检索结果-内蒙古大学图书馆

Integration of Large Language Models and Computer Vision algorithms in LMS: A Methodology for Automated Verification of software Tasks and Multimodal Analysis of Educational Data

Integration of Large Language Models and Computer Vision Alg...

引用

International Russian Smart Industry Conference (SmartIndustryCon)

作者： E. I. Markin V. V. Zuparova A. I. Martyshkin Penza state technological University PSTU Penza Russia

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

This paper presents a study on the design and development of a learning management system (LMS) integrated with large language models (LLMs) and image recognition/generation algorithms to automate software task validation and multimodal educational data analysis. The purpose of the development is to improve the quality of feedback for learners, deepen the understanding of errors made and expand the capabilities of the system by synthesizing formal LLM models and visual processing algorithms. The system is based on the use of domestic LLMs such as GigaChat and YandexGPT, Retrieval-Augmented Generation (RAG) technology, and modern computer vision algorithms. The system architecture is described, including GitVerse for code storage, GitVerse Actions for automated testing of solutions in Docker containers, and image processing modules for analyzing and generating visual data in the educational process. The conducted experiment demonstrates the effectiveness of the integrative approach, which allows to improve the quality of feedback and increase the performance of students. Prospects for further research include optimization of computational resources and development of techniques for integrated analysis of multimodal educational data.

关键词： Visualization Computer vision Codes Image recognition Costs Large language models Computational modeling software algorithms Trajectory Testing

来源：评论

学校读者我要写书评

暂无评论

Newton's Cooling Law-Based Oversampling Technique for Handling Imbalanced Data in software Defect Prediction

引用

IEEE ACCESS 2025年 13卷 47820-47832页

作者： Wang, Faqiang Tao, Liangliang Liang, Yage Zhang, Lilin Luo, Tianyu Jiangxi Polytech Univ Coll Informat Engn Jiujiang 332007 Peoples R China

Class imbalance presents considerable challenges for software defect prediction. However, software defect datasets exhibit additional complex characteristics, with class overlap being the most harmful to prediction performance. Currently, most techniques only focus on balancing data distributions. To this end, this study applies the previously proposed Newton's Cooling Law-Based Oversampling Technique (NCLWO) to software defect prediction. The method first uses density and distance factors to identify hard-to-learn defect instances in SDP, such as boundary samples in overlapping distributions and small disjoints. Then, the density and distance factors are used to measure the initial heat of each defect instance. Newton's Cooling Law is applied to expand the sampling area into a hypersphere until thermal equilibrium is achieved, moving non-defective instances out of the region to clean the overlapping area. Finally, weighted oversampling is performed within the expanded sampling area to generate defect instances, addressing within-class imbalance. Comparative experiments were conducted between NCLWO and ten state-of-the-art sampling methods on 30 software defect datasets. The experimental results reveal that the proposed method excels in performance and showcases significant robustness and versatility in handling the joint effects of class overlap and imbalance.

关键词： software Cooling Sampling methods Heating systems software algorithms Accuracy Training Predictive models Data models Costs software defect prediction class imbalance class overlap Newton's cooling law oversampling

来源：评论

学校读者我要写书评

暂无评论

An Analytical Hierarchy Process-Based Technique for software Requirements Prioritization

引用

IEEE ACCESS 2025年 13卷 50603-50610页

作者： Ahmad Al-Rawashdeh, Thamer Al'Azzeh, Feras Al-Tarawneh, Feras Al Zaytoonah Univ Jordan Sch Sci & Informat Technol Amman 11733 Jordan Al Zaytoonah Univ Jordan Sch Engn Amman 11733 Jordan

software requirements prioritization is a crucial step in the requirements engineering process. It is applied to define the ordering of specific requirements according to schedule and budget constraints. Many requirements prioritization approaches have been proposed in the literature, but not all have been empirically investigated in real-life settings, cannot be used for all types of projects, and do not provide a hierarchical model for the requirements. Therefore, this study proposes an analytical hierarchy process-based technique to prioritize functional and quality requirements prioritization based on stakeholders' perspectives. The proposed technique has been demonstrated in the organization's quality management system and eliminates inconsistencies between business and technical stakeholder valuations. The results indicated that the consistency ratio for hierarchy was acceptable (0.089), thereby confirming the accuracy of the analysis. Notably, the effectiveness requirement (28%) was the highest among the functional and nonfunctional categories in this hierarchy.

关键词： software Stakeholders Scalability Analytic hierarchy process Accuracy Systematics software quality Requirements engineering Business software algorithms Analytical hierarchy process functional requirements non-functional requirements requirements prioritization

来源：评论

学校读者我要写书评

暂无评论

Meeting the Big Synthetic Aperture Radar Data Processing Challenge: Introducing the software for Earth big data Processing, Prediction modeling, and Organization cloud-scaling solution

引用

IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE 2025年

作者： Kellndorfer, Josef Cartus, Oliver Helfrich, Sean Earth Big Data LLC Woods Hole MA 02543 USA Gamma Remote Sensing AG CH-3073 Gumlingen Switzerland NOAA Natl Weather Serv Natl Ctr Environm Predict College Pk MD 20740 USA

With the launch of NISAR, available open access Earth Observation data reaches a new milestone with an estimated data rate of similar to 70 Terabytes of NISAR science data produced daily. This additional data creates many opportunities within the science and user community for new and more indepth analyses, yet at the same time, most organizations lack the budget, resources, and skills to analyze all this data on-premise. This article introduces concepts on how SAR processing software from commercial and open-source providers can be coupled with highly scalable cloud processing techniques to digest SAR data at various input levels (from raw to value added products). Included in this article are examples on the global-scale processing of Sentinel-1 data for InSAR coherence estimation, the input to global biomass modeling, and the routine operational processing of SAR time series data for national and international near-real time flood mapping. The cloud-scaling software for Earth big data Processing, Prediction Modeling, and Organization (SEPPO), which is used to meet the processing challenges utilizing Amazon Web Services (AWS) for large volume and operational SAR data processing in complex workflows is introduced.

关键词： Cloud computing Synthetic aperture radar Data processing Coherence Sentinel-1 Earth Orbits Data models Throughput software algorithms

来源：评论

学校读者我要写书评

暂无评论

A Survey: Collaborative Hardware and software Design in the Era of Large Language Models

引用

IEEE CIRCUITS AND SYSTEMS MAGAZINE 2025年第1期25卷 35-57页

作者： Guo, Cong Cheng, Feng Du, Zhixu Kiessling, James Ku, Jonathan Li, Shiyu Li, Ziru Ma, Mingyuan Molom-Ochir, Tergel Morris, Benjamin Shan, Haoxuan Sun, Jingwei Wang, Yitu Wei, Chiyue Wu, Xueying Wu, Yuhao Yang, Hao Frank Zhang, Jingyang Zhang, Junyao Zheng, Qilin Zhou, Guanglei Li, Hai Chen, Yiran Duke Univ Dept Elect & Comp Engn Durham NC 27705 USA

The rapid development of large language models (LLMs) has significantly transformed the field of artificial intelligence, demonstrating remarkable capabilities in natural language processing and moving towards multi-modal functionality. These models are increasingly integrated into diverse applications, impacting both research and industry. However, their development and deployment present substantial challenges, including the need for extensive computational resources, high energy consumption, and complex software optimizations. Unlike traditional deep learning systems, LLMs require unique optimization strategies for training and inference, focusing on system-level efficiency. This paper surveys hardware and software co-design approaches specifically tailored to address the unique characteristics and constraints of large language models. This survey analyzes the challenges and impacts of LLMs on hardware and algorithm research, exploring algorithm optimization, hardware design, and system-level innovations. It aims to provide a comprehensive understanding of the trade-offs and considerations in LLM-centric computing systems, guiding future advancements in AI. Finally, we summarize the existing efforts in this space and outline future directions toward realizing production-grade co-design methodologies for the next generation of large language models and AI systems.

关键词： Large language models Artificial intelligence Natural language processing Multimodal sensors Energy consumption Deep learning Training Hardware design languages Algorithm design and analysis software algorithms Inference algorithms Next generation networking Collaborative software Large language model hardware-software co-design

来源：评论

学校读者我要写书评

暂无评论

HSoMLSDP: A Hybrid Swarm-Optimized Machine Learning Framework for software Defect Prediction

引用

IEEE ACCESS 2025年 13卷 61161-61180页

作者： Das, Madhusmita Mohan, Biju R. Guddeti, Ram Mohana Reddy Natl Inst Technol Karnataka Dept Informat Technol Surathkal 575025 Mangalore India

This research aims to design a hybrid swarm-optimized machine learning software defect prediction (HSoMLSDP) framework to predict software defects. We strive to do this by designing a swarm-optimized machine learning defect prediction (SoMLDP) model within the HSoMLSDP framework. In pursuit of enhancing the defect prediction accuracy of the SoMLDP model, this paper designed two novel hybrid swarm-optimization algorithms (SOAs) referred to as gravitational force grasshopper optimization algorithm-artificial bee colony (GFGOA-ABC), and levy flight grasshopper optimization algorithm-artificial bee colony (LFGOA-ABC) algorithms. By combining the enhanced exploration features of LFGOA and GFGOA with the robust exploitation capacity of the artificial bee colony (ABC), the LFGOA-ABC and GFGOA-ABC algorithms are proposed. Prior to validating the HSoMLSDP framework, the LFGOA-ABC and GFGOA-ABC algorithm's efficacy is first confirmed by experimenting on 19 benchmark functions (BFs) to assess their mean, standard deviation (SD) of optimal values, convergence rate, and convergence rate improvements. Following BFs verification, the second experiment tunes the hyperparameters of the ML models (artificial neural network, XGBOOST) to improve the defect accuracy of the SoMLDP model. The outcomes of the experiments justify a more rapid convergence rate for BFs and notable enhancements of 0.01-0.28 in software defect prediction (SDP) accuracy for NASA defect datasets when compared with state-of-the-art methods. As an enhancement of accuracy justifies the correctness of the SoMLDP model, thus validating the HSoMLSDP framework.

关键词： Optimization Tuning Prediction algorithms software Convergence Accuracy software algorithms Predictive models Machine learning Machine learning algorithms Swarm-optimization algorithm benchmark functions machine learning software defect prediction

来源：评论

学校读者我要写书评

暂无评论

Fully Automated software Product Line Evolution With Diverse Artifacts

引用

IEEE ACCESS 2025年 13卷 27325-27358页

作者： Perdek, Jakub Vranic, Valentino Slovak Univ Technologyin Bratislava Inst Informat Informat Syst & Software Engn Fac Informat & Informat Technol Bratislava 81243 Slovakia Pan European Univ Fac Informat Bratislava 82009 Slovakia

Existing approaches in software product lines usually neglect knowledge modeling and simulation of the interaction between features capable of bringing dynamism and automation. Consequently, these solutions miss opportunities to resolve associated and emerging problems, including defect detection or quality assurance, which can be solved by effectively extracting and utilizing knowledge from data based on the differences between variants. We bring capabilities to seize them in introducing a fully automated and minimalistic approach to software product line evolution that strictly focuses on handling variability at low-level code fragments. It incorporates the autonomous modeling of emerging knowledge across preconfigured simulations. Specifically, fully automated knowledge-driven software product line evolution provides various views on an existing software product line, its variants, and their evolution through semantic and structural information accompanied by the time and order of the performed changes. We initially developed our approach for software product line evolution, followed by its successful application to the evolution of fractal scripts. We present it accordingly. Fractal products are much simpler because an application state does not span out of recursive behavior, making it manageable within the drawing. Each change is propagated into repetitive phases, causing the visual performance of the implemented feature to be infinitely detailed. Even minor changes in low code fragments tend to manifest as user-visible features owing to recursive behavior, allowing one to massively introduce new features and/or configure existing features and manage variability observable as infinitely detailed shapes. Future applications propose automated observation of more comprehensive in-code representation of feature trees.

关键词： software product lines Codes software Fractals Annotations Quality assurance Automation Testing Source coding software algorithms Aspect-oriented configuration expressions knowledge-driven software product line evolution variability modeling

来源：评论

学校读者我要写书评

暂无评论

software Implementation of Fast List Decoder for PAC Codes

引用

IEEE EMBEDDED SYSTEMS LETTERS 2025年第1期17卷 14-17页

作者： Yin, Hang Dai, Jingxin Lv, Yansong Wang, Yuhuan Lv, Rui Commun Univ China State Key Lab Media Convergence & Commun Beijing 100024 Peoples R China

In this letter, a novel high throughput software polarization-adjusted convolutional (PAC) decoder based on the four-node fast list (FFL) decoding algorithm is proposed. To improve the parallel processing capabilities of the proposed decoder, we effectively parallel map the FFL decoding algorithm to processors by using the single-instruction-multiple-data (SIMD) instruction set to decode multiple frames of data in parallel. Moreover, the proposed decoder has sufficient generality to be implemented on X86 and ARM processors (NEON, SSE, and AVX256 instruction sets). Experimentations show that the proposed software PAC decoder can achieve 26.256 Mb/s.

关键词： Decoding Picture archiving and communication systems software Vectors software algorithms Convolutional codes Convolution Fast list decoder polarization-adjusted convolutional (PAC) codes single-instruction-multiple-data (SIMD) software

来源：评论

学校读者我要写书评

暂无评论

Influence of the 1990 IEEE TSE Paper "Automated software Test Data Generation" on software Engineering

引用

IEEE TRANSACTIONS ON software ENGINEERING 2025年第3期51卷 751-753页

作者： Korel, Bogdan IIT Dept Comp Sci Chicago IL 60616 USA

Generating test data is a critical component of software testing, essential for ensuring the proper functioning of software systems. Automated test data generation, in particular, can greatly improve the efficiency and accuracy of the testing process. In 1990, the paper "Automated software Test Data Generation," published in IEEE Transactions on software Engineering (Korel, 1990), introduced a novel approach to automated test data generation, focusing on actual program execution, fitness function minimization methods, and dynamic data flow analysis. This paper discusses the impact of the 1990 IEEE TSE publication (Korel, 1990) on automated test data generation and software engineering.

关键词： software Data collection software engineering software reliability Reliability software testing software algorithms software systems Genetics Computer science Automated test data generation search-based test generation fitness function dynamic data flow analysis alternating variable method search-based software engineering

来源：评论

学校读者我要写书评

暂无评论

Cost-Sensitive Hypergraph Learning With Structure Quality Preservation for IoT software Defect Prediction

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY

引用

IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY 2025年 6卷 2780-2791页

作者： Wang, Nan Liu, Jiqiang Du, Bing Zhao, Qinxin Sun, Yuanlin Zhang, Tao Fan, Dunqiu Li, Wenjin Li, Binyong Beijing Jiaotong Univ Sch Cyberspace Sci & Technol Beijing 100044 Peoples R China China Acad Railway Sci Corp Ltd Railway Engn Res Inst Beijing 100081 Peoples R China Nanjing Univ Dept Comp Sci & Technol State Key Lab Novel Software Technol Nanjing 210023 Peoples R China NSFOCUS Technol Grp Co Ltd Res Dept Beijing 100085 Peoples R China NSFOCUS Inc Secur Capabil Ctr Beijing 100085 Peoples R China Chengdu Univ Informat Technol Adv Cryptog & Syst Secur Key Lab Sichuan Prov Chengdu 610000 Peoples R China

Generative AI is revolutionizing software Engineering (SE), as both engineers and academics embrace this technology in their work. To better leverage this technology for software generation, it is essential to propose effective IoT software defect prediction methods. However, this task is challenging due to the unclear high-order correlation underlying the data. Moreover, in real-world IoT software defect prediction applications, different types of misclassifications generally lead to distinct losses and associated costs. However, accurately determining these specific costs is often not feasible. Under such circumstances, we propose a cost-sensitive hypergraph learning method with structure quality preservation (csHLQ) to optimize the cost information and preserve the graph quality in a principled way. Due to the representational ability on high-order relationship exploring, we employ hypergraph structure instead of graph structure to model the complex correlations among the datasets. We note that if a cost-sensitive hypergraph has a high quality, its classification results may exhibit a large margin separation. Thus, csHLQ exploits the large margin cost-sensitive hypergraph while avoiding using of a cost-sensitive hypergraph with a small margin. To measure the performance of our proposed method, we performed experiments on three distinct groups of datasets, i.e., the NASA Metrics Data Program (NASA) dataset, CK metric dataset and UCI Machine Learning Repository (UCI) dataset. Experimental results and comparisons with state-of-the-art methods demonstrate the superiority of our method.

关键词： software Costs software engineering software measurement software algorithms Mathematical models Generative AI Feature extraction Ensemble learning Correlation Cost-sensitive hypergraph learning hypergraph structure optimization IoT software defect prediction

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：