检索结果-内蒙古大学图书馆

An empirical study of manual abstraction between class diagrams and code of open-source systems

software and Systems Modeling 2025年 1-27页

作者： Zhang, Wenli Zhang, Weixing Strüber, Daniel Hebig, Regina Department of Computer Science and Engineering Chalmers University of Technology and University of Gothenburg Gothenburg Sweden Department of Software Science Radboud University Nijmegen The Netherlands Institute of Computer Science University of Rostock Rostock Germany

Models play a crucial role in software design, analysis, and supporting new maintainers. However, over time, the benefits of models can diminish as system implementations evolve without corresponding updates to the original models. Reverse engineering methods and tools can help maintain alignment between models and implementation code. Yet, automatically reverse-engineered models often lack abstraction and contain extensive details that hinder comprehension. Recent advancements in AI-based content generation suggest that we may soon see reverse engineering tools capable of human-grade abstraction. To guide the design and validation of such tools, we need a principled understanding of manual abstraction—a topic that has received limited attention in existing literature. In pursuit of this goal, our paper presents a multiple-case study of model-to-code differences, examining nine substantial open-source software projects obtained through repository mining. We manually matched source code from projects comprising 4983 classes, 26k attributes, and 54k operations to 523 model elements (including classes, attributes, operations, and relationships). These mappings precisely capture discrepancies between provided class diagram designs and actual implementation code. By analyzing these differences in detail, we derive a taxonomy of difference types and provide a well-organized list of cases corresponding to identified differences. Our findings have the potential to contribute to improved reverse engineering methods and tools, propose new mapping rules for model-to-code consistency checks, and offer guidelines to avoid over-abstraction and over-specification during the design process.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Next-POI Recommendation via Spatial-Temporal Knowledge Graph Contrastive Learning and Trajectory Prompt

引用

IEEE Transactions on Knowledge and Data engineering 2025年第6期37卷 3570-3582页

作者： Chen, Wei Huang, Haoyu Zhang, Zhiyu Wang, Tianyi Lin, Youfang Chang, Liang Wan, Huaiyu Guilin University of Electronic Technology Guangxi Key Lab of Trusted Software Guangxi Guilin541004 China Beijing Jiaotong University School of Computer Science and Technology Beijing100044 China Chinese University of Hong Kong Department of Computer Science and Engineering Ma Liu Shui Hong Kong Beijing Jiaotong University Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence Beijing100044 China

Next POI (Point-of-Interest) recommendation aims to forecast users' future movements based on their historical check-in trajectories, holding significant value in location-based services. Existing methods address trajectory data sparsity by integrating rich auxiliary information or using spatial-temporal knowledge graphs (STKGs), showing promising results. Yet, they face two main challenges: i) Due to the difficulty of transforming structured trajectory data into trajectory text describing users' spatial-temporal mobility, the powerful reasoning ability of pre-trained language models is rarely explored to enhance recommendation performance. ii) Methods based on STKG can introduce external knowledge inconsistent with user preferences, leading to the knowledge noise generated hampering the accuracy of recommendations. To this end, we propose a novel approach called STKG-PLM that integrates STKG contrastive learning and prompt pre-trained language model (PLM) to enhance the next POI recommendation. Specifically, we design a spatial-temporal trajectory prompt template that transforms structured trajectories into text corpus based on STKG, serving as the input of PLM to understand the movement pattern of users from coarse-grained and fine-grained perspectives. Additionally, we propose an STKG contrastive learning framework to mitigate the introduced knowledge noise. Extensive experiments on three real-world datasets demonstrate that STKG-PLM exhibits notable performance improvements over the state-of-the-art baseline methods. © 1989-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Experimental Study on Dynamic Lifelong Learning with GPT for Mitigating Catastrophic Forgetting in Aspect-Based Sentiment Analysis

引用

IEEE Access 2025年

作者： Huang, Huang Asemi, Adeleh Universiti Malaya Faculty of Computer Science Information Technology Department of Software Engineering Kuala Lumpur Malaysia

GPT is widely recognized as one of the most versatile and powerful large language models, excelling across diverse domains. However, its significant computational demands often render it economically unfeasible for individuals and small businesses, underscoring the need for efficient, domainspecific alternatives. In Aspect-Based Sentiment Analysis (ABSA), existing models are typically optimized for single domains, facing challenges in performing effectively across multiple domains. A key issue, known as "catastrophic forgetting," arises when models trained on one domain lose previously learned knowledge upon exposure to new domain data. This leads to two significant problems: limited cross-domain generalization and difficulty in retaining prior knowledge while learning domain-specific information. To address these challenges, we introduce the Dynamic Lifelong Learning Aspect-Based Sentiment Analysis GPT (DllaGPT), a model designed to handle multiple domains while mitigating catastrophic forgetting. Leveraging datasets from four ABSA domains—Laptops, Restaurants, Tweets, and Finance—this study fine-tunes a pretrained GPT model from HuggingFace sequentially across domains. DllaGPT employs a mechanism to retain real data from earlier domains during new domain training, effectively preserving prior knowledge. Experimental results highlight that DllaGPT achieves an average accuracy of 0.85 and a Backward Transfer (BWT) score of -0.09 across the four domains, showcasing its high accuracy and robust lifelong learning capabilities. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

AAV Virtual Antenna Array Deployment for Uplink Interference Mitigation in Data Collection Networks

引用

IEEE Internet of Things Journal 2025年第8期12卷 10834-10850页

作者： Li, Hongjuan Kang, Hui Sun, Geng Li, Jiahui Wang, Jiacheng Wang, Xue Niyato, Dusit Leung, Victor C. M. Jilin University College of Computer Science and Technology Changchun 130012 China Jilin University College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun 130012 China Nanyang Technological University College of Computing and Data Science Jurong West Singapore Jilin University Department of Communication Engineering Changchun 130012 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Shenzhen 518115 China Shenzhen University College of Computer Science and Software Engineering Shenzhen 518060 China The University of British Columbia Department of Electrical and Computer Engineering Vancouver V6T 1Z4 BC Canada

Autonomous aerial vehicles (AAVs) have gained considerable attention as a platform for establishing aerial wireless networks and communications. However, the Line of Sight (LoS) dominance in air-to-ground (A2G) communications often leads to significant interference with terrestrial networks, reducing communication efficiency among terrestrial terminals. This article explores a novel uplink interference mitigation approach based on the collaborative beamforming (CB) method in multi-AAV network systems. Specifically, the AAV swarm forms an AAV-enabled virtual antenna array (VAA) to achieve the transmissions of gathered data to multiple base stations (BSs) for data backup and distributed processing. However, there is a tradeoff tradeoff between the effectiveness of CB-based interference mitigation and the energy conservation of AAVs. Thus, by optimizing the excitation current weights and hover position of AAVs as well as the sequence of data transmission to various BSs, we formulate an uplink interference mitigation multiobjective optimization problem (MOOP) to decrease interference affection, enhance transmission efficiency, and improve energy efficiency, simultaneously. In response to the computational demands of the formulated problem, we introduce an evolutionary computation method, namely chaotic nondominated sorting genetic algorithm II (CNSGA-II) with multiple improved operators. The proposed CNSGA-II efficiently addresses the formulated MOOP, outperforming several other comparative algorithms, as evidenced by the outcomes of the simulations. Moreover, the proposed CB-based uplink interference mitigation approach can significantly reduce the interference caused by AAVs to nonreceiving BSs. © 2014 IEEE.

关键词： autonomous aerial vehicle (AAV) network Collaborative beamforming (CB) evolutionary computation interference mitigation multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

TRANSIT-EEG - A Framework for Cross-Subject Classification with Subject Specific Adaptation

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Ahuja, Chirag Sethia, Divyashikha Delhi Technology University Department of Computer Science and Engineering Delhi India Delhi Technology University Department of Software Engineering Delhi India

Electroencephalography (EEG) is pivotal in monitoring and analysing cerebral activity across diverse domains, including medical diagnostics, cognitive neuroscience, and brain-computer interfaces. However, the inherent intricacy of EEG signals and their subject-specific characteristics pose formidable challenges in devising robust and generalisable classification models. Traditional EEG signal classification paradigms rely on extensive subject-specific datasets. Also, the domain adaption for new subjects often leads to "catastrophic forgetting,"thereby diminishing the performance of model trained on prior subjects. This paper proposes a novel framework, Transfer and Robust Adaptation of New Subjects in EEG Technology (TRANSIT-EEG), designed to adapt adeptly to new subjects. TRANSIT-EEG demonstrates resilience to subject-specific artefacts by integrating synthetic data generation using the proposed subject-specific augmentation model - Individualised Diffusion Probabilistic Model (IDPM). Also, it employs a robust Self Organising Graph Attention Transformer (SOGAT) that dynamically constructs a graph for each subject, fostering a more accurate classification. Moreover, TRANSIT-EEG introduces adapter-based finetuning using Low-Rank Adaptation (LoRA) for new subjects, enriching the adaptation process. The TRANSIT-EEG framework presents a promising avenue for advancing the realm of EEG signal classification. Evaluation of widely studied datasets, specifically focusing on two significant tasks, SEED for Emotion Recognition and PhyAat for Auditory Activity Recognition, substantiates the efficacy and versatility of TRANSIT-EEG. This validation indicates a substantial stride toward achieving more generalisable and accurate EEG signal classification. © 2016 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Strategy Masking: A Method for Guardrails in Value-based Reinforcement Learning Agents

arXiv

引用

arXiv 2025年

作者： Keane, Jonathan Keyser, Sam Kedziora, Jeremy Department of Computer Science and Software Engineering Milwaukee School of Engineering MilwaukeeWI United States

The use of reward functions to structure AI learning and decision making is core to the current reinforcement learning paradigm;however, without careful design of reward functions, agents can learn to solve problems in ways that may be considered "undesirable" or "unethical. Without thorough understanding of the incentives a reward function creates, it can be difficult to impose principled yet general control mechanisms over its behavior. In this paper, we study methods for constructing guardrails for AI agents that use reward functions to learn decision making. We introduce a novel approach, which we call strategy masking, to explicitly learn and then suppress undesirable AI agent behavior. We apply our method to study lying in AI agents and show that it can be used to effectively modify agent behavior by suppressing lying post-training without compromising agent ability to perform effectively. © 2025, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

PathNetDRP: a novel biomarker discovery framework using pathway and protein–protein interaction networks for immune checkpoint inhibitor response prediction

引用

BMC Bioinformatics 2025年第1期26卷 1-24页

作者： Lee, Dohee Ahn, Jaegyoon Choi, Jonghwan Department of Computer Science and Engineering Incheon National University 119 Academy-ro Yeonsu-gu Incheon22012 Korea Republic of Division of Software Hallym University 1 Hallymdaehak-gil Gangwon-do Chuncheon24252 Korea Republic of

Background: Predicting immune checkpoint inhibitor (ICI) response remains a significant challenge in cancer immunotherapy. Many existing approaches rely on differential gene expression analysis or predefined immune signatures, which may fail to capture the complex regulatory mechanisms underlying immune response. Network-based models attempt to integrate biological interactions, but they often lack a quantitative framework to assess how individual genes contribute within pathways, limiting the specificity and interpretability of biomarkers. Given these limitations, we developed PathNetDRP, a framework that integrates biological pathways, protein-protein interaction networks, and machine learning to identify functionally relevant biomarkers for ICI response prediction. Results: We introduce PathNetDRP, a novel biomarker discovery approach that applies the PageRank algorithm to prioritize ICI-associated genes, maps them to relevant biological pathways, and calculates PathNetGene scores to quantify their contribution to immune response. Unlike conventional methods that focus solely on gene expression differences, PathNetDRP systematically incorporates biological context to improve biomarker selection. Validation across multiple independent cancer cohorts showed that PathNetDRP achieved strong predictive performance, with cross-validation the area under the receiver operating characteristic curves increasing from 0.780 to 0.940. Interestingly, PathNetDRP did not merely improve predictive accuracy;it also provided insights into key immune-related pathways, reinforcing its potential for identifying clinically relevant biomarkers. Conclusion: The biomarkers identified by PathNetDRP demonstrated robust predictive performance across cross-validation and independent validation datasets, suggesting their potential utility in clinical applications. Furthermore, enrichment analysis highlighted key immune-related pathways, providing a deeper understanding of their role in ICI res

关键词： Immune system

来源：评论

学校读者我要写书评

暂无评论

An Analysis of Anonymous MQTT for Publish-Subscribe-Based IoT Networks

引用

IEEE Transactions on Network science and engineering 2025年

作者： Fukushima, Yudai Tsunamoto, Hotaru Sakai, Kazuya Sun, Min-Te Ku, Wei-Shinn Tokyo Metropolitan University Department of Electrical Engineering and Computer Science Tokyo191-0065 Japan National Central University Department of Computer Science and Information Engineering Taoyuan320 Taiwan Auburn University Department of Computer Science and Software Engineering AuburnAL36849 United States

Message queuing telemetry transport (MQTT) is widely used as a communication primitive in publish-subscribe-based IoT applications. However, the current MQTT standard does not support the privacy of IoT devices and users. Therefore, in this paper, we address the anonymous communications for MQTT-based IoT networks by tailored onion routing. To this end, we first introduce the concept of distributed IoT broker networks, in which a collection of IoT brokers are interconnected with each other. These brokers serve as onion routers. Then, we propose a generic anonymous messaging protocol (A-MQTT) for publish-subscribe-based IoT systems. Unlike typical anonymous communications, there are multiple destination IoT devices, called subscribers, in MQTT contexts. Hence, the privacy notions, such as traceable rate, device anonymity, and path anonymity, are redesigned. To illuminate the fundamental privacy issues, closed-form approximations for these privacy metrics are modeled. In addition, simulation results demonstrate that our A-MQTT significantly improves the security performance and that our proposed models closely approximate the various privacy performance. Furthermore, a proof-of-concept protocol is implemented on a Raspberry Pi 4 in order to show that the proposed A-MQTT can be deployed in an IoT environment. © 2013 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Segmentation Techniques Applied to CNNs for Cervical Cancer Classification

引用

IEEE Access 2025年 13卷 74678-74688页

作者： Ortiz-Gonzalez, Ana Martinez-Espana, Raquel Morales-Garcia, Juan Imbernon, Baldomero Martinez-Mas, Jose Alvarez, Mauricio A. Romero, Oscar D. Martinez-Cendan, Juan Pedro Bueno-Crespo, Andres University Hospital Complex of Cartagena Pathology Department Spain University of Murcia Information and Communications Engineering Department Spain University of Alicante Department of Software and Computing Systems Spain Spain Catholic University of Murcia Faculty of Medicine Spain CIAGO Gynecological Center Obstetrics and Gynecology Department Spain University of Manchester Computer Science Department United Kingdom University General Hospital Santa Lucía Obstetrics and Gynecology Department Spain

Cervical cancer continues to be a significant global health issue, ranking as the fourth most prevalent cancer affecting women. Enhancing population screening programs by refining the examination of cervical samples conducted by skilled pathologists offers a compelling alternative for early detection of this disease. Deep Learning facilitates the development of automatic classification models to aid experts in this task. However, it is increasingly important to bring explainability to the model both to understand how the network learns to identify pathology and to bring confidence to the diagnosis. In this paper, we design an automatic segmentation masks for the classification of cervicovaginal cell images. This automatic segmentation is combined in a classification model that allows the models to improve their performance thanks to the morphological information provided by the combined segmentation in a Global Average Pooling layer with the convolutional network analysis of the original image. The models will be trained with real data so that learning can recognize the diversity of colors, shapes and sizes of human cell nuclei. The results show a robust and explainable model with satisfactory results, obtaining an F1 Score value of 0.935 in binary classification of revisable and non-revisable cell. © 2013 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Fire Detection for Industrial and Environmental Safety using IoT-Integrated Vision Sensors and Residual Clutch Attention Network and Depthwise Distinguishable Convolutional Neural Networks 3

Enhanced Fire Detection for Industrial and Environmental Saf...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Christy Sujatha, D. Singh, Priyanshu Vallikannu, C. Varman, Ravi Skanda, M.G. Gavaskar, T. Department of Software Engineering Periyar Maniammai Institute of Science & Technology Tamil Nadu Thanjavur India Department of Computer Science and Engineering R.V college of engineering Karnataka Bangalore India Department of Humanities and Sciences Rajalakshmi Engineering College Tamil Nadu Chennai India Department of Electrical and Electronics Engineering Karpagam academy of Higher Education Tamil Nadu Coimbatore India Department of Industrial and Production Engineering SJCE JSS Science and Technology University Karnataka Mysore India Department of Mechanical Engineering St. Joseph's College of Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331527549

Fire detection is an important factor in improved safety in industrial and environmental conditions. The conventional flame detectors, largely relying on heat and smoke detectors, have drawbacks of time lag, low sensitivity, and low coverage when compared with our requirement in large industrial scenes and vast natural terrains vulnerable to fire occurrence. These systems are highly unsuitable for dynamic and high-risk situations as they require a higher accuracy and a faster reaction time for the alarms to be efficient as is now the case due to the aforementioned reasons. In an attempt to remedy these limitations, this research introduces a fire detection system using IoT and vision sensors that combines a RCAN with DDCNN. This architecture is tuned using the Crayfish Optimization Algorithm (COA), which seeks to improve model parameter to improve response time and accuracy. By incorporating feedbacks from sensors placed at its different parts and reading from the environment, the RCAN-DDCNN model can quickly identify the fire patterns and respond by activating the sprinkler systems as well as setting off alarms. The proposed system presents a superior option for fire detecting because it is scalable and adaptive and it provides high degree of precision, making it an optimal development in fire detection technology for industry and environment. The introduced approach attains higher accuracy as 99%. © 2025 IEEE.

关键词： Sprinkler systems (fire fighting)

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：