effectiveness of project-driven teaching, this study designs and implements a multi-role AI Agent named SE_Coach. It simulates roles in software development, such as product managers, and guides students through heuristic questioning and situational simulation. A 16-week controlled experiment was conducted with 80 junior computer science students. The experimental group adopted a model of teacher guidance + AI agent + group collaboration, while the control group used traditional group collaboration. The results show that the experimental group had significantly better self-efficacy and project outcome quality. SE_Coach effectively improves students’ practical abilities and collaborative thinking, providing a feasible paradigm for AI-empowered software engineering teaching. 展开更多
关键词 Software engineering AI agent Project-driven teaching Constructivist learning theory Practical capability
暂未订购 下载PDF
Research on the Construction of Post Competency Model and Competency Map for Software Engineering Major under the Background of Emerging Engineering Education 认领 引用
17
作者 Shizhong Hou Lei Du +1 位作者 Chuanlei Song Wanjun Wang 《Journal of Contemporary Educational Research》 2026年第5期134-139,共6页
Against the background of the deep integration of Emerging Engineering Education construction and digital economy,to address the challenges of vague competency standards and fragmented training paths in software engin... Against the background of the deep integration of Emerging Engineering Education construction and digital economy,to address the challenges of vague competency standards and fragmented training paths in software engineering talent cultivation,this study first constructs a quantifiable post competency model using the Onion Model as the framework,combined with the Delphi method and coefficient of variation method.Furthermore,based on this model,a three-level progressive competency map of“Basic Competency-Professional Competency-Innovative Application Competency”is designed and refined into observable training indicators throughout the four-year undergraduate program.The research results lay a foundation for the precise industry-education connection and the subsequent construction of smart courses. 展开更多
关键词 Emerging Engineering Education Post competency Competency map Software engineering Delphi method
暂未订购 下载PDF
Construction and Practice of Ideological and Political Teaching Mode for Software Engineering Courses Based on the Integration of Online and Offline 认领 引用
18
作者 HU Guanlin DING Fuxing 《外文科技期刊数据库（文摘版）教育科学》 2026年第2期045-049,共5页
In view of the problems such as insufficient element mining and the separation of online and offline education in ideological and political teaching of software engineering courses, this paper proposes and designs an ... In view of the problems such as insufficient element mining and the separation of online and offline education in ideological and political teaching of software engineering courses, this paper proposes and designs an integrated online and offline teaching model. The educational goal of integrating knowledge imparting, ability development and value shaping was clearly established, and the correspondence between ideological and political elements and professional knowledge was comprehensively sorted out. The online session led values by building a resource library embedded with ideological and political cases and conducting thematic discussions. Offline classes, on the other hand, rely on case-based teaching and project-driven approaches to shape professionalism and use scenario simulations to enhance awareness of the rule of law and ethics. This model efficiently promotes the connection of teaching links and the establishment of a closed loop of education, enhancing students' professional skills while significantly improving their ideological and political qualities. 展开更多
关键词 Online and offline integration Course-based ideological and political education Teaching mode Software engineering Ideological and political elements
暂未订购 下载PDF
Exploration of the Training Model for Excellent Scientific and Technological Innovation Talents in Software Engineering Bridging Undergraduate and Graduate Studies 认领 引用
19
作者 Lifeng Yin Zhen Liu 《Journal of Contemporary Educational Research》 2026年第4期222-232,共11页
Against the backdrop of the digital economy and the construction of emerging engineering disciplines,this paper proposes and constructs a training model for excellent scientific and technological innovation talents,br... Against the backdrop of the digital economy and the construction of emerging engineering disciplines,this paper proposes and constructs a training model for excellent scientific and technological innovation talents,bridging undergraduate and graduate studies in software engineering,characterized by“integrated objectives,project-driven learning,and the integration of science and education.”This model aims to cultivate outstanding scientific and technological innovation talents as its overall goal,achieving seamless integration of undergraduate and graduate ability cultivation through the construction of a hierarchical and progressive objective system.It establishes a comprehensive five-level progressive project training system to bridge the gap between undergraduate practice and graduate research,and sets up a deeply integrated mechanism for the collaboration of science,education,and industry to promote the transformation of scientific research and industrial resources into teaching.Additionally,it improves the support system from three aspects:institutional frameworks,evaluation,and incentives.The study also outlines a five-stage practical path:“top-level design-resource integration-pilot operation-comprehensive promotion-dynamic optimization.”This model effectively breaks down the barriers between undergraduate and graduate training,strengthens students’scientific research innovation and engineering practice abilities,and provides a replicable practical paradigm for the training of scientific and technological innovation talents bridging undergraduate and graduate studies in engineering disciplines. 展开更多
关键词 Bridging undergraduate and graduate studies Software engineering Excellent scientific and technological innovation talents Integrated objectives Project-driven learning Integration of science and education
暂未订购 下载PDF
Software Defect Prediction Based on Semantic Views of Metrics:Clustering Analysis and Model Performance Analysis 认领 引用
20
作者 Baishun Zhou Haijiao Zhao +4 位作者 Yuxin Wen Gangyi Ding Ying Xing Xinyang Lin Lei Xiao 《Computers, Materials & Continua》 SCIE EI 2025年第9期5201-5221,共21页
In recent years,with the rapid development of software systems,the continuous expansion of software scale and the increasing complexity of systems have led to the emergence of a growing number of software metrics.Defe... In recent years,with the rapid development of software systems,the continuous expansion of software scale and the increasing complexity of systems have led to the emergence of a growing number of software metrics.Defect prediction methods based on software metric elements highly rely on software metric data.However,redundant software metric data is not conducive to efficient defect prediction,posing severe challenges to current software defect prediction tasks.To address these issues,this paper focuses on the rational clustering of software metric data.Firstly,multiple software projects are evaluated to determine the preset number of clusters for software metrics,and various clustering methods are employed to cluster the metric elements.Subsequently,a co-occurrence matrix is designed to comprehensively quantify the number of times that metrics appear in the same category.Based on the comprehensive results,the software metric data are divided into two semantic views containing different metrics,thereby analyzing the semantic information behind the software metrics.On this basis,this paper also conducts an in-depth analysis of the impact of different semantic view of metrics on defect prediction results,as well as the performance of various classification models under these semantic views.Experiments show that the joint use of the two semantic views can significantly improve the performance of models in software defect prediction,providing a new understanding and approach at the semantic view level for defect prediction research based on software metrics. 展开更多
关键词 Software defect prediction software engineering semantic views clustering interpretability
暂未订购 下载PDF
已选0条
引用分析
参考文献
引证文献
 统计分析
检索结果
已选文献
上一页 1 2 … 10 下一页 到第 页
在线咨询 使用帮助 返回顶部 意见反馈