检索结果-内蒙古大学图书馆

IEEE International Conference on Image Processing

作者： Y. Sun D.L. Page J.K. Paik A. Koschan M.A. Abidi Imaging Robotics and Intelligent Systems Laboratory Department of Electrical and Computer Engineering University of Tennessee Knoxville USA

Triangle meshes are widely used in representing surfaces in computer vision and computer graphics. Although 2D image processing-based edge detection techniques have been popular in many application areas, they are not well developed for surfaces represented by triangle meshes. This paper proposes a robust edge detection algorithm for triangle meshes and its applications to surface segmentation and adaptive surface smoothing. The proposed edge detection technique is based on eigen analysis of the surface normal vector field in a geodesic window. To compute the edge strength of a certain vertex, the neighboring vertices in a specified geodesic distance are involved. Edge information are used further to segment the surfaces with the watershed algorithm and to achieve edge-preserved, adaptive surface smoothing. The proposed algorithm is novel in robustly detecting edges on triangle meshes against noise. The 3D watershed algorithm is an extension from previous work. Experimental results on surfaces reconstructed from multi-view real range images are presented.

关键词： Image edge detection Smoothing methods Application software Image segmentation Surface reconstruction computer vision computer graphics Geophysics computing Noise robustness Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

FUZZY COGNITIVE MAPS MODEL FOR LARGE SCALE COMPLEX systems

引用

IFAC Proceedings Volumes 2002年第1期35卷 277-282页

作者： C.D. Stylios Peter P. Groumpos Laboratory for Automation and Robotics Department of Electrical and Computer Engineering University of Patras Rion 26500 GREECE Tel. +30 61 997293 Fax. +30 61 997309

Most of the technological systems are characterized by complexity, coupled relationships with feedback and a demanding procedure to develop their models. This paper presents the Soft Computing technique of Fuzzy Cognitive Maps that are knowledge-based methodologies suitable to describe and model complex systems and handle with available information from an abstract point of view. Fuzzy cognitive Maps develop behavioral model of the system exploiting the experience and knowledge of experts. Fuzzy Cognitive Maps applicability in modeling complex systems is presented and a general hierarchical structure is proposed to model any complex system. Within the hierarchical structure, Fuzzy Cognitive Map models the coordinator of the system and develops an abstract conceptual model of the complex system.

关键词： Complex systems Fuzzy Cognitive Map Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

ACTIVATION HEBBIAN LEARNING RULE FOR FUZZY COGNITIVE MAPS

引用

IFAC Proceedings Volumes 2002年第1期35卷 319-324页

作者： Elpiniki Papageorgiou Chrysostomos D. Stylios Peter P. Groumpos Laboratory for Automation and Robotics Department of Electrical and Computer Engineering University of Patras Rion 26500 GREECE Tel. +30 61 997293 Fax. +30 61 997309

Fuzzy Cognitive Maps (FCM) is a soft computing, modeling methodology for complex systems, which is originated from the combination of fuzzy logic and neural networks. Many different learning algorithms have been suggested for the training of neural networks. Only some initial thoughts on learning rules have described for FCMs. A learning law is a mathematical algorithm, which can train the FCM by selecting the appropriate weights and it is very important for a system to have learning and adaptive capabilities. In this paper a new learning algorithm, the Activation Hebbian Learning (AHL) has been proposed for FCMs. The learning rule for a FCM is a procedure where FCM weight matrix is modified in order the FCM to model the behavior of a system. Simulation results proving the strength of the learning rule are provided.

关键词： Hebbian learning Fuzzy Cognitive Maps Modeling Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Signal modification for coding purely voiced sections in a wideband ACELP speech coder

Signal modification for coding purely voiced sections in a w...

引用

European Signal Processing Conference (EUSIPCO)

作者： Mikko Tammi Milan Jelinek Tampere University of Technology. Digital and computer Systems Laboratory. Tampere Finland Department of Electrical Engineering University of Sherbrooke Sherbrooke Quebec Canada

In narrowband CELP coding, signal modification is often employed to improve pitch prediction at lowest bit rates. In this paper, we extend signal modification for wideband speech coding. A method for identifying, modifying, and coding purely voiced speech frames in a variable bit rate wideband ACELP coder is presented. Signal modification enables coding of purely voiced frames with a low bit rate mode. Modification is performed frame and pitch synchronously preserving the original time scale at the end of each frame. Since no modification is allowed at the frame end, the delay parameter of pitch prediction is prone to oscillations. These oscillations can be reduced by choosing a proper delay contour for interpolating the parameter over the modified frame We also demonstrate that the signal modification algorithm can be employed for detecting reliably frames suitable for signal modification. Informal listening tests indicate good performance for the proposed method.

关键词： Delays Speech Bit rate Speech coding Interpolation Oscillators

来源：评论

学校读者我要写书评

暂无评论

ON–LINE IMPROVEMENT FOR THE DECENTRALIZED PREDICTIVE CONTROL OF THE HEAT DYNAMICS OF A GREENHOUSE

引用

IFAC Proceedings Volumes 2002年第1期35卷 37-42页

作者： E.J. Kyriannakis K.G. Arvanitis N. Sigrimis National Technical University of Athens Dept. of Electrical and Computer Engineering Intelligent Robotics and Automation Laboratory Zographou 15773 Athens GREECE Agricultural University of Athens Department of Agricultural Engineering Athens 11855 GREECE

A decentralized model-based predictive controller is used for the design of discrete-time control systems aiming at regulating the air temperature and heat supply in greenhouses. Moreover, alternative techniques are proposed for the approximation of the decentralized part of the control and the on-line improvement of the overall control problem. A state space model is used to predict the corresponding local indoor temperature over a long-range time-period and approximate models are used to predict the interactions among the subsystems. The sun radiation and outdoor temperature are treated as external disturbances that affect the overall system dynamics. A series of energy fluxes consist the heating system and the predictive controllers have proved to be powerful in controlling the supply temperature.

关键词： Decentralized control predictive control greenhouse heat dynamics

来源：评论

学校读者我要写书评

暂无评论

Entire region filling in indoor environments using neural networks

Entire region filling in indoor environments using neural ne...

引用

World Congress on Intelligent Control and automation (WCICA)

作者： Chaomin Luo S.X. Yang M. Meng Advanced Robotics and Intelligent Systems (ARIS) Laboratory School of Engineering University of Guelph Guelph Canada Department of Electrical and Computer Engineering University of Alberta Edmonton Canada

Entire region filling is a special type of robot path planning strategy that requires the mobile robot to cover every part of the whole workspace, which has many applications such as cleaning robots, vacuum cleaners, painter robots, land mine detectors, lawn mowers, and window cleaners. In this paper, a novel biologically inspired neural network approach is proposed for entire region filling with obstacle avoidance of a mobile cleaning robot in a nonstationary environment. The dynamics of each neuron in the topologically organized neural network is characterized by a shunting equation or an additive equation derived from Hodgkin and Huxley's (1952) membrane equation. There are only local lateral connections among neurons. Thus the computational complexity linearly depends on the neural network size. The robot path is autonomously generated from the dynamic activity landscape of the neural network and the previous robot location. The proposed model algorithm is computationally efficient. It can deal with an unstructured environment with irregular obstacles. The effectiveness of the proposed model is demonstrated by simulation results.

关键词： Filling Indoor environments Neural networks Mobile robots Equations Cleaning Landmine detection Neurons Computational modeling Path planning

来源：评论

学校读者我要写书评

暂无评论

A new approach to credit assignment in a team of cooperative Q-learning agents

A new approach to credit assignment in a team of cooperative...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： A. Harati M.N. Ahmadabadi Institute for Studies on Theoretical Physics and Mathematics School of Intelligent Systems Tehran Iran Robotics and AI Laboratory Department of Electrical and Computer Engineering University of Tehran Tehran Iran

Q-learning is widely used in many multi agent systems. In most cases, a separate critic is considered for qualifying each individual agent behavior or it is assumed that the critic is completely aware of effects of all agents' actions on the team qualification. But, in many cases, the role of each team member in the group performance is not known. In order to distribute a common credit among the agents, a suitable criterion must be provided to estimate the role of each agent in the team performance and to judge if an agent has done a wrong action. In this paper two such criteria, named certainty and expertness, for a team of agents with parallel tasks are introduced. In addition, two methods for reinforcing the agents based on the proposed measures are provided. Some simulation results are also reported to show the effectiveness of the proposed measures and methods.

关键词： Intelligent agent Learning systems Multiagent systems Intelligent sensors Artificial intelligence Laboratories Intelligent systems Intelligent robots Physics Mathematics

来源：评论

学校读者我要写书评

暂无评论

Cooperative Q-learning with heterogeneity in actions

Cooperative Q-learning with heterogeneity in actions

引用

IEEE International Conference on systems, Man and Cybernetics

作者： S.M. Reza MirFattah M.N. Ahmadabadi Institute for Studies on Theoretical Physics and Mathematics School of Intelligent Systems Tehran Iran Robotics and AI Laboratory Department of Electrical and Computer Engineering University of Tehran Tehran Iran

Cooperation in learning improves the speed of convergence and the quality of learning. Special care is needed when heterogeneous agents cooperate in learning. It is discussed that, cooperation in learning may cause the learning process to diverge if heterogeneity is not handled properly. In this paper, it is assumed that two heterogeneous Q-learning agents cooperate to learn. The heterogeneity is assumed in their action order (and not in their action set). A Q-learning-based method is introduced for the agents to learn the mapping among their actions. It is shown that, the agents are able to learn this mapping while cooperating in learning. Some simulation results are reported to show the effectiveness of the proposed method.

关键词： Intelligent agent Intelligent robots Humans Telecommunication control Artificial intelligence Laboratories Intelligent systems Physics Mathematics Convergence

来源：评论

学校读者我要写书评

暂无评论

An extension of weighted strategy sharing in cooperative Q-learning for specialized agents

An extension of weighted strategy sharing in cooperative Q-l...

引用

International Conference on Neural Information Processing

作者： S.M. Eshgh M.N. Ahmadabadi School of Intelligent Systems Institute of Studies in Theoretical Physics and Mathematics Tehran Iran Control and Intelligent Processing Center of Excellence and Robotics Laboratory Department of Electrical and Computer Engineering University of Tehran Tehran Iran

Using other agents' experiences and knowledge, a learning agent may learn faster, make fewer mistakes, and create some rides for unseen situations. These benefits will be gained if the learning agents know the area of expertise and the expertness values of each other. In this paper, some Q-learning agents with different skills and expertness levels cooperate in learning. The agents use some criteria to judge others information and knowledge. Four expertness criterion, certainty and entropy measures are used to assign degrees of importance to others' Q-Tables. Effects of measuring these values based on their whole Q-Table, a portion of Q-Tables that reflects their proficiencies, and the states in Q-Tables on the learning quality are studied. Simple strategy sharing and two different weighted strategy-sharing methods are used to combine the acquired knowledge from different agents.

关键词： Intelligent robots Intelligent agent Process control Control systems Intelligent control Laboratories Intelligent systems Physics Mathematics Entropy

来源：评论

学校读者我要写书评

暂无评论

Certainty and expertness-based credit assignment for cooperative Q-Learning agents with an AND-type task

Certainty and expertness-based credit assignment for coopera...

引用

International Conference on Neural Information Processing

作者： A. Harati M.N. Ahmadabadi School of Intelligent Systems Institute of Studies in Theoretical Physics and Mathematics Tehran Iran Control and Intelligent Processing Center of Excellence & AI and Robotics Laboratory Department of Electrical and Computer Engineering University of Tehran Tehran Iran

In multiagent reinforcement learning, inter-agent credit assignment is a fundamental problem, since a single scalar reinforcement signal is the only reliable feedback that teams of learning agents receive. This problem is more critical in groups of independent learners with a joint task. In this research, it is assumed that a critic agent receives the environment feedback and assigns a proper credit to each agent using some measures. Three of such measures for a team of cooperative agents with a parallel and AND-type task are introduced. These measures somehow compare the agents' knowledge. One of these criteria, called normal expertness, is a non-relative measure while two other ones (certainty and relative normal expertness) are relative measure. It is experimentally shown that relative measures work better as they contain more information for the critic agent.

关键词： Feedback Intelligent agent Intelligent robots Process control Control systems Intelligent control Artificial intelligence Robot kinematics Physics computing Reliability engineering

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：