检索结果-南通市图书馆

Fusion tracking in color and infrared images using joint sparse representation

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) 2012年第3期55卷 590-599页

作者： LIU HuaPing1,2.3 & SUN FuChun1,2.3 1department of computer {2. and technology, tsinghua University, beijing 100084, china 2.7} key laboratory of intelligent technology and {12.s, beijing 100084, china 3tsinghua National laboratory for Information {2. and technology, beijing 100084, china 1. department of computer science and technology Tsinghua University Beijing 100084 China2. State Key Laboratory of Intelligent Technology and Systems Beijing 100084 China3. Tsinghua National Laboratory for Information Science and Technology Beijing 100084 China

Currently sparse signal reconstruction gains considerable interest and is applied in many fields. In this paper, a similarity induced by joint sparse representation is designed to construct the likelihood function of particle filter tracker so that the color visual spectrum and thermal spectrum images can be fused for object tracking. The proposed fusion scheme performs joint sparse representation calculation on both modalities and the resultant tracking results are fused using min operation on the sparse representation coefficients. In addition, a co-learning approach is proposed to update the reference templates of both modality and enhance the tracking robustness. The proposed fusion scheme outperforms state-of-the-art approaches, and its effectiveness is verified using OTCBVS database.

关键词： joint sparse representation fusion tracking color image infrared image

A stochastic policy search model for matching behavior

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) 2011年第7期54卷 1430-1443页

作者： CHENG ZhenBo 1,2.ZHANG Yu 1 & DENG ZhiDong 1 1 state key {2. on intelligent technology and systems,tsinghua National {2. for Information science and technology,department of computer science,tsinghua University,beijing 100084,china 2.17},Zhejiang University of technology,Hangzhou 310014,china 1. state key {2. on intelligent technology and systems Tsinghua National Laboratory for Information Science and Technology Department of Computer Science Tsinghua University Beijing 100084 China2. Department of Computer Science and Technology Zhejiang University of Technology Hangzhou 310014 China

The matching law is one of the basic empirical laws in decision theory,and it states that a subject’s preference to optional targets depends on which choices are *** this paper,we study the possible mechanisms that explain why subjects’ decisions often obey this *** the basis of reinforcement learning theory,we put forward a decision-making model in which the policy is updated by a policy parameter,and the model might be implemented in the brain through the prefrontal cortex and the basal ganglia neural *** on this model,an algorithm that satisfies the matching law is derived under some simple *** analysis and simulation results show that the decision behavior achieved by the algorithm obeys the matching *** addition,the matching behaviors in two classical experiments are reproduced using the *** results provide a reasonable strategy for the matching law and a useful computational tool for rewarded decision-making tasks.

关键词： policy model matching law reinforcement learning decision-making model

Fuzzy tolerance quotient spaces and fuzzy subsets

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) 2010年第4期53卷 704-714页

作者： ZHANG Ling1 & ZHANG Bo2,3,4* 1computer science & technology College, Anhui University, Anhui 230039, china 2state key laboratory of intelligent technology and systems, beijing 100084, china 3tsinghua National laboratory of Information science & technology, beijing 100084, china 4Information science & technology College, computer science & technology department, tsinghua University, beijing 100084, china 1. computer science & {2. College Anhui University Anhui 230039 China2. State Key Laboratory of Intelligent Technology and Systems Beijing 100084 China3. Tsinghua National Laboratory of Information Science & Technology Beijing 100084 China4. Information Science & Technology College Computer Science & Technology Department Tsinghua University Beijing 100084 China

The structure and characteristic of fuzzy subsets are discussed by using the concepts of granulation and hierarchy in quotient space theory. First, the equivalence relation based quotient space theory is extended to the fuzzy tolerance relation. Second, the isomorphism and its discriminant of fuzzy tolerance relations are discussed. Finally, by using the fuzzy tolerance relation to define the fuzzy subset, its properties are addressed. The main results are given below: (1) several equivalent statements of fuzzy tolerance relations; (2. the definition of isomorphism of fuzzy tolerance relations; (3) the isomorphic discriminant of fuzzy tolerance relations; (4) the definition and properties of fuzzy subsets based on the fuzzy tolerance relations; and (5) the necessary and sufficient condition of the isomorphism of fuzzy subsets. These results will help us further comprehend the concepts of fuzzy tolerance relations and fuzzy subsets.

关键词： Fuzzy tolerance relation quotient space isomorphism fuzzy subset

The structural analysis of fuzzy measures

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) 2011年第1期54卷 38-50页

作者： ZHANG Ling1,ZHANG Bo2.& ZHANG YanPing1 1 computer science College,Anhui University,Hefei 2.0039,{2. 2.3} key Lab of intelligent technology & systems tsinghua National Lab for Information science & technology Information science & technology College,computer science & technology,tsinghua University,beijing 100084,{2. 1. computer science College Anhui University Hefei 230039 China2. State Key Lab of Intelligent Technology & Systems tsinghua National Lab for Information science & {2. Information science & technology College Computer Science & Technology Tsinghua University Beijing 100084 China

From quotient space based granular computing theory we explore the fuzzy measures of fuzzy sets. Based on the structural analysis of fuzzy sets,we present an"isotropism"*** this assumption we achieved the following insights:(1)the uniqueness of a fuzzy measure being isotropic on a finite complete semi-ordered set;(2.the necessary and suffcient condition of the isomorphism for fuzzy measure functions in fuzzy mathematics;(3)the necessary and suffcient condition that fuzzy measures have fuzzy and granular monotonicity;(4)under a certain assumption,the analytic expression for fuzzy *** results clarify the relationship between fuzzy measures and granular computing,reveal the essence of fuzzy measures,and provide a simple way of constructing fuzzy measures.

关键词： quotient space fuzzy set fuzzy measure rough set structural analysis

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

调度问题的建模方法

清华大学学报（自然科学版） 1997年第3期37卷 24-27页

作者： Wang Jiaxin department of computer science and technology, tsinghua University {2. key laboratory of intelligent technology & system, beijing 100084 清华大学计算机科学与技术系智能技术与系统国家重点实验室

生产调度问题有广泛的应用前景，有明显的经济效益与社会效益。但是生产调度问题的研究大多只考虑求解方法，很少涉及建模方法。建模方法主要依靠专家的经验和技巧。本文提供了调度问题的数学描述，这是把调度问题定义为一类约束满足问... 详细信息

生产调度问题有广泛的应用前景，有明显的经济效益与社会效益。但是生产调度问题的研究大多只考虑求解方法，很少涉及建模方法。建模方法主要依靠专家的经验和技巧。本文提供了调度问题的数学描述，这是把调度问题定义为一类约束满足问题。然后以皇后问题为例研究了调度问题的建模方法。由此实例给出了模型的测度，并给出基于约束的建模方法。这种基于约束的建模方法对于建模问题的理论化，形式化，是积极的探索。这可以指导调度问题的数学模型的建立。

关键词：生产调度八皇后问题建模方法调度问题排序

维普期刊数据库

Optimal MAC based cooperative spectrum sensing in cognitive radio networks

在线全文

学校读者我要写书评

暂无评论

science china(Information sciences) 2012年第6期55卷 1388-1396页

作者： CHEN Zhong 1,ZHANG XianDa 1 & YANG LanJuan 2.1 state key {2. of intelligent technology and systems,tsinghua National {2. for Information science and technology,department of Automation,tsinghua University,{12. 100084,china 2.Institute of Command Automation,PLA University of science and technology,Nanjing 2.0007,china 1. state key {2. of intelligent technology and systems Tsinghua National Laboratory for Information Science and Technology Department of Automation Tsinghua University Beijing 100084 China2. Institute of Command Automation PLA University of Science and Technology Nanjing 210007 China

This paper considers a cognitive radio (CR) system in non-ideal fading wireless channels and pro-poses cooperative spectrum sensing schemes based on coherent multiple access channels (MAC),serving as an alternative way to improve the cooperative spectrum sensing performance and provide space diversity for spec-trum *** statistics are transmitted using a common channel from the secondary users (SUs) to a fusion center (FC) where the global decision is *** optimal scaling factors of the proposed schemes are obtained by maximizing the detection probability under a target false alarm probability and a transmit power *** the proposed optimal MAC scheme has high computational complexity,a sub-optimal solu-tion based on maximization of the deflection coefficient (DC) is also *** results show that the proposed algorithms can significantly improve the spectrum sensing performance and approach the detection baseline.

关键词： cognitive radio (CR) spectrum sensing multiple access channel (MAC) deflection coefficient optimization

On the placement of actuators and sensors for flexible structures with closely spaced modes

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(Technological sciences) 2010年第7期53卷 1973-1982页

作者： LIU XiaoXiang1,2.& HU Jun1,2.1 beijing Institute of Control Engineering, beijing 100190,{2. 2.state key laboratory of science and technology on Space intelligent Control, beijing 100190,{2. 1. beijing Institute of Control Engineering Beijing 100190 China2. State Key Laboratory of Science and Technology on Space Intelligent Control Beijing 100190 China

This paper analyzed the fundamental limitations of previous work and developed a new method to optimally locate actuators and sensors for structures with close modes. Optimization criteria were defined based on the distinguishing modal controllability and observability measures of close modes. An appropriate genetic algorism was adopted as the optimization algorism. Solving the high order Lyapunov functions was avoided by means of the closed-form expressions for controllability and observability Grammians. Since structure with widely separated natural frequencies is approximately balanced, computational efficiency was improved by grouping close modes together and dealing with the resulting subsystems independently. Finally, the effectiveness and optimality of the novel placement scheme were verified on a model structure with close modes.

关键词： close modes controllability/observability sensor/actuator optimization criterion optimization algorithm

维普期刊数据库

Competent predicate abstraction in model checking

在线全文

学校读者我要写书评

暂无评论

science china(Information sciences) 2011年第2期54卷 258-267页

作者： LI Li1,2.3, SONG XiaoYu4, GU Ming2.3 & LUO XiangYu2.3 1department of computer {2. & technology, tsinghua University, beijing 100084, china 2.7} laboratory for Information system Security, Ministry of Education of china, beijing 100084, china 3School of Software, tsinghua University, beijing 100084, china 4department of ECE, Portland state University, Portland, Oregon 972.7, USA 1. department of computer {2. & technology Tsinghua University Beijing 100084 China2. Key Laboratory for Information System Security Ministry of Education of China Beijing 100084 China3. School of Software Tsinghua University Beijing 100084 China4. Department of ECE Portland State University Portland Oregon 97207 USA

The paper presents a new approach to computing the abstract state and a maximum weight heuristic method for finding the shortest counter-example in verification of imperative programs. The strategy is incorporated in a verification system based on the counterexample-guided abstraction refinement method. The proposed method slashes both the size of the abstract state space and the number of invokes of a decision procedure. A number of benchmarks are employed to evaluate the effectiveness of the approach.

关键词： program model checking predicate abstraction weight heuristic

Fuzzy dynamic characteristic model based attitude control of hypersonic vehicle in gliding phase

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) 2011年第3期54卷 448-459页

作者： LUO Xiong 1,2.& LI Jiang 1 1 department of computer science and technology, key {2. of Advanced Control of Iron and Steel Process (Ministry of Education), University of science and technology beijing, beijing 100083, china 2.National {2. of Space intelligent Control, beijing 100190, china 1. department of computer science and technology Key Laboratory of Advanced Control of Iron and Steel Process (Ministry of Education) University of Science and Technology Beijing Beijing 100083 China2. National Laboratory of Space Intelligent Control Beijing 100190 China

The intelligent autonomous control of hypersonic vehicles has aroused great interest from the field of spacecraft. To solve the problem of longitudinal attitude control of hypersonic vehicle in gliding phase, a new intelligent controller is proposed in this paper. This new controller is based on the fuzzy dynamic characteristic modeling method. The fuzzy logic is introduced into the characteristic modeling by dividing the whole restriction range into several subspaces. Simulations show that this modification greatly improves the performance of the original method. With the same whole restriction range the fuzzy dynamic characteristic modeling decreases the time of convergence, and at the same time makes the attitude angle tracing more precise and robust. Since the sub-model is a characteristic model that has stronger adaptiveness than a fixed local model, the number of fuzzy rules is greatly reduced. Our model sharply reduces the complexity in constructing a fuzzy dynamic model. Finally, simulation results are given to show the effectiveness of the proposed approach in dealing with the attitude control problem of hypersonic vehicle in gliding phase.

关键词： hypersonic vehicle gliding attitude control fuzzy dynamic characteristic modeling