检索结果-内蒙古大学图书馆

Revisiting the LQR Problem of Singular Systems

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2236-2252页

作者： Komeil Nosrati Juri Belikov Aleksei Tepljakov Eduard Petlenkov IEEE the Department of Computer Systems Tallinn University of Technology the Department of Software Science Tallinn University of Technology

In the development of linear quadratic regulator(LQR) algorithms, the Riccati equation approach offers two important characteristics——it is recursive and readily meets the existence condition. However, these attributes are applicable only to transformed singular systems, and the efficiency of the regulator may be undermined if constraints are violated in nonsingular versions. To address this gap, we introduce a direct approach to the LQR problem for linear singular systems, avoiding the need for any transformations and eliminating the need for regularity assumptions. To achieve this goal, we begin by formulating a quadratic cost function to derive the LQR algorithm through a penalized and weighted regression framework and then connect it to a constrained minimization problem using the Bellman's criterion. Then, we employ a dynamic programming strategy in a backward approach within a finite horizon to develop an LQR algorithm for the original system. To accomplish this, we address the stability and convergence analysis under the reachability and observability assumptions of a hypothetical system constructed by the pencil of augmented matrices and connected using the Hamiltonian diagonalization technique.

关键词： DC motor optimal control penalized weighted regression power system quadratic regulator singular system

来源：评论

学校读者我要写书评

暂无评论

Re-quantization based binary graph neural networks

引用

Science China(Information Sciences) 2024年第7期67卷 160-171页

作者： Kai-Lang YAO Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing University

Binary neural networks have become a promising research topic due to their advantages of fast inference speed and low energy consumption. However, most existing studies focus on binary convolutional neural networks, while less attention has been paid to binary graph neural networks. A common drawback of existing studies on binary graph neural networks is that they still include lots of inefficient full-precision operations in multiplying three matrices and are therefore not efficient enough. In this paper, we propose a novel method, called re-quantization-based binary graph neural networks(RQBGN), for binarizing graph neural networks. Specifically, re-quantization, a necessary procedure contributing to the further reduction of superfluous inefficient full-precision operations, quantizes the results of multiplication between any two matrices during the process of multiplying three matrices. To address the challenges introduced by requantization, in RQBGN we first study the impact of different computation orders to find an effective one and then introduce a mixture of experts to increase the model capacity. Experiments on five benchmark datasets show that performing re-quantization in different computation orders significantly impacts the performance of binary graph neural network models, and RQBGN can outperform other baselines to achieve state-of-the-art performance.

关键词： graph neural networks binary neural networks mixture of experts computation-efficient algorithms

来源：评论

学校读者我要写书评

暂无评论

Stochastic normalized gradient descent with momentum for large-batch training

引用

Science China(Information Sciences) 2024年第11期67卷 77-91页

作者： Shen-Yi ZHAO Chang-Wei SHI Yin-Peng XIE Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing University

Stochastic gradient descent(SGD) and its variants have been the dominating optimization methods in machine learning. Compared with SGD with small-batch training, SGD with large-batch training can better utilize the computational power of current multi-core systems such as graphics processing units(GPUs)and can reduce the number of communication rounds in distributed training settings. Thus, SGD with large-batch training has attracted considerable attention. However, existing empirical results showed that large-batch training typically leads to a drop in generalization accuracy. Hence, how to guarantee the generalization ability in large-batch training becomes a challenging task. In this paper, we propose a simple yet effective method, called stochastic normalized gradient descent with momentum(SNGM), for large-batch training. We prove that with the same number of gradient computations, SNGM can adopt a larger batch size than momentum SGD(MSGD), which is one of the most widely used variants of SGD, to converge to an?-stationary point. Empirical results on deep learning verify that when adopting the same large batch size,SNGM can achieve better test accuracy than MSGD and other state-of-the-art large-batch training methods.

关键词： non-convex problems large-batch training stochastic normalized gradient descent momentum

来源：评论

学校读者我要写书评

暂无评论

Clustered Reinforcement Learning

引用

Frontiers of computer Science 2025年第4期19卷 43-57页

作者： Xiao MA Shen-Yi ZHAO Zhao-Heng YIN Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing UniversityNanjing 210023China Department of Electrical Engineering and Computer Sciences University of CaliforniaBerkeleyCA 94720-1770USA

Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)areas or high reward(quality)*** existing methods perform exploration by only utilizing the novelty of *** novelty and quality in the neighboring area of the current state have not been well utilized to simultaneously guide the agent’s *** address this problem,this paper proposes a novel RL framework,called clustered reinforcement learning(CRL),for efficient exploration in *** adopts clustering to divide the collected states into several clusters,based on which a bonus reward reflecting both novelty and quality in the neighboring area(cluster)of the current state is given to the *** leverages these bonus rewards to guide the agent to perform efficient ***,CRL can be combined with existing exploration strategies to improve their performance,as the bonus rewards employed by these existing exploration strategies solely capture the novelty of *** on four continuous control tasks and six hard-exploration Atari-2600 games show that our method can outperform other state-of-the-art methods to achieve the best performance.

关键词： deep reinforcement learning exploration count-based method clustering K-means

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Privacy Protection Scheme for Efficient Edge Computation Offloading in IoV

引用

Chinese Journal of Electronics 2024年第4期33卷 910-919页

作者： Liang YAO Xiaolong XU Wanchun DOU Muhammad Bilal School of Software Nanjing University of Information Science and Technology State Key Laboratory for Novel Software Technology Nanjing University Department of Computer and Electronics Systems Engineering Hankuk University of Foreign Studies

As a pivotal enabler of intelligent transportation system(ITS), Internet of vehicles(Io V) has aroused extensive attention from academia and industry. The exponential growth of computation-intensive, latency-sensitive,and privacy-aware vehicular applications in Io V result in the transformation from cloud computing to edge computing,which enables tasks to be offloaded to edge nodes(ENs) closer to vehicles for efficient execution. In ITS environment,however, due to dynamic and stochastic computation offloading requests, it is challenging to efficiently orchestrate offloading decisions for application requirements. How to accomplish complex computation offloading of vehicles while ensuring data privacy remains challenging. In this paper, we propose an intelligent computation offloading with privacy protection scheme, named COPP. In particular, an Advanced Encryption Standard-based encryption method is utilized to implement privacy protection. Furthermore, an online offloading scheme is proposed to find optimal offloading policies. Finally, experimental results demonstrate that COPP significantly outperforms benchmark schemes in the performance of both delay and energy consumption.

关键词： Industries Privacy Energy consumption Transportation Computational efficiency Encryption Protection

来源：评论

学校读者我要写书评

暂无评论

ASLP-DL—A Novel Approach Employing Lightweight Deep Learning Framework for Optimizing Accident Severity Level Prediction

引用

computers, Materials & Continua 2024年第2期78卷 2535-2555页

作者： Saba Awan Zahid Mehmood Department of Software Engineering University of Engineering and TechnologyTaxila47050Pakistan Department of Computer Engineering University of Engineering and TechnologyTaxila47050Pakistan

Highway safety researchers focus on crash injury severity,utilizing deep learning—specifically,deep neural networks(DNN),deep convolutional neural networks(D-CNN),and deep recurrent neural networks(D-RNN)—as the preferred method for modeling accident *** learning’s strength lies in handling intricate relation-ships within extensive datasets,making it popular for accident severity level(ASL)prediction and *** prior success,there is a need for an efficient system recognizing ASL in diverse road *** address this,we present an innovative Accident Severity Level Prediction Deep Learning(ASLP-DL)framework,incorporating DNN,D-CNN,and D-RNN models fine-tuned through iterative hyperparameter selection with Stochastic Gradient *** framework optimizes hidden layers and integrates data augmentation,Gaussian noise,and dropout regularization for improved *** and factor contribution analyses identify influential *** on three diverse crash record databases—NCDB 2018–2019,UK 2015–2020,and US 2016–2021—the D-RNN model excels with an ACC score of 89.0281%,a Roc Area of 0.751,an F-estimate of 0.941,and a Kappa score of 0.0629 over the NCDB *** proposed framework consistently outperforms traditional methods,existing machine learning,and deep learning techniques.

关键词： Injury severity prediction deep learning feature

来源：评论

学校读者我要写书评

暂无评论

Robust tube-based MPC with smooth computation for dexterous robot manipulation

引用

Science China(Information Sciences) 2024年第11期67卷 252-268页

作者： Yu LUO Tianying JI Fuchun SUN Qie SIMA Huaping LIU Mingxuan JING Jianwei ZHANG Department of Computer Science and Technology Tsinghua University Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Department of Informatics University of Hamburg

Dexterous robot manipulation has shone in complex industrial scenarios, where multiple manipulators, or fingers, cooperate to grasp and manipulate objects. When encountering multi-objective optimization with system constraints in such scenarios, model predictive control(MPC) has demonstrated exceptional performance in complex multi-robot manipulation tasks involving multi-objective optimization with system constraints. However, in such scenarios, the substantial computational load required to solve the optimal control problem(OCP) at each triggering instant can lead to significant delays between state sampling and control application, hindering real-time performance. To address these challenges, this paper introduces a novel robust tube-based smooth MPC approach for two fundamental manipulation tasks: reaching a given target and tracking a reference trajectory. By predicting the successor state as the initial condition for imminent OCP solving, we can solve the forthcoming OCP ahead of time, alleviating delay effects. Additionally,we establish an upper bound for linearizing the original nonlinear system, reducing OCP complexity and enhancing response speed. Grounded in tube-based MPC theory, the recursive feasibility and closed-loop stability amidst constraints and disturbances are ensured. Empirical validation is provided through two numerical simulations and two real-world dexterous robot manipulation tasks, which shows that the seamless control input by our methods can effectively enhance the solving efficiency and control performance when compared to conventional time-triggered MPC strategies.

关键词： dexterous robot manipulation model predictive control smooth computation

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 13卷 90316-90332页

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

A Transfer Learning Framework for Deep Multi-Agent Reinforcement Learning

引用

IEEE/CAA Journal of Automatica Sinica 2024年第11期11卷 2346-2348页

作者： Yi Liu Xiang Wu Yuming Bo Jiacun Wang Lifeng Ma the School of Automation Nanjing University of Science and Technology the Department of Computer Science and Software Engineering Monmouth University

Dear Editor,This letter presents a new transfer learning framework for the deep multi-agent reinforcement learning(DMARL) to reduce the convergence difficulty and training time when applying DMARL to a new scenario [1... 详细信息

关键词： Deep agent Framework

来源：评论

学校读者我要写书评

暂无评论

Understanding and Detecting Inefficient Image Displaying Issues in Android Apps

引用

Journal of computer Science & technology 2024年第2期39卷 434-459页

作者：李文杰马骏蒋炎岩许畅马晓星 State Key Laboratory of Novel Software Technology Nanjing UniversityNanjing 210023China Department of Computer Science and Technology Nanjing UniversityNanjing 210023China

Mobile applications(apps for short)often need to display ***,inefficient image displaying(IID)issues are pervasive in mobile apps,and can severely impact app performance and user *** paper first establishes a descriptive framework for the image displaying procedures of IID *** on the descriptive framework,we conduct an empirical study of 216 real-world IID issues collected from 243 popular open-source Android apps to validate the presence and severity of IID issues,and then shed light on these issues’characteristics to support research on effective issue *** the findings of this study,we propose a static IID issue detection tool TAPIR and evaluate it with 243 real-world Android ***,49 and 64 previously-unknown IID issues in two different versions of 16 apps reported by TAPIR are manually confirmed as true positives,respectively,and 16 previously-unknown IID issues reported by TAPIR have been confirmed by developers and 13 have been ***,we further evaluate the performance impact of these detected IID issues and the performance improvement if they are *** results demonstrate that the IID issues detected by TAPIR indeed cause significant performance degradation,which further show the effectiveness and efficiency of TAPIR.

关键词： Android application(app) inefficient image displaying(IID) performance empirical study static analysis

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：