检索结果-内蒙古大学图书馆

Unified output feedback based prescribed performance consensus tracking control of heterogeneous multi-agent systems

引用

IEEE/CAA Journal of Automatica Sinica 2025年

作者： Luo, Dahui Wang, Yujuan Lewis, Frank L. Song, Yongduan Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing University The School of Automation Chongqing University Chongqing400044 China Star Institute for Intelligent Systems Chongqing400044 China Uta Research Institute University of Texas at Arlington Fort WorthTX76118 United States

This paper proposes an output-feedback based prescribed performance consensus tracking control methodology for a class of heterogeneous multi-agent systems (HMASs) with inconsistent system structure, where the performance behavior is allowed to be different from that of each other. Both the heterogeneous system structures and the nonidentical performance requirements make the control problem much more challenging than that of MASs with identical structure and performance requirement. This is mainly due to the coupling effect of the system dynamics and performance restriction of each agent in the cooperative control action. The key to solve this problem is to introduce a dual-phase performance-guaranteed method, in which the consensus tracking error is decomposed into auxiliary tracking error and filter tracking error and then the whole performance control is decomposed into two phases. By confining the two errors respectively, the practical tracking error can be proved to be explicitly confined within an arbitrarily given performance envelope by merely adjusting the design parameters rather than modifying control structure. Moreover, the prescribed performance control (PPC) result is not only uniform with any initial conditions and design parameters, allowing it to be global, but also unifying both the global and semi-global result into one frame, distinguishing itself from most existing PPC works where either only global or only semi-global result is guaranteed. Finally, the effectiveness of the proposed control scheme is confirmed by the simulation conducted on a group of tunnel-diode circuits (TDC). © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Levees

来源：评论

学校读者我要写书评

暂无评论

Leveraging Personality Traits for Enhanced Graph Convolutional Networks-Based Social Recommendation Systems

SSRN

引用

SSRN 2023年

作者： Guo, Xiangxing Zhou, Wei Yang, Zhengyi Fu, Cheng Wen, Junhao School of Big Data and Software Engineering Chongqing University Daxuecheng South Rd. 55 Chognqing400044 China Key Laboratory of Dependable Service Computing in Cyber Physical Society MoE Chognqing400030 China

Social recommendation has emerged as a crucial technology for online service platforms, with a growing body of research in recent years. People's varying personalities influence their preferences for items and friends, and neglecting these personalities can result in impure representations that affect recommendation outcomes. In this paper, we propose a Personality-Aware Graph Convolutional Network (PGCN-SRec) model to capture users' preferences based on their personalities. The model first classifies users and their neighbors into personality subgraphs using their representations, and then graph convolution is performed within these subgraphs. User representations from social and interaction subgraphs are fused through a novel fusion module, and layer representations are generated by weighted summation. Experimental results demonstrate that our proposed method significantly improves recommendation performance on the Lastfm and Ciao datasets (by 1\% to 5\%). Furthermore, PGCN-SRec effectively alleviate the oversmoothing problem associated with stacked graph neural networks. Our PyTorch implementation is available at https://***/hsianghsing/PGCN-SRec. © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

CMCache: An Adaptive Cross-Level Data Placement Method for Multi-Level Cache

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Zeng, Zhaoyang Tan, Yujuan Ma, Zhulin Li, Jiali Zhao, Sanle Liu, Duo Chen, Xianzhang Ren, Ao Chongqing University College of Computer Science Chongqing400044 China Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing400044 China Chongqing Universityof Posts and Telecommunications College of Software Engineering China Chongqing University College of Big Data and Software Engineering Chongqing China

Multi-level cache systems enhance I/O performance by optimizing data placement across various cache levels from a global perspective. However, existing methods often struggle to place data at the optimal cache level promptly due to their reliance on historical access patterns and inflexible placement strategies. These methods face two main challenges: (1) For already cached data with sufficient access history, existing approaches only optimize movement between adjacent cache levels, potentially delaying data arrival at its globally optimal cache level and leading to unnecessary bandwidth consumption and increased latency. (2) For newly entered data without access history, current methods cannot accurately predict their future hotness and simply place them at a fixed cache level (i.e. first or last level), overlooking future accesses of new data and potentially resulting in high cache miss rates or cache pollution. To address these issues, we propose CMCache, an adaptive cross-level data placement method for multi-level cache. CMCache applies distinct placement strategies for cached and new data to reach the optimal level timely, considering their different characteristics. It also logically divides cache space into two sections to manage cached and new data separately, dynamically adjusting section sizes based on access patterns. This approach significantly improves data placement efficiency, achieving up to an 89% reduction in miss rates and a 79% decrease in average response times compared to existing methods. © 2025 IEEE.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

RASTE: A Relation-Guided Joint Method for Aspect Sentiment Triplet Extraction 19

RASTE: A Relation-Guided Joint Method for Aspect Sentiment T...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Zhong, Linyang Shang, Jiaxing Zheng, Linjiang Hao, Fei Cao, Weiwei Sun, Hong Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society College of Computer Science Chongqing China Shaanxi Normal University School of Computer Science Xian China Civil Aviation Flight University of China Key Laboratory of Flight Techniques and Flight Safety Guanghan China Civil Aviation Flight University of China Flight Technology and Flight Safety Research Base Guanghan China

ISBN: (纸本)9798350346558

Aspect Sentiment Triplet Extraction (ASTE) is an important subtask of aspect-based sentiment analysis. It aims to extract aspect terms, corresponding sentiment polarities and related opinion terms from a sentence. The most advanced research efforts solve this problem in an end-to-end manner. However, they usually use one classifier to handle both relation detection and sentiment polarity classification tasks for aspectopinion pairs, which affects the prediction performance of the classifier. Moreover, the previous works treat subtasks equally, ignoring the differences between subtasks. In this paper, we propose a relation-guided method that models the relation detection and sentiment polarity classification subtasks differently to extract aspect sentiment triplets more effectively. Further, we capture the corresponding contextual features for each subtask separately to improve the overall performance of the model. We conducted experiments on two group benchmark datasets. Our model turns out to be one of the state-of-the-art models with effectiveness and superiority according to the experimental results. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

INGB: Informed Nonlinear Granular Ball Oversampling Framework for Noisy Imbalanced Classification

arXiv

引用

arXiv 2023年

作者： Li, Min Zhou, Hao Liu, Qun Shao, Yabin Wang, Guoying The Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing China The Key Laboratory of Dependable Services Computing in Cyber Physical Society-Ministry of Education College of Computer Science Chongqing University Chongqing China

In classification problems, the datasets are usually imbalanced, noisy or complex. Most sampling algorithms only make some improvements to the linear sampling mechanism of the synthetic minority oversampling technique (SMOTE). Nevertheless, linear oversampling has several unavoidable drawbacks. Linear oversampling is susceptible to overfitting, and the synthetic samples lack diversity and rarely account for the original distribution characteristics. An informed nonlinear oversampling framework with the granular ball (INGB) as a new direction of oversampling is proposed in this paper. It uses granular balls to simulate the spatial distribution characteristics of datasets, and informed entropy is utilized to further optimize the granular-ball space. Then, nonlinear oversampling is performed by following high-dimensional sparsity and the isotropic Gaussian distribution. Furthermore, INGB has good compatibility. Not only can it be combined with most SMOTE-based sampling algorithms to improve their performance, but it can also be easily extended to noisy imbalanced multi-classification problems. The mathematical model and theoretical proof of INGB are given in this work. Extensive experiments demonstrate that INGB outperforms the traditional linear sampling frameworks and algorithms in oversampling on complex datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fault-Tolerant Controller and Operation Strategies Designed for Mixed Vehicular Platoons in the Vicinity of a Signalized Intersection

SSRN

引用

SSRN 2022年

作者： Liu, Xiaoyu Zhao, Min Sun, Dihua Wang, Shihui Zhang, Yicai Key Laboratory of Dependable Service Computing in Cyber-Physical Society Ministry of Education Chongqing University Chongqing 400044 China College of Automation Chongqing University Chongqing 400044 China

Trajectories control for vehicles in the vicinity of a signalized intersection under the mixed traffic scenario can improve fuel efficiency and shorten travel time (TT). The emergence of Connected and Automated Vehicles (CAVs) enables control of trajectories from the platoon level. At the same time, the actuator faults are not conducive to implementing trajectories control, and fault-tolerant control of transportation systems under 100% penetration rate (PR) of CAVs is no longer applicable. Hence, mixed vehicular platoons are investigated under V2X in this paper. An adaptive fault-tolerant platoon controller is constructed under the mixed traffic scenario. Meanwhile, the platoon splitting and merging strategies for trajectories control considering the non-connected characteristics of AVs are designed. The presented methods are verified through simulations under different conditions and comparison simulations. © 2022, The Authors. All rights reserved.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Weapon target assignment strategy for multi-missile cooperative guidance with auction algorithm 40

Weapon target assignment strategy for multi-missile cooperat...

引用

40th Chinese Control Conference, CCC 2021

作者： Li, Qingze Dong, Xiwang Li, Qingdong Yu, Jianglong Ren, Zhang Beihang University School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beijing100191 China Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education of China Chongqing University Chongqing400044 China

ISBN: (纸本)9789881563804

This paper presents a weapon target assignment method to reduce maneuverability overload through redistribution for multi-missile cooperative attack. Firstly, a dynamic constrained model of multi-missile cooperative attack on multi-target is established. Secondly, in order to evaluate the missile's cooperative attack performance better, a cooperative attack probability matrix considering the cooperative attack efficiency is constructed by taking the time-to-go and the line-of-sight rate as indexes. Three kinds of maneuvering overload results are compared to verify the effectiveness of redistribution, including unassigned process, primary target assignment and redistribution at the beginning of mid-to-terminal guidance handover. Then, an auction algorithm is used to solve the target assignment problem under multiple constraints. Finally, the simulation results show that the proposed algorithm is much less time-consuming than the existing intelligent optimization algorithms and meets the real-time requirement. © 2021 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

A Naming Pattern Based Approach for Method Name Recommendation

A Naming Pattern Based Approach for Method Name Recommendati...

引用

International Symposium on Software Reliability Engineering (ISSRE)

作者： Yanping Yang Ling Xu Meng Yan Zhou Xu Zhongyang Deng Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Ministry of Education China School of Big Data and Software Engineering Chongqing University Chongqing China

ISBN: (数字)9781665451321

ISBN: (纸本)9781665451338

Method names in software projects are significant for developers to understand the method functionality. Existing state-of-the-art automated approaches tend to explore tokens composing method names from method contexts. However, the method name is not a simple combination of tokens, as it is structured and contains many repetitive naming patterns (e.g. “get __”, “create __”). Through a large-scale empirical analysis on 15M methods from 14K real software projects developed with Java codes, we found repetitive naming patterns in method names. In addition, the names of two function-similar methods usually have the same naming pattern. Based on our empirical study, we propose a naming pattern-based approach for method name recommendation, named Nam-Pat. Specifically, for a target method, NamPat first retrieve the most similar method from the training data by estimating their body code similarity. Then, the name of the most similar method is used as the pattern guider to provide the naming pattern, and NamPat combines it with the context information of the target method to perform method name recommendation. To verify the effectiveness of the proposed approach, we conducted experiments on 17M methods from a widely used Java dataset. Experimental results show that compared with Code2vec, Code2seq, MNire, and Cognac, NamPat improves the state-of-the-art approaches in precision (5.8%-27.1%), recall (11.1%-60.1 %), and F-score (8.5 %-43.9%), which proves the effectiveness of our proposed approach.

关键词： Java Codes Source coding Semantics Training data Software Generators

来源：评论

学校读者我要写书评

暂无评论

Implementation Analysis of Reachability Graph and Its Application in Net Learning

Implementation Analysis of Reachability Graph and Its Applic...

引用

Computer, Control and Robotics (ICCCR), International Conference on

作者： Mingjian Guang Chungang Yan Zihao Lu Rui Duan Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China

ISBN: (数字)9798350373141

ISBN: (纸本)9798350373158

Reachability represents the most fundamental dynamic property of Petri nets. The reachability graph serves as a crucial tool for analyzing reachability, and its generation algorithm has garnered widespread attention. However, most of the existing work has focused primarily on the accuracy of the generation algorithm, often overlooking computational and time costs. Therefore, this paper concentrates on the implementation of reachability graphs and proposes three implementation methods: definition-based (DB), matrix-based (MB), and a fast generation method without self-loops (FG). Through comprehensive experiments, we evaluate and analyze the running speed and applicable scenarios of these three methods. Furthermore, we have successfully applied the proposed methods in net learning.

关键词： Digital control Costs Accuracy Heuristic algorithms Petri nets Benchmark testing Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Pushing The Limit of LLM Capacity for Text Classification 25

Pushing The Limit of LLM Capacity for Text Classification

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Yazhou Zhang Mengyao Wang Qiuchi Li Prayag Tiwari Jing Qin Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education Chongqing University Chongqing Chongqing China and Tianjin University Tianjin Tianjin China Zhengzhou University of Light Industry Zhengzhou China Copenhagen University Copenhagen Denmark Halmstad University Halmstad Sweden The Hong Kong Polytechnic University Hong Kong Hong Kong

ISBN: (纸本)9798400713316

In this era of open-ended language modeling, where task boundaries are gradually fading, an urgent question emerges: have we made significant progress in text classification with the full benefit of LLMs? To answer this question, we propose RGPT, an adaptive boosting framework tailored to produce a specialized text classification LLM by recurrently ensembling a pool of base learners. The base learners are constructed by adaptively adjusting the distribution of training samples and iteratively fine-tuning LLMs with them. Such base learners are then ensembled to be a specialized text classification LLM, by recurrently incorporating the historical predictions from the previous learners. Through a comprehensive empirical comparison, we show that RGPT significantly outperforms 8 state-of-the-art (SoTA) PLMs and 7 SoTA LLMs on four benchmarks by 2.90% on average. Further evaluation experiments reveal a clear superiority of RGPT over average human classification performance.

关键词： boosting

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：