检索结果-南通市图书馆

维普期刊数据库博看期刊

Reachable Set Estimation and Safety Verification of Nonlinear Systems via Iterative Sums of Squares Programming

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2022年第3期35卷 1154-1172页

作者： LIN Wang YANG Zhengfeng ding zuohua School of Information Science and Technology Zhejiang Sci-Tech UniversityHangzhou 310018China Shanghai Key Laboratory of Trustworthy Computing East China Normal UniversityShanghai 200062China

In this paper,the problems of forward reachable set estimation and safety verification of uncertain nonlinear systems with polynomial dynamics are ***,an iterative sums of squares(SOS)programming approach is developed for reachable set *** characterizes the over-approximations of the forward reachable sets by sub-level sets of time-varying Lyapunovlike functions that satisfy an invariance condition,and formulates the problem of searching for the Lyapunov-like functions as a bilinear SOS program,which can be solved via an iterative *** make the over-approximation tight,the proposed approach seeks to minimize the volume of the overapproximation set with a desired ***,the reachable set estimation approach is extended for safety verification,via explicitly encoding the safety constraint such that the Lyapunov-like functions guarantee both reaching and *** efficiency of the presented method is illustrated by some numerical examples.

关键词： Computer mathematics reachable set estimation safety verification sums of squares programming

Path Planning for Intelligent Robots Based on Deep Q-learning With Experience Replay and Heuristic Knowledge

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2020年第4期7卷 1179-1189页

作者： Lan Jiang Hongyun Huang zuohua ding the Laboratory of Intelligent Computing and Software Engineering Zhejiang Sci-Tech UniversityHangzhou 310018China the Center of Multi-Media Big Data of Library Zhejiang Sci-Tech UniversityHangzhou 310018China

Path planning and obstacle avoidance are two challenging problems in the study of intelligent robots. In this paper, we develop a new method to alleviate these problems based on deep Q-learning with experience replay and heuristic knowledge. In this method, a neural network has been used to resolve the "curse of dimensionality" issue of the Q-table in reinforcement learning. When a robot is walking in an unknown environment, it collects experience data which is used for training a neural network;such a process is called experience *** knowledge helps the robot avoid blind exploration and provides more effective data for training the neural network. The simulation results show that in comparison with the existing methods, our method can converge to an optimal action strategy with less time and can explore a path in an unknown environment with fewer steps and larger average reward.

关键词： Deep Q-learning(DQL) experience replay(ER) heuristic knowledge(HK) path planning

Hybrid MARTE statecharts

在线全文

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2013年第1期7卷 95-108页

作者： Jing LIU Ziwei LIU Jifeng HE Freederic MALLET zuohua ding Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai 200062 China INRIA Sophia Antipolis M6diterran6e Sophia Antipolis 06902 France Center of Math Computing and Software Engineering Zhejiang Sci-Tech University Hangzhou 310018 China

The specification of modeling and analysis of real-time and embedded systems （MARTE） is an extension of the unified modeling language （UML） in the domain of real-time and embedded systems. Even though MARTE time model offers a support to describe both discrete and dense clocks, the biggest effort has been put so far on the specifi- cation and analysis of discrete MARTE models. To address hybrid real-time and embedded systems, we propose to ex- tend statecharts using both MARTE and the theory of hybrid automata. We call this extension hybrid MARTE statecharts. It provides an improvement over the hybrid automata in that： the logical time variables and the chronometric time vari- ables are unified. The formal syntax and semantics of hybrid MARTE statecharts are given based on labeled transition sys- tems and live transition systems. As a case study, we model the behavior of a train control system with hybrid MARTE statecharts to demonstrate the benefit.

关键词： UML MARTE hybrid automata hybrid MARTE statechart train control system

Petri net based test case generation for evolved specification

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2016年第8期59卷 67-91页

作者： zuohua ding Mingyue JIANG Haibo CHEN Zhi JIN Mengchu ZHOU School of Information Science Zhejiang Sci-Tech University Software Engineering Institute Peking University Department of Electrical and Computer Engineering New Jersey Institute of Technology

Model-based testing can use a model to test a concrete program’s implementation. When the model is changed due to the evolution of the specification, it is important to maintain the test suites up to date, such that it can be used for regression testing. A complete regeneration of the whole test suite from the new model,although inefficient, is still frequently used in practice. To address this problem effectively, we propose a test case reusability analysis technique to identify reusable test cases of the original test suite based on graph analysis,such that we can generate new test cases to cover only the change-related parts of the new model. The Market Information System(MIS) is employed to demonstrate the feasibility and effectiveness of the proposed *** experimental results show that the use of our method saves about 31.5% test case generation cost.

关键词： test case generation regression testing evolved specification Petri net reachability graph

A software-defined MAPE-K architecture for unmanned systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2023年第5期66卷 286-288页

作者： Mingyue JIANG Libin ZHENG zuohua ding Zhi JIN School of Information Science and Technology Zhejiang Sci-Tech University Key Laboratory of High Confidence of Software Technologies (MoE) Peking University

Dear editor,With the advances in software, sensors, and communication technologies, there is rapid development in unmanned systems. An unmanned system consists of unmanned vehicles,a control system and a communication system among its components. These kinds of systems, due to their specific autonomy and high mobility, ofer a wide range of applications and have been used as important tools in various domains.

关键词：

AADL+: a simulation-based methodology for cyber-physical systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2019年第3期13卷 516-538页

作者： Jing LIU Tengfei LI zuohua ding Yuqing QIAN Haiying SUN Jifeng HE Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai 200062 China Zhejiang Sci-Tech University Xiasha College Park Hangzhou 310018 China

AADL (architecture analysis and design language) concentrates on the modeling and analysis of application system *** is quite popular for its simple syntax,powerful functionality and extensibility and has been widely applied in embedded systems for its ***,it is not enough for AADL to model cyber-physical systems (CPS) mainly because it cannot be used to model the continuous dynamic *** paper proposes an approach to construct a new sublanguage of AADL called AADL+,to facilitate the modeling of not only the discrete and continuous behavior of CPS,but also interaction between cyber components and physical *** syntax and semantics of the sublanguage are provided to describe the behaviors of the ***'s more,we develop a plug-in to OSATE (open-source AADL tool environment) for the modeling of *** the plug-in supports syntax checking and simulation of the system model through linking with ***,the AADL+ annex is successfully applied to model a lunar rover control system.

关键词： AADL cyber-physical systems (CPS) simulation OSATE lunar rover control system

Automated GUI widgets classification

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2023年第1期17卷 233-235页

作者： Kabir Sulaiman SAID Liming NIE Yuanchang LIN Yaowen ZHENG zuohua ding School of Computer Science and Technology Zhejiang Sci-Tech UniversityHangzhou 310018China School of Computer Science and Engineering Nanyang Technological UniversitySingap

1 Introduction Graphical User Interface(GUI)widgets classification entails classifying widgets into their appropriate domain-specific types(e.g.,CheckBox and EditText)[1,2].The widgets classification is essential as it supports several software engineering tasks,such as GUI design and testing[1,3].The ability to obtain better widget classification performance has become one of the keys to the success of these *** in recent years have proposed many techniques for improving widget classification performance[1,2,4].For example,Moran et al.[1]proposed a deep learning technique to classify GUI widgets into their domain-specific *** authors used the deep learning algorithm,a Convolutional Neural Network(CNN)architecture,to classify the GUI *** et al.[2]proposed combining text-based and non-text-based models to improve the overall performance of GUI widget detection while classifying the widgets with the ResNet50 model.

关键词： GUI User classify

在线全文

学校读者我要写书评

暂无评论

基于增强动态稠密轨迹特征的布料材质识别

计算机辅助设计与图形学学报 2020年第6期32卷 930-942页

作者：夏海浜缪永伟张佳婧丁佐华浙江理工大学信息学院杭州310018

为了克服基于视频的布料材质识别中由于忽略了动态因素的影响导致材质识别准确率低的难点,利用布料仿真视频库,提出一种基于增强动态稠密轨迹特征的布料材质识别方法以有效识别布料的材质属性信息.首先利用材质合成方法构造64种不同材... 详细信息

为了克服基于视频的布料材质识别中由于忽略了动态因素的影响导致材质识别准确率低的难点,利用布料仿真视频库,提出一种基于增强动态稠密轨迹特征的布料材质识别方法以有效识别布料的材质属性信息.首先利用材质合成方法构造64种不同材质的布料仿真视频数据库;然后利用构造的布料动态视频库,通过迁移预训练的VGG网络增强布料动态视频的各帧特征信息,并消除部分非动态特征;其次利用动态稠密轨迹特征描述布料视频的动态特征,以充分捕捉不同布料材质视频的动态信息;最后通过Fisher向量编码生成布料动态信息的特征数据库,并训练SVM分类器建立布料材质视频动态信息到材质属性参数的映射.利用构建的布料仿真视频库作为数据集进行实验的结果表明,该方法对64种不同布料材质视频的材质种类识别准确率达到73.83%.

关键词：布料材质识别仿真视频库迁移学习动态稠密轨迹布料动态特征

在线全文

学校读者我要写书评

暂无评论

基于迁移学习与支持向量机的服装舒适度评估

纺织学报 2020年第6期41卷 125-131页

作者：夏海浜黄鸿云丁佐华浙江理工大学信息学院浙江杭州310018

针对传统服装舒适度评估需要直接试穿服装导致的舒适度评估精确度不高和评估过程耗时的问题,提出一种从试穿服装数据库学习服装舒适度评估模型的方法,可以快速准确地评估服装舒适度。首先,采集试衣模特尺寸和试穿样板图,并利用迁移学习... 详细信息

针对传统服装舒适度评估需要直接试穿服装导致的舒适度评估精确度不高和评估过程耗时的问题,提出一种从试穿服装数据库学习服装舒适度评估模型的方法,可以快速准确地评估服装舒适度。首先,采集试衣模特尺寸和试穿样板图,并利用迁移学习改善试穿样板图构建试穿服装数据库,同时提出基于虚拟试衣技术的舒适度标签获取方法,为数据库中对应的试穿样板图添加舒适度标签;然后,提取试穿样板图的局部二值模式为服装样板特征,并融合试衣模特尺寸数据形成服装试穿特征向量;最后,提取试穿服装数据库的融合特征训练支持向量机,得到服装舒适度评估模型。实验结果表明,该方法的准确率和系统时间分别为0.8344和12 s,具有较高的精确度和效率。

关键词：服装舒适度评估迁移学习虚拟试衣特征融合支持向量机