Rough set theory is emerging as a new tool for dealing with fuzzy and uncertain data. In recent years, it has been successfully applied in such fields as machine learning, data mining, knowledge acquiring, etc. In thi...
详细信息
More researchers recognize that it is an emergent and important issue that intelligent tutoring mechanism can be depicted, evaluated and measured on the uniform theoretical foundation which should be a highly formaliz...
详细信息
Digital Human is a booming research area andits combination with distance education will greatlypromote the advances of medicine, anatomy andother relevant disciplines, ht this paper they areintegrated to establish a...
详细信息
ISBN:
(纸本)0780379411
Digital Human is a booming research area andits combination with distance education will greatlypromote the advances of medicine, anatomy andother relevant disciplines, ht this paper they areintegrated to establish a local-network baseddistance education experimental system whichcontains functions such as teaching, practicing,tutoring and discussing, etc. The volume of thedigital human datasets is too huge to be dealt withtraditional centralized storing methods, so the gridtechnology is introduced to provide an efficient, safeand transparent management of the mass *** this experiment our solution is proved tobe valid and feasible.
Perceptual learning happens at the perceptual level. We combine holism and reductionism to research perception learning. Based on information geometry the paper presents a neural field model which is used to understan...
详细信息
ISBN:
(纸本)0769521908
Perceptual learning happens at the perceptual level. We combine holism and reductionism to research perception learning. Based on information geometry the paper presents a neural field model which is used to understand the transformation mechanism, dynamical behavior, capability and limitation of neural network models, by the study of globally topological and geometrical structure on parameter spaces of neural networks. We discuss neural field representation, fractal learning principle, topology approximation correction learning and the dualistic correction learning algorithm. Finally the paper gives conclusions and points out future research topics.
Agent-oriented programming is an important technology for autonomic computing and grid computing. Advances in agent technology depend on improving frameworks for building and supporting agent societies. Experience sug...
详细信息
ISBN:
(纸本)0769521908
Agent-oriented programming is an important technology for autonomic computing and grid computing. Advances in agent technology depend on improving frameworks for building and supporting agent societies. Experience suggests that first generation multiagent systems focus only on some aspects and fall short of providing a rapid prototyping development environment for the systematic analysis, design, construction and deployment of agent-oriented applications. This paper presents MAGE, an agent-oriented programming environment, with complete tools to support agent-oriented requirement analysis, design, development and deployment. It also gives some comparison between MAGE and other multiagent platforms with particular focus on methodology. At last, this paper gives some applications on MAGE.
Management of various complex resources is an important issue to be well done, in order to fulfill the potential of Grid. In this paper, we propose a formal data model and algebra for resource sharing in the Grid. In ...
详细信息
Machine vision is an active branch of Artificial Intelligence. An important problem in this area is the balance among efficiency, accuracy and huge computing. The visual system of human can keep watchfulness to the pe...
详细信息
Machine vision is an active branch of Artificial Intelligence. An important problem in this area is the balance among efficiency, accuracy and huge computing. The visual system of human can keep watchfulness to the perimeter of visual field while at same time their central attention is focused to the center of visual field for fine information processing. This mechanism of computing resource assignment could ease the demand for huge and complex hardware structure. Therefore designing computer model based on biological visual
Gait is a biometric feature and identification of people from gait captured on video that has become a challenging problem in computer vision. A recognition method based on amplitude spectrum (Fourier spectrum) of fre...
详细信息
ISBN:
(纸本)0769521223
Gait is a biometric feature and identification of people from gait captured on video that has become a challenging problem in computer vision. A recognition method based on amplitude spectrum (Fourier spectrum) of frequency domain is proposed. Fourier spectrum reflects the frequency feature of person's pose in the current frame. After getting the period and key poses through the whole sequence according to the height of centroid and the amplitude value in frequency domain, we extract 5D features from the sequence including four amplitude values corresponding to four key poses image and the proportion of body. Finally, three measures are applied to evaluate our algorithm. Experiments result on USF dataset show that our method is insensitive to many changes condition of background, lighting, clothing, walking speed, segment noise and so on. For we implement gait recognition according to the discriminant analysis, the result to some extent is robust to the variation of viewpoint and cloth and recognition rate is satisfying.
An algebraic multi-class classification method AHSC, i.e., algebraic hyper surface classification, is proposed. The separating algebraic hyper surface of two-class data may be directly constructed by a single polynomi...
详细信息
ISBN:
(纸本)0780384032
An algebraic multi-class classification method AHSC, i.e., algebraic hyper surface classification, is proposed. The separating algebraic hyper surface of two-class data may be directly constructed by a single polynomial in theory, but it is too difficult to separate multi-class data by a single polynomial even though the polynomial is multivalued. AHSC can be used for classifying multi-class data by integrating a series of polynomial networks based on binary numbers, which are used for labeling the classes of samples. The problem that multi-class data cannot always be separated by a single polynomial is solved by AHSC. Moreover, using an adaptive method can choose the order of polynomial. The experimental results show that the new method can efficiently and accurately classify multi-class and high dimension data.
intelligent agent technology has been raised as the primary technology in the intelligent Internet and mobile computing. In this paper, MAGE (multi-agent environment) is introduced which is an environment for rapidly ...
详细信息
ISBN:
(纸本)0769520332
intelligent agent technology has been raised as the primary technology in the intelligent Internet and mobile computing. In this paper, MAGE (multi-agent environment) is introduced which is an environment for rapidly developing distributed, heterogeneous multi-agent systems. Agent model, agent architecture, MAGE platforms, comparison between MAGE and other multi-agent framework is presented in the paper. This paper illustrates two application systems, such as e-business, parallel Web spider. The MAGE is written in Java and is a powerful tool to construct multi-agent systems for Internet applications.
暂无评论