With the rapid development of artificial intelligence,the intelligence level of software is increasingly improving.Intelligent software,which is widely applied in crucial fields such as autonomous driving,intelligent ...With the rapid development of artificial intelligence,the intelligence level of software is increasingly improving.Intelligent software,which is widely applied in crucial fields such as autonomous driving,intelligent customer service,and medical diagnosis,is constructed based on complex technologies like machine learning and deep learning.Its uncertain behavior and data dependence pose unprecedented challenges to software testing.However,existing software testing courses mainly focus on conventional contents and are unable to meet the requirements of intelligent software testing.Therefore,this work deeply analyzed the relevant technologies of intelligent software testing,including reliability evaluation indicator system,neuron coverage,and test case generation.It also systematically designed an intelligent software testing course,covering teaching objectives,teaching content,teaching methods,and a teaching case.Verified by the practical teaching in four classes,this course has achieved remarkable results,providing practical experience for the reform of software testing courses.展开更多
Background:Despite the promise shown by large language models(LLMs)for standardized tasks,their multidimensional performance in real-world oncology decision-making remains unevaluated.This study aims to introduce a fr...Background:Despite the promise shown by large language models(LLMs)for standardized tasks,their multidimensional performance in real-world oncology decision-making remains unevaluated.This study aims to introduce a framework for evaluating LLMs and physician decisions in challenging lung cancer cases.Methods:We curated 50 challenging lung cancer cases(25 local and 25 published)classified as complex,rare,or refractory.Blinded three-dimensional,five-point Likert evaluations(1–5 for comprehensiveness,specificity,and readability)compared standalone LLMs(DeepSeek R1,Claude 3.5,Gemini 1.5,and GPT-4o),physicians by experience level(junior,intermediate,and senior),and AI-assisted juniors;intergroup differences and augmentation effects were analyzed statistically.Results:Of 50 challenging cases(18 complex,17 rare,and 15 refractory)rated by three experts,DeepSeek R1 achieved scores of 3.95±0.33,3.71±0.53,and 4.26±0.18 for comprehensiveness,specificity,and readability,respectively,positioning it between intermediate(3.68,3.68,3.75)and senior(4.50,4.64,4.53)physicians.GPT-4o and Claude 3.5 reached intermediate physician–level comprehensiveness(3.76±0.39,3.60±0.39)but junior-to-intermediate physician–level specificity(3.39±0.39,3.39±0.49).All LLMs scored higher on rare cases than intermediate physicians but fell below junior physicians in refractory-case specificity.AIassisted junior physicians showed marked gains in rare cases,with comprehensiveness rising from 2.32 to 4.29(84.8%),specificity from 2.24 to 4.26(90.8%),and readability from 2.76 to 4.59(66.0%),while specificity declined by 3.2%(3.17 to 3.07)in refractory cases.Error analysis showed complementary strengths,with physicians demonstrating reasoning stability and LLMs excelling in knowledge updating and risk management.Conclusions:LLMs performed variably in clinical decision-making tasks depending on case type,performing better in rare cases and worse in refractory cases requiring longitudinal reasoning.Complementary strengths between LLMs and physicians support case-and task-tailored human–AI collaboration.展开更多
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 https://figshare.com/articles/media/OSSerCopilot_Introduction_mp4/29510276.展开更多
Heavy-ion collisions(HICs)is a unique experimental tool for investigating the properties of nuclear matter under extreme conditions in the laboratory.At HIRFL-CSR energies,HICs can create nuclear matter with 2-3 times...Heavy-ion collisions(HICs)is a unique experimental tool for investigating the properties of nuclear matter under extreme conditions in the laboratory.At HIRFL-CSR energies,HICs can create nuclear matter with 2-3 times the saturation density(ρ_(0)).The HIRFL-CSR external-target experiment(CEE)is a large-acceptance spectrometer designed to explore frontier topics in high-energy nuclear physics,such as the QCD phase structure and nuclear matter equation of states.In this letter,we introduce simulation and analysis software for the CEE experiment(CeeROOT).Based on the CEE conceptual design and CeeROOT software,the configurations of its subdetectors were optimized by considering foreseeable physical constraints.The final detector layout of the CEE spectrometer and its acceptances were validated through simulations of U+U collisions at 500 MeV/u and pp collisions at 2.8 GeV,which demonstrated that the CEE experiment will serve as a detector with wide acceptance and multi-particle identification capabilities for studying high-energy nuclear physics topics at HIRFL-CSR energies with pp,pA,and A A collisions.展开更多
While parametric Software Reliability Growth Models(SRGMs)serve as a cornerstone in software reliability assessment,their reliance on known fault-detection time distributions often presents a significant limitation in...While parametric Software Reliability Growth Models(SRGMs)serve as a cornerstone in software reliability assessment,their reliance on known fault-detection time distributions often presents a significant limitation in practical software testing.In this study,the authors develop a novel shaperestricted spline estimator for quantifying software reliability.Compared with parametric SRGMs,the proposed estimator not only shares a key characteristic with parametric SRGMs,but also obviates the need for specifying fault-detection time distributions.More importantly,it effectively utilizes the critical shape information of the mean value function(MVF)of fault-detection process,a detail seldom considered in prior work.Moreover,the authors investigate the predictive performance of the proposed methods by employing the so-called one-step look-ahead prediction method.Furthermore,the authors show that under certain conditions,the shape-restricted spline estimator will attain the point-wise convergence rate O_P(n~(-3/7)).In numerical experiment,the authors show that spline estimators under restriction demonstrate competitive performance compared to parametric and certain non-parametric models.展开更多
In the modern era of ubiquitous and highly interconnected information technology,cybersecurity threats stemming from software code vulnerabilities have become increasingly severe,posing significant risks to the confid...In the modern era of ubiquitous and highly interconnected information technology,cybersecurity threats stemming from software code vulnerabilities have become increasingly severe,posing significant risks to the confidentiality,integrity,and availability of modern information systems.To enhance software code quality,enterprises often integrate static code analysis tools into Continuous Integration(CI) pipelines.However,the high rates of false positives and false negatives remain a challenge.The advent of large language models(LLMs),such as ChatGPT,presents a new opportunity to address these challenges.In this paper,we propose AI-SCDF,a framework that utilizes the custombuilt Nebula-Coder AI model for detecting and fixing code security issues in real time during the developer ' s personal build process.We construct a static code checking rule knowledge base through summarizing and classifying Common Weakness Enumeration(CWE) code security problems identified by security and quality assurance teams.The rule knowledge base is combined with CodeFuse-processed code contexts to serve as input for an AI code security detection microservice,which assists in identifying code quality and security issues.If any abnormalities are detected,they are addressed by an AI code security patching microservice,which alerts the developer and requests confirmation before committing the code into the repository.Experimental results show that our approach effectively improves code quality.We also develop a VS Code plugin for code alert detection and fix based on LLMs,which facilitates test shift-left and lowers the risk of software development.展开更多
Environmental problems are intensifying due to the rapid growth of the population,industry,and urban infrastructure.This expansion has resulted in increased air and water pollution,intensified urban heat island effect...Environmental problems are intensifying due to the rapid growth of the population,industry,and urban infrastructure.This expansion has resulted in increased air and water pollution,intensified urban heat island effects,and greater runoff from parks and other green spaces.Addressing these challenges requires prioritizing green infrastructure and other sustainable urban development strategies.This study introduces a novel Integrated Decision Support System that combines Pythagorean Fuzzy Sets with the Advanced Alternative Ranking Order Method allowing for Two-Step Normalization(AAROM-TN),enhanced by a dual weighting strategy.The weighting approach integrates the Criteria Importance Through Intercriteria Correlation(CRITIC)method with the Criteria Importance through Means and Standard Deviation(CIMAS)technique.The originality of the proposed framework lies in its ability to objectively quantify criteria importance using CRITIC,incorporate decision-makers’preferences through CIMAS,and capture the uncertainty and hesitation inherent in human judgment via Pythagorean Fuzzy Sets.A case study evaluating green infrastructure alternatives in metropolitan regions demonstrates the applicability and effectiveness of the framework.A sensitivity analysis is conducted to examine how variations in criteria weights affect the rankings and to evaluate the robustness of the results.Furthermore,a comparative analysis highlights the practical and financial implications of each alternative by assessing their respective strengths and weaknesses.展开更多
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
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
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
With the rapid development of artificial intelligence,intelligent air combat maneuver decision-making(ACMD)has garnered global attention.Although deep reinforcement learning provides a promising approach to ACMD,exist...With the rapid development of artificial intelligence,intelligent air combat maneuver decision-making(ACMD)has garnered global attention.Although deep reinforcement learning provides a promising approach to ACMD,existing methods often suffer from rigid reward functions and limited adaptability to evolving adversarial strategies.Moreover,most research assumes open airspace,overlooking the influence of potential obstacles.In this paper,we address one-on-one within-visual-range ACMD in obstructed environments,and propose an improved Soft Actor-Critic(SAC)algorithm trained under a curriculum self-play framework.A maneuver strategy mirroring inference module is integrated to estimate each other's likely positions when visual obstruction occurs.By leveraging curriculum learning to guide progressive experience accumulation and self-play for adversarial evolution,our method enhances both training efficiency and tactical diversity.We further integrate an attention mechanism that dynamically adjusts the weights of sub-rewards,enabling the learned policy to adapt to rapidly changing air combat situations.Numerical simulations demonstrate that our enhanced SAC converges more quickly and achieves higher win rates than other baseline methods.An animation is available at bilibili.com/video/BV1BHVszHE98 for better illustration.展开更多
With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance s...With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance strategies often struggle to accurately predict the degradation process of equipment,leading to excessive maintenance costs or potential failure risks.However,existing prediction methods based on statistical models are difficult to adapt to nonlinear degradation processes.To address these challenges,this study proposes a novel condition-based maintenance framework for planetary gearboxes.A comprehensive full-lifecycle degradation experiment was conducted to collect raw vibration signals,which were then processed using a temporal convolutional network autoencoder with multi-scale perception capability to extract deep temporal degradation features,enabling the collaborative extraction of longperiod meshing frequencies and short-term impact features from the vibration signals.Kernel principal component analysis was employed to fuse and normalize these features,enhancing the characterization of degradation progression.A nonlinear Wiener process was used to model the degradation trajectory,with a threshold decay function introduced to dynamically adjust maintenance strategies,and model parameters optimized through maximum likelihood estimation.Meanwhile,the maintenance strategy was optimized to minimize costs per unit time,determining the optimal maintenance timing and preventive maintenance threshold.The comprehensive indicator of degradation trends extracted by this method reaches 0.756,which is 41.2%higher than that of traditional time-domain features;the dynamic threshold strategy reduces the maintenance cost per unit time to 55.56,which is 8.9%better than that of the static threshold optimization.Experimental results demonstrate significant reductions in maintenance costs while enhancing system reliability and safety.This study realizes the organic integration of deep learning and reliability theory in the maintenance of planetary gearboxes,provides an interpretable solution for the predictive maintenance of complex mechanical systems,and promotes the development of condition-based maintenance strategies for planetary gearboxes.展开更多
Small angle x-ray scattering(SAXS)is an advanced technique for characterizing the particle size distribution(PSD)of nanoparticles.However,the ill-posed nature of inverse problems in SAXS data analysis often reduces th...Small angle x-ray scattering(SAXS)is an advanced technique for characterizing the particle size distribution(PSD)of nanoparticles.However,the ill-posed nature of inverse problems in SAXS data analysis often reduces the accuracy of conventional methods.This article proposes a user-friendly software for PSD analysis,GranuSAS,which employs an algorithm that integrates truncated singular value decomposition(TSVD)with the Chahine method.This approach employs TSVD for data preprocessing,generating a set of initial solutions with noise suppression.A high-quality initial solution is subsequently selected via the L-curve method.This selected candidate solution is then iteratively refined by the Chahine algorithm,enforcing constraints such as non-negativity and improving physical interpretability.Most importantly,GranuSAS employs a parallel architecture that simultaneously yields inversion results from multiple shape models and,by evaluating the accuracy of each model's reconstructed scattering curve,offers a suggestion for model selection in material systems.To systematically validate the accuracy and efficiency of the software,verification was performed using both simulated and experimental datasets.The results demonstrate that the proposed software delivers both satisfactory accuracy and reliable computational efficiency.It provides an easy-to-use and reliable tool for researchers in materials science,helping them fully exploit the potential of SAXS in nanoparticle characterization.展开更多
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
Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for opti...Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for optimal coverage,ranking further refines their execution order to detect critical faults earlier.This study investigates machine learning techniques to enhance both prioritization and ranking,contributing to more effective and efficient testing processes.We first employ advanced feature engineering alongside ensemble models,including Gradient Boosted,Support Vector Machines,Random Forests,and Naive Bayes classifiers to optimize test case prioritization,achieving an accuracy score of 0.98847 and significantly improving the Average Percentage of Fault Detection(APFD).Subsequently,we introduce a deep Q-learning framework combined with a Genetic Algorithm(GA)to refine test case ranking within priority levels.This approach achieves a rank accuracy of 0.9172,demonstrating robust performance despite the increasing computational demands of specialized variation operators.Our findings highlight the effectiveness of stacked ensemble learning and reinforcement learning in optimizing test case prioritization and ranking.This integrated approach improves testing efficiency,reduces late-stage defects,and improves overall software stability.The study provides valuable information for AI-driven testing frameworks,paving the way for more intelligent and adaptive software quality assurance methodologies.展开更多
Faculty development serves as a critical foundation for ensuring the quality of higher education.To meet the needs of cultivating specialized software talents and promoting teaching reform,it is particularly crucial t...Faculty development serves as a critical foundation for ensuring the quality of higher education.To meet the needs of cultivating specialized software talents and promoting teaching reform,it is particularly crucial to build a faculty team with knowledge in industry application fields and experience in domestic software development.This paper first analyzes the new requirements for the faculty imposed by the cultivation of specialized software talents and the existing problems in the current faculty.Then,in response to these issues,it introduces the reforms and explorations carried out by the School of Software Engineering at Beijing Jiaotong University in the construction of the faculty for cultivating specialized software talents.The aim is to build a high-caliber and diversified faculty that boasts strong political qualities,interdisciplinary integration,complementary advantages between full-time and part-time faculty,and in-depth integration of industry and education.展开更多
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
Researchers have been active in the field of software engineering measurement over more than 30 years. The software quality product is becoming increasingly important in the computerized society. Target setting in sof...Researchers have been active in the field of software engineering measurement over more than 30 years. The software quality product is becoming increasingly important in the computerized society. Target setting in software quality function and usability deployment are essential since they are directly related to development of high quality products with high customer satisfaction. Software quality can be measured as the degree to which a particular software program complies with consumer demand regarding function and characteristics. Target setting is usually subjective in practice, which is unscientific. Therefore, this study proposes a quantity model for controlling and measuring software quality via the expert decision-making algorithm-based method for constructing an evaluation method can provide software in relation to users and purchasers, thus enabling administrators or decision makers to identify the most appropriate software quality. Importantly, the proposed model can provide s users and purchasers a reference material, making it highly applicable for academic and government purposes.展开更多
Software security poses substantial risks to our society because software has become part of our life. Numerous techniques have been proposed to resolve or mitigate the impact of software security issues. Among them, ...Software security poses substantial risks to our society because software has become part of our life. Numerous techniques have been proposed to resolve or mitigate the impact of software security issues. Among them, software testing and analysis are two of the critical methods, which significantly benefit from the advancements in deep learning technologies. Due to the successful use of deep learning in software security, recently,researchers have explored the potential of using large language models(LLMs) in this area. In this paper, we systematically review the results focusing on LLMs in software security. We analyze the topics of fuzzing, unit test, program repair, bug reproduction, data-driven bug detection, and bug triage. We deconstruct these techniques into several stages and analyze how LLMs can be used in the stages. We also discuss the future directions of using LLMs in software security, including the future directions for the existing use of LLMs and extensions from conventional deep learning research.展开更多
The critical role of patient-reported outcome measures(PROMs)in enhancing clinical decision-making and promoting patient-centered care has gained a profound significance in scientific research.PROMs encapsulate a pati...The critical role of patient-reported outcome measures(PROMs)in enhancing clinical decision-making and promoting patient-centered care has gained a profound significance in scientific research.PROMs encapsulate a patient's health status directly from their perspective,encompassing various domains such as symptom severity,functional status,and overall quality of life.By integrating PROMs into routine clinical practice and research,healthcare providers can achieve a more nuanced understanding of patient experiences and tailor treatments accordingly.The deployment of PROMs supports dynamic patient-provider interactions,fostering better patient engagement and adherence to tre-atment plans.Moreover,PROMs are pivotal in clinical settings for monitoring disease progression and treatment efficacy,particularly in chronic and mental health conditions.However,challenges in implementing PROMs include data collection and management,integration into existing health systems,and acceptance by patients and providers.Overcoming these barriers necessitates technological advancements,policy development,and continuous education to enhance the acceptability and effectiveness of PROMs.The paper concludes with recommendations for future research and policy-making aimed at optimizing the use and impact of PROMs across healthcare settings.展开更多
基金Computer Basic Education Teaching Research Project of Association of Fundamental Computing Education in Chinese Universities(Nos.2025-AFCEC-527 and 2024-AFCEC-088)Research on the Reform of Public Course Teaching at Nantong College of Science and Technology(No.2024JGG015).
文摘With the rapid development of artificial intelligence,the intelligence level of software is increasingly improving.Intelligent software,which is widely applied in crucial fields such as autonomous driving,intelligent customer service,and medical diagnosis,is constructed based on complex technologies like machine learning and deep learning.Its uncertain behavior and data dependence pose unprecedented challenges to software testing.However,existing software testing courses mainly focus on conventional contents and are unable to meet the requirements of intelligent software testing.Therefore,this work deeply analyzed the relevant technologies of intelligent software testing,including reliability evaluation indicator system,neuron coverage,and test case generation.It also systematically designed an intelligent software testing course,covering teaching objectives,teaching content,teaching methods,and a teaching case.Verified by the practical teaching in four classes,this course has achieved remarkable results,providing practical experience for the reform of software testing courses.
文摘Background:Despite the promise shown by large language models(LLMs)for standardized tasks,their multidimensional performance in real-world oncology decision-making remains unevaluated.This study aims to introduce a framework for evaluating LLMs and physician decisions in challenging lung cancer cases.Methods:We curated 50 challenging lung cancer cases(25 local and 25 published)classified as complex,rare,or refractory.Blinded three-dimensional,five-point Likert evaluations(1–5 for comprehensiveness,specificity,and readability)compared standalone LLMs(DeepSeek R1,Claude 3.5,Gemini 1.5,and GPT-4o),physicians by experience level(junior,intermediate,and senior),and AI-assisted juniors;intergroup differences and augmentation effects were analyzed statistically.Results:Of 50 challenging cases(18 complex,17 rare,and 15 refractory)rated by three experts,DeepSeek R1 achieved scores of 3.95±0.33,3.71±0.53,and 4.26±0.18 for comprehensiveness,specificity,and readability,respectively,positioning it between intermediate(3.68,3.68,3.75)and senior(4.50,4.64,4.53)physicians.GPT-4o and Claude 3.5 reached intermediate physician–level comprehensiveness(3.76±0.39,3.60±0.39)but junior-to-intermediate physician–level specificity(3.39±0.39,3.39±0.49).All LLMs scored higher on rare cases than intermediate physicians but fell below junior physicians in refractory-case specificity.AIassisted junior physicians showed marked gains in rare cases,with comprehensiveness rising from 2.32 to 4.29(84.8%),specificity from 2.24 to 4.26(90.8%),and readability from 2.76 to 4.59(66.0%),while specificity declined by 3.2%(3.17 to 3.07)in refractory cases.Error analysis showed complementary strengths,with physicians demonstrating reasoning stability and LLMs excelling in knowledge updating and risk management.Conclusions:LLMs performed variably in clinical decision-making tasks depending on case type,performing better in rare cases and worse in refractory cases requiring longitudinal reasoning.Complementary strengths between LLMs and physicians support case-and task-tailored human–AI collaboration.
基金supported by the National Natural Science Foundation of China (62202022, 92582204, and 62572030)the Fundamental Research Funds for the Central Universitiesthe exploratory elective projects of the State Key Laboratory of Complex and Critical Software Environments
文摘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 https://figshare.com/articles/media/OSSerCopilot_Introduction_mp4/29510276.
基金supported by the Strategic Priority Research Program of Chinese Academy of Sciences(No.XDB34030000)the National Natural Science Foundation of China(Nos.11927901 and 12475133)+1 种基金the Youth Team Program in Basic Research Fields Stably Supported by the Chinese Academy of Sciences(No.YSBR-088)the Western Light Project of the Chinese Academy of Sciences。
文摘Heavy-ion collisions(HICs)is a unique experimental tool for investigating the properties of nuclear matter under extreme conditions in the laboratory.At HIRFL-CSR energies,HICs can create nuclear matter with 2-3 times the saturation density(ρ_(0)).The HIRFL-CSR external-target experiment(CEE)is a large-acceptance spectrometer designed to explore frontier topics in high-energy nuclear physics,such as the QCD phase structure and nuclear matter equation of states.In this letter,we introduce simulation and analysis software for the CEE experiment(CeeROOT).Based on the CEE conceptual design and CeeROOT software,the configurations of its subdetectors were optimized by considering foreseeable physical constraints.The final detector layout of the CEE spectrometer and its acceptances were validated through simulations of U+U collisions at 500 MeV/u and pp collisions at 2.8 GeV,which demonstrated that the CEE experiment will serve as a detector with wide acceptance and multi-particle identification capabilities for studying high-energy nuclear physics topics at HIRFL-CSR energies with pp,pA,and A A collisions.
文摘While parametric Software Reliability Growth Models(SRGMs)serve as a cornerstone in software reliability assessment,their reliance on known fault-detection time distributions often presents a significant limitation in practical software testing.In this study,the authors develop a novel shaperestricted spline estimator for quantifying software reliability.Compared with parametric SRGMs,the proposed estimator not only shares a key characteristic with parametric SRGMs,but also obviates the need for specifying fault-detection time distributions.More importantly,it effectively utilizes the critical shape information of the mean value function(MVF)of fault-detection process,a detail seldom considered in prior work.Moreover,the authors investigate the predictive performance of the proposed methods by employing the so-called one-step look-ahead prediction method.Furthermore,the authors show that under certain conditions,the shape-restricted spline estimator will attain the point-wise convergence rate O_P(n~(-3/7)).In numerical experiment,the authors show that spline estimators under restriction demonstrate competitive performance compared to parametric and certain non-parametric models.
文摘In the modern era of ubiquitous and highly interconnected information technology,cybersecurity threats stemming from software code vulnerabilities have become increasingly severe,posing significant risks to the confidentiality,integrity,and availability of modern information systems.To enhance software code quality,enterprises often integrate static code analysis tools into Continuous Integration(CI) pipelines.However,the high rates of false positives and false negatives remain a challenge.The advent of large language models(LLMs),such as ChatGPT,presents a new opportunity to address these challenges.In this paper,we propose AI-SCDF,a framework that utilizes the custombuilt Nebula-Coder AI model for detecting and fixing code security issues in real time during the developer ' s personal build process.We construct a static code checking rule knowledge base through summarizing and classifying Common Weakness Enumeration(CWE) code security problems identified by security and quality assurance teams.The rule knowledge base is combined with CodeFuse-processed code contexts to serve as input for an AI code security detection microservice,which assists in identifying code quality and security issues.If any abnormalities are detected,they are addressed by an AI code security patching microservice,which alerts the developer and requests confirmation before committing the code into the repository.Experimental results show that our approach effectively improves code quality.We also develop a VS Code plugin for code alert detection and fix based on LLMs,which facilitates test shift-left and lowers the risk of software development.
基金supported by the Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2026R259)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.Ashit Kumar Dutta would like to thank AlMaarefa University for supporting this research under project number MHIRSP2025017.
文摘Environmental problems are intensifying due to the rapid growth of the population,industry,and urban infrastructure.This expansion has resulted in increased air and water pollution,intensified urban heat island effects,and greater runoff from parks and other green spaces.Addressing these challenges requires prioritizing green infrastructure and other sustainable urban development strategies.This study introduces a novel Integrated Decision Support System that combines Pythagorean Fuzzy Sets with the Advanced Alternative Ranking Order Method allowing for Two-Step Normalization(AAROM-TN),enhanced by a dual weighting strategy.The weighting approach integrates the Criteria Importance Through Intercriteria Correlation(CRITIC)method with the Criteria Importance through Means and Standard Deviation(CIMAS)technique.The originality of the proposed framework lies in its ability to objectively quantify criteria importance using CRITIC,incorporate decision-makers’preferences through CIMAS,and capture the uncertainty and hesitation inherent in human judgment via Pythagorean Fuzzy Sets.A case study evaluating green infrastructure alternatives in metropolitan regions demonstrates the applicability and effectiveness of the framework.A sensitivity analysis is conducted to examine how variations in criteria weights affect the rankings and to evaluate the robustness of the results.Furthermore,a comparative analysis highlights the practical and financial implications of each alternative by assessing their respective strengths and weaknesses.
基金supported by the Shanghai Municipal Education Research Project“Exploring the Practical Application of Generative Artificial Intelligence in Cultivating Innovative Thinking and Capabilities of Interdisciplinary Application Technology Talents‘Practice Path’”(C2025299)the university-level postgraduate course project“Software Process Management”(PX-2025251502)of Shanghai Sanda Universitythe key course project at the university level of Shanghai Sanda University,“Introduction to Software Engineering”(PX-5241216).
文摘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.
基金supported in part by the Graduate Education Reform Research Project of Hubei University of Technology under Grant 2024YB003the Hubei University of Arts and Science,Teaching Research Project,under Grant JY2025018.
文摘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.
基金supported in part by the Northeastern University’s 2024 Undergraduate Education and Teaching Reform Research Project:Innovation and Practice of Professional Course Teaching Paradigms in the Context of Digital Education.
文摘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.
基金support of the National Key Research and Development Plan(No.2021YFB3302501)the financial support of the National Science Foundation of China(No.12161076)the financial support of the Fundamental Research Funds for the Central Universities(No.DUT25GF207).
文摘With the rapid development of artificial intelligence,intelligent air combat maneuver decision-making(ACMD)has garnered global attention.Although deep reinforcement learning provides a promising approach to ACMD,existing methods often suffer from rigid reward functions and limited adaptability to evolving adversarial strategies.Moreover,most research assumes open airspace,overlooking the influence of potential obstacles.In this paper,we address one-on-one within-visual-range ACMD in obstructed environments,and propose an improved Soft Actor-Critic(SAC)algorithm trained under a curriculum self-play framework.A maneuver strategy mirroring inference module is integrated to estimate each other's likely positions when visual obstruction occurs.By leveraging curriculum learning to guide progressive experience accumulation and self-play for adversarial evolution,our method enhances both training efficiency and tactical diversity.We further integrate an attention mechanism that dynamically adjusts the weights of sub-rewards,enabling the learned policy to adapt to rapidly changing air combat situations.Numerical simulations demonstrate that our enhanced SAC converges more quickly and achieves higher win rates than other baseline methods.An animation is available at bilibili.com/video/BV1BHVszHE98 for better illustration.
基金funded by scientific research projects under Grant JY2024B011.
文摘With the increasing complexity of industrial automation,planetary gearboxes play a vital role in largescale equipment transmission systems,directly impacting operational efficiency and safety.Traditional maintenance strategies often struggle to accurately predict the degradation process of equipment,leading to excessive maintenance costs or potential failure risks.However,existing prediction methods based on statistical models are difficult to adapt to nonlinear degradation processes.To address these challenges,this study proposes a novel condition-based maintenance framework for planetary gearboxes.A comprehensive full-lifecycle degradation experiment was conducted to collect raw vibration signals,which were then processed using a temporal convolutional network autoencoder with multi-scale perception capability to extract deep temporal degradation features,enabling the collaborative extraction of longperiod meshing frequencies and short-term impact features from the vibration signals.Kernel principal component analysis was employed to fuse and normalize these features,enhancing the characterization of degradation progression.A nonlinear Wiener process was used to model the degradation trajectory,with a threshold decay function introduced to dynamically adjust maintenance strategies,and model parameters optimized through maximum likelihood estimation.Meanwhile,the maintenance strategy was optimized to minimize costs per unit time,determining the optimal maintenance timing and preventive maintenance threshold.The comprehensive indicator of degradation trends extracted by this method reaches 0.756,which is 41.2%higher than that of traditional time-domain features;the dynamic threshold strategy reduces the maintenance cost per unit time to 55.56,which is 8.9%better than that of the static threshold optimization.Experimental results demonstrate significant reductions in maintenance costs while enhancing system reliability and safety.This study realizes the organic integration of deep learning and reliability theory in the maintenance of planetary gearboxes,provides an interpretable solution for the predictive maintenance of complex mechanical systems,and promotes the development of condition-based maintenance strategies for planetary gearboxes.
基金Project supported by the Project of the Anhui Provincial Natural Science Foundation(Grant No.2308085MA19)Strategic Priority Research Program of the Chinese Academy of Sciences(Grant No.XDA0410401)+2 种基金the National Natural Science Foundation of China(Grant No.52202120)the National Key Research and Development Program of China(Grant No.2023YFA1609800)USTC Research Funds of the Double First-Class Initiative(Grant No.YD2310002013)。
文摘Small angle x-ray scattering(SAXS)is an advanced technique for characterizing the particle size distribution(PSD)of nanoparticles.However,the ill-posed nature of inverse problems in SAXS data analysis often reduces the accuracy of conventional methods.This article proposes a user-friendly software for PSD analysis,GranuSAS,which employs an algorithm that integrates truncated singular value decomposition(TSVD)with the Chahine method.This approach employs TSVD for data preprocessing,generating a set of initial solutions with noise suppression.A high-quality initial solution is subsequently selected via the L-curve method.This selected candidate solution is then iteratively refined by the Chahine algorithm,enforcing constraints such as non-negativity and improving physical interpretability.Most importantly,GranuSAS employs a parallel architecture that simultaneously yields inversion results from multiple shape models and,by evaluating the accuracy of each model's reconstructed scattering curve,offers a suggestion for model selection in material systems.To systematically validate the accuracy and efficiency of the software,verification was performed using both simulated and experimental datasets.The results demonstrate that the proposed software delivers both satisfactory accuracy and reliable computational efficiency.It provides an easy-to-use and reliable tool for researchers in materials science,helping them fully exploit the potential of SAXS in nanoparticle characterization.
文摘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.
文摘Test case prioritization and ranking play a crucial role in software testing by improving fault detection efficiency and ensuring software reliability.While prioritization selects the most relevant test cases for optimal coverage,ranking further refines their execution order to detect critical faults earlier.This study investigates machine learning techniques to enhance both prioritization and ranking,contributing to more effective and efficient testing processes.We first employ advanced feature engineering alongside ensemble models,including Gradient Boosted,Support Vector Machines,Random Forests,and Naive Bayes classifiers to optimize test case prioritization,achieving an accuracy score of 0.98847 and significantly improving the Average Percentage of Fault Detection(APFD).Subsequently,we introduce a deep Q-learning framework combined with a Genetic Algorithm(GA)to refine test case ranking within priority levels.This approach achieves a rank accuracy of 0.9172,demonstrating robust performance despite the increasing computational demands of specialized variation operators.Our findings highlight the effectiveness of stacked ensemble learning and reinforcement learning in optimizing test case prioritization and ranking.This integrated approach improves testing efficiency,reduces late-stage defects,and improves overall software stability.The study provides valuable information for AI-driven testing frameworks,paving the way for more intelligent and adaptive software quality assurance methodologies.
文摘Faculty development serves as a critical foundation for ensuring the quality of higher education.To meet the needs of cultivating specialized software talents and promoting teaching reform,it is particularly crucial to build a faculty team with knowledge in industry application fields and experience in domestic software development.This paper first analyzes the new requirements for the faculty imposed by the cultivation of specialized software talents and the existing problems in the current faculty.Then,in response to these issues,it introduces the reforms and explorations carried out by the School of Software Engineering at Beijing Jiaotong University in the construction of the faculty for cultivating specialized software talents.The aim is to build a high-caliber and diversified faculty that boasts strong political qualities,interdisciplinary integration,complementary advantages between full-time and part-time faculty,and in-depth integration of industry and education.
基金supported by the Research Funding Project for Graduate Education and Teaching Reform of Beijing University of Posts and Telecommunications(No.2024Y036)the Postgraduate Education and Teaching Reform Research Fund Project of Beijing University of Posts and Telecommunications(No.2024Z007)the Postgraduate Education and Teaching Reform Project of Beijing University of Posts and Telecommunications(2025).
文摘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.
文摘Researchers have been active in the field of software engineering measurement over more than 30 years. The software quality product is becoming increasingly important in the computerized society. Target setting in software quality function and usability deployment are essential since they are directly related to development of high quality products with high customer satisfaction. Software quality can be measured as the degree to which a particular software program complies with consumer demand regarding function and characteristics. Target setting is usually subjective in practice, which is unscientific. Therefore, this study proposes a quantity model for controlling and measuring software quality via the expert decision-making algorithm-based method for constructing an evaluation method can provide software in relation to users and purchasers, thus enabling administrators or decision makers to identify the most appropriate software quality. Importantly, the proposed model can provide s users and purchasers a reference material, making it highly applicable for academic and government purposes.
文摘Software security poses substantial risks to our society because software has become part of our life. Numerous techniques have been proposed to resolve or mitigate the impact of software security issues. Among them, software testing and analysis are two of the critical methods, which significantly benefit from the advancements in deep learning technologies. Due to the successful use of deep learning in software security, recently,researchers have explored the potential of using large language models(LLMs) in this area. In this paper, we systematically review the results focusing on LLMs in software security. We analyze the topics of fuzzing, unit test, program repair, bug reproduction, data-driven bug detection, and bug triage. We deconstruct these techniques into several stages and analyze how LLMs can be used in the stages. We also discuss the future directions of using LLMs in software security, including the future directions for the existing use of LLMs and extensions from conventional deep learning research.
文摘The critical role of patient-reported outcome measures(PROMs)in enhancing clinical decision-making and promoting patient-centered care has gained a profound significance in scientific research.PROMs encapsulate a patient's health status directly from their perspective,encompassing various domains such as symptom severity,functional status,and overall quality of life.By integrating PROMs into routine clinical practice and research,healthcare providers can achieve a more nuanced understanding of patient experiences and tailor treatments accordingly.The deployment of PROMs supports dynamic patient-provider interactions,fostering better patient engagement and adherence to tre-atment plans.Moreover,PROMs are pivotal in clinical settings for monitoring disease progression and treatment efficacy,particularly in chronic and mental health conditions.However,challenges in implementing PROMs include data collection and management,integration into existing health systems,and acceptance by patients and providers.Overcoming these barriers necessitates technological advancements,policy development,and continuous education to enhance the acceptability and effectiveness of PROMs.The paper concludes with recommendations for future research and policy-making aimed at optimizing the use and impact of PROMs across healthcare settings.
