检索结果-内蒙古大学图书馆

Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models

ACM Transactions on software Engineering and Methodology 1000年

作者： Quanjun Zhang Chunrong Fang Yi Zheng Yaxin Zhang Yuan Zhao Rubing Huang Jianyi Zhou Yun Yang Tao Zheng Zhenyu Chen Department of Computing Technologies Swinburne University of Technology Australia and State Key Laboratory for Novel Software Technology Nanjing University China State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Engineering Macau University of Science and Technology China Huawei Cloud Computing Technologies Co. Ltd. China Department of Computing Technologies Swinburne University of Technology Australia State Key Laboratory for Novel Software Technology Nanjing University China and Shenzhen Research Institute of Nanjing University China

Unit testing validates the correctness of the units of the software system under test and serves as the cornerstone in improving software quality and reliability. To reduce manual efforts in writing unit tests, some techniques have been proposed to generate test assertions automatically, including deep learning (DL)-based, retrieval-based, and integration-based ones. Among them, recent integration-based approaches inherit from both DL-based and retrieval-based approaches and are considered state-of-the-art. Despite being promising, such integration-based approaches suffer from inherent limitations, such as retrieving assertions with lexical matching while ignoring meaningful code semantics, and generating assertions with a limited training *** this paper, we propose a novel Retrieval-Augmented Deep Assertion Generation approach, namely RetriGen, based on a hybrid assertion retriever and a pre-trained language model (PLM)-based assertion generator. Given a focal-test, RetriGen first builds a hybrid assertion retriever to search for the most relevant test-assert pair from external codebases. The retrieval process takes both lexical similarity and semantical similarity into account via a token-based and an embedding-based retriever, respectively. RetriGen then treats assertion generation as a sequence-to-sequence task and designs a PLM-based assertion generator to predict a correct assertion with historical test-assert pairs and the retrieved external assertion. Although our concept is general and can be adapted to various off-the-shelf encoder-decoder PLMs, we implement RetriGen to facilitate assertion generation based on the recent CodeT5 model. We conduct extensive experiments to evaluate RetriGen against six state-of-the-art approaches across two large-scale datasets and two metrics. The experimental results demonstrate that RetriGen achieves 57.66% and 73.24% in terms of accuracy and CodeBLEU, outperforming all baselines with an average improvement of 50.66%

关键词： Unit Testing Assertion Generation Pre-trained Language Models AI4SE

来源：评论

学校读者我要写书评

暂无评论

Topology in Process Calculus 1

引用

1000年

作者： Mingsheng Ying

ISBN: (数字)9781461301233

ISBN: (纸本)9780387950921;9781461265221

Communication and concurrency are essential in understanding complex dynamic systems, and there have been many theories to deal with them such as Petri nets, CSP and ACP. Among them, CCS (process calculus is one of the most important and mathematically developed models of communication and concurrency. Various behavior equivalences between agents, such as (strong and weak) bisimilarity, observation congruence, trace equivalence, testing equivalence and failure equivalence, are central notions in process calculus. In the real applications of process calculus, specification and implementation are described as two agents, correctness of programs is treated as a certain behavior equivalence between specification and implementation, and then the proof of correctness of programs is a task to establish some behavior equivalence between them. The goal of this book is to provide some suitable and useful concepts and tools for the understanding and analysis of approximate correctness of programs in concurrent systems. Throughout this book the focus is on the framework of process calculus, and the main idea is to construct some natural and reasonable topological structures which can reveal suitably a mechanism of approximate computation in process calculus and to work out various relationships among processes which are compatible with these topological structures.

关键词： software Engineering/Programming and Operating Systems

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement Learning based Edge Content Caching for Connected Autonomous Vehicles in IoV

引用

ACM Transactions on Autonomous and Adaptive Systems 1000年

作者： Xiaolong Xu Linjie Gu Muhammad Bilal Maqbool Khan Yiping Wen Guoqiang Liu Yuan Yuan School of Software Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services Nanjing University of Information Science and Technology China Changwang School of Honors Nanjing University of Information Science and Technology China Department of Computer and Electronics Systems Engineering Hankuk University of Foreign Studies Korea Department of IT and Computer Science Pak-Austria Fachhochschule-Institute of Applied Sciences and Technology Pakistan School of Computer Science and Engineering Hunan University of Science and Technology China School of Software Nanjing University of Information Science and Technology China School of Computer Science and Engineering Beihang University State Key Laboratory of Software Development Environment Zhongguancun Laboratory China

Connected Autonomous Vehicle (CAV) Driving, as a data-driven intelligent driving technology within the Internet of Vehicles (IoV), presents significant challenges to the efficiency and security of real-time data management. The combination of Web3.0 and edge content caching holds promise in providing low-latency data access for CAVs’ real-time applications. Web3.0 enables the reliable pre-migration of frequently requested content from content providers to edge nodes. However, identifying optimal edge node peers for joint content caching and replacement remains challenging due to the dynamic nature of traffic flow in IoV. Addressing these challenges, this article introduces GAMA-Cache, an innovative edge content caching methodology leveraging Graph Attention Networks (GAT) and Multi-Agent Reinforcement Learning (MARL). GAMA-Cache conceptualizes the cooperative edge content caching issue as a constrained Markov decision process. It employs a MARL technique predicated on cooperation effectiveness to discern optimal caching decisions, with GAT augmenting information extracted from adjacent nodes. A distinct collaborator selection mechanism is also developed to streamline communication between agents, filtering out those with minimal correlations in the vector input to the policy network. Experimental results demonstrate that, in terms of service latency and delivery failure, the GAMA-Cache outperforms other state-of-the-art MARL solutions for edge content caching in IoV.

关键词： Content Caching Reinforcement Learning Connected Autonomous Driving

来源：评论

学校读者我要写书评

暂无评论

Conceptual Modeling for Advanced Application Domains 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Shan Wang Katsumi Tanaka Shuigeng Zhou Tok-Wang Ling Jihong Guan Dong-qing Yang Fabio Grandi Eleni E. Mangina Il-Yeol Song Heinrich C. Mayr

来源：评论

学校读者我要写书评

暂无评论

An X Language-Driven Framework for Systematic Development of Digital Twin Healthcare Systems

引用

ACM Transactions on Multimedia Computing, Communications, and Applications 1000年

作者： Kunyu Xie Lin Zhang Yuan Yang Xiaohe Li Ridha Khedri Zhen Chen M. Jamal Deen Simulation Technology Innovation Center Hangzhou International Innovation Institute of Beihang University Hangzhou 311115 Zhejiang China School of Automation Science and Electrical Engineering Beihang University Beijing 100191 China State Key Laboratory of Intelligent Manufacturing Systems Technology Beijing 100191 China School of Automation Science and Electrical Engineering Beihang University Beijing 100191 China Shenzhen Third People’s Hospital & Second Hospital Affiliated to Southern University of Science and Technology Shenzhen 518112 Guangdong China Dept. of Computing and Software McMaster University Hamilton Ontario Canada L8S 4K1 Department of Electrical and Computer Engineering McMaster University Hamilton ON L8S 4L8 Canada

The rapid advancements in big data and the Internet of Things (IoT) have significantly accelerated the digital transformation of medical institutions, leading to the widespread adoption of Digital Twin Healthcare (DTH). The Cloud DTH Platform (CDTH) serves as a cloud-based framework that integrates DTH models, healthcare resources, patient data, and medical services. By leveraging real-time data from medical devices, the CDTH platform enables intelligent healthcare services such as disease prediction and medical resource optimization. However, the platform functions as a system of systems (SoS), comprising interconnected yet independent healthcare services. This complexity is further compounded by the integration of both black-box AI models and domain-specific mechanistic models, which pose challenges in ensuring the interpretability and trustworthiness of DTH models. To address these challenges, we propose a Model-Based Systems Engineering (MBSE)-driven DTH modeling methodology derived from systematic requirement and functional analyses. To implement this methodology effectively, we introduce a DTH model development approach using the X language, along with a comprehensive toolchain designed to streamline the development process. Together, this methodology and toolchain form a robust framework that enables engineers to efficiently develop interpretable and trustworthy DTH models for the CDTH platform. By integrating domain-specific mechanistic models with AI algorithms, the framework enhances model transparency and reliability. Finally, we validate our approach through a case study involving elderly patient care, demonstrating its effectiveness in supporting the development of DTH models that meet healthcare and interpretability requirements.

关键词： Digital Twin Model-based system engineering X Language Medical Cyber-Physical Systems Digital Twin Healthcare Design

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Logic and Soft Computing 1

引用

丛书名： The International Series on Asian Studies in computer and Information science

1000年

作者： Guoqing Chen Mingsheng Ying Kai-Yuan Cai

ISBN: (数字)9781461552611

ISBN: (纸本)9780792386506;9781461373995

contains contributions from world-leading experts from both the academic and industrial communities. The first part of the volume consists of invited papers by international authors describing possibilistic logic in decision analysis, fuzzy dynamic programming in optimization, linguistic modifiers for word computation, and theoretical treatments and applications of fuzzy reasoning. The second part is composed of eleven contributions from Chinese authors focusing on some of the key issues in the fields: stable adaptive fuzzy control systems, partial evaluations and fuzzy reasoning, fuzzy wavelet neural networks, analysis and applications of genetic algorithms, partial repeatability, rough set reduction for data enriching, limits of agents in process calculus, medium logic and its evolution, and factor spaces canes.;These contributions are not only theoretically sound and well-formulated, but are also coupled with applicability implications and/or implementation treatments. The domains of applications realized or implied are: decision analysis, word computation, databases and knowledge discovery, power systems, control systems, and multi-destinational routing. Furthermore, the articles contain materials that are an outgrowth of recently conducted research, addressing fundamental and important issues of fuzzy logic and soft computing.

关键词： Mathematical Logic and Foundations software Engineering/Programming and Operating Systems Calculus of Variations and Optimal Control Optimization Electrical Engineering Data Structures and Information Theory Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

Parallel and Distributed Processing and Applications 1

引用

丛书名： Lecture Notes in computer science

1000年

作者： Yi Pan Daoxu Chen Minyi Guo Jiannong Cao Jack Dongarra

ISBN: (数字)9783540321002

ISBN: (纸本)9783540297697

Welcome to the proceedings of ISPA 2005 which was held in the city of Nanjing. Parallel computing has become a mainstream research area in computer science and the ISPA conference has become one of the premier forums for the presentation of new and exciting research on all aspects of parallel computing. We are pleased to present the proceedings for the 3rd International Symposium on Parallel and Distributed Processing and Applications (ISPA 2005), which comprises a collection of excellent technical papers, and keynote speeches. The papers accepted cover a wide range of exciting topics, including architectures, software, networking, and applications. The conference continues to grow and this year a record total of 968 manuscripts (including workshop submissions) were submitted for consideration by the Program Committee or workshops. From the 645 papers submitted to the main conference, the Program Committee selected only 90 long papers and 19 short papers in the program. Eight workshops complemented the outstanding paper sessions.

关键词： computer System Implementation Algorithm Analysis and Problem Complexity computer Communication Networks Information Systems Applications (incl. Internet) System Performance and Evaluation software Engineering

来源：评论

学校读者我要写书评

暂无评论

Secure Collaborative Learning for Self-Adaptive Systems on Connected Autonomous Vehicles

引用

ACM Transactions on Autonomous and Adaptive Systems 1000年

作者： Xiaotong Wu Yuwen Liu Xiaoxiao Chi Rong Jiang Xiaokang Zhou Wajid Rafique Maqbool Khan Alibaba Business School Hangzhou Normal University China College of Computer Science and Technology China University of Petroleum (East China) China Department of Computing Macquarie University Australia Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics China Faculty of Business Data Science Kansai University Japan and RIKEN Center for Advanced Intelligence Project Japan Department of Electrical and Software Engineering University of Calgary Canada Software Competence Center Hagenberg Austria

As an advanced carrier of on-board sensors, connected autonomous vehicle (CAV) can be viewed as an aggregation of self-adaptive systems with monitor-analyze-plan-execute (MAPE) for vehicle-related services. Meanwhile, machine learning (ML) has been applied to enhance analysis and plan functions of MAPE so that self-adaptive systems have optimal adaption to changing conditions. However, most of ML-based approaches don’t utilize CAVs’ connectivity to collaboratively generate an optimal learner for MAPE, because of sensor data threatened by gradient leakage attack (GLA). In this article, we first design an intelligent architecture for MAPE-based self-adaptive systems on Web 3.0-based CAVs, in which a collaborative machine learner supports the capabilities of managing systems. Then, we observe by practical experiments that importance sampling of sparse vector technique (SVT) approaches cannot defend GLA well. Next, we propose a fine-grained SVT approach to secure the learner in MAPE-based self-adaptive systems, that uses layer and gradient sampling to select uniform and important gradients. At last, extensive experiments show that our private learner spends a slight utility cost for MAPE (e.g., \(0.77\%\) decrease in accuracy) defending GLA and outperforms the typical SVT approaches in terms of defense (increased by \(10\%\sim 14\%\) attack success rate) and utility (decreased by \(1.29\%\) accuracy loss).

关键词： collaborative learning optimal adaption vehicle application data security self-adaptive system

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of Parameter-Efficient Fine-Tuning for software Engineering Tasks

引用

ACM Transactions on software Engineering and Methodology 1000年

作者： Wentao Zou Zongwen Shen Qi Li Jidong Ge Chuanyi Li Xiang Chen Xiaoyu Shen LiGuo Huang Bin Luo National Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence and Computer Science Nantong University China Eastern Institute for Advanced Study China Department of Computer Science Southern Methodist University USA

Pre-trained models (PTMs) have succeeded in various software engineering (SE) tasks following the “pre-train then fine-tune” paradigm. As fully fine-tuning all parameters of PTMs can be computationally expensive, a potential solution is parameter-efficient fine-tuning (PEFT), which freezes PTMs while introducing extra parameters. Although PEFT methods have been applied to SE tasks, researchers often focus on specific scenarios and lack a comprehensive comparison of PTMs from different aspects such as field, size, and architecture. To fill this gap, we have conducted an empirical study on six PEFT methods, eight PTMs, and four SE tasks. The experimental results reveal several noteworthy findings. For example, model architecture has little impact on PTM performance when using PEFT methods. Additionally, we provide a comprehensive discussion of PEFT methods from three perspectives. First, we analyze the effectiveness and efficiency of PEFT methods. Second, we explore the impact of the scaling factor hyperparameter. Finally, we investigate the application of PEFT methods on the latest open-source large language model, Llama 3.2. These findings provide valuable insights to guide future researchers in effectively applying PEFT methods to SE tasks.

关键词： parameter-efficient fine-tuning pre-trained model software engineering task empirical study effectiveness and efficiency

来源：评论

学校读者我要写书评

暂无评论

Vehicle Dynamics and Interaction for Trajectory Prediction and Traffic Control

引用

ACM Transactions on Autonomous and Adaptive Systems 1000年

作者： Jian Chen Shaorui Zhou Wei Wang Yuzhu Hu Jianqing Li Ben-Guo He Junxin Chen Marwan Omar Ali Kashif Bashir Xiping Hu School of Intelligent Systems Engineering Sun Yat-Sen University China Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen MSU-BIT University China School of Computer Science and Engineering Faculty of Innovation Engineering Macau University of Science and Technology Macao SAR China Key Laboratory of Ministry of Education on Safe Mining of Deep Metal Mines Northeastern University China the School of Software Dalian University of Technology China Information Technology and Management Illinois Institute of Technology USA Department of Computing and Mathematics Manchester Metropolitan University UK Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Rajpura 140401 Punjab India

Trajectory prediction is a crucial challenge in autonomous vehicle motion planning and decision-making techniques. However, existing methods face limitations in accurately capturing vehicle dynamics and interactions. To address this issue, this paper proposes a novel approach to extracting vehicle velocity and acceleration, enabling the learning of vehicle dynamics and encoding them as auxiliary information. The VDI-LSTM model is designed, incorporating graph convolution and attention mechanisms to capture vehicle interactions using trajectory data and dynamic information. Specifically, a dynamics encoder is designed to capture the dynamic information, a dynamic graph is employed to represent vehicle interactions, and an attention mechanism is introduced to enhance the performance of LSTM and graph convolution. To demonstrate the effectiveness of our model, extensive experiments are conducted, including comparisons with several baselines and ablation studies on real-world highway datasets. Experimental results show that VDI-LSTM outperforms other baselines compared, which obtains a 3% improvement on the average RMSE indicator over the five prediction steps.

关键词： Trajectory Prediction Vehicle Dynamics Interaction Perception Graph Convolution Attention Mechanism

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：