Bayesian Networks is a popular tool for representing uncertainty knowledge in artificial intelligence fields. Learning BNs from data is helpful to understand the casual relation between variables. But Learning BNs is ...
Bayesian Networks is a popular tool for representing uncertainty knowledge in artificial intelligence fields. Learning BNs from data is helpful to understand the casual relation between variables. But Learning BNs is a NP hard problem. This paper presents an immune genetic algorithm for learning Markov equivalence classes, which combining dependency analysis and search-scoring approach together. Experiments show that the immune operators can constrain the search space and improve the computational performance.
Hierarchy is a remedy way to reduce the demanding complexity of model-based diagnosis. In this paper, an approach to diagnosis of discrete-event systems in a hierarchical way is proposed, inspired by the concept "...
详细信息
Hierarchy is a remedy way to reduce the demanding complexity of model-based diagnosis. In this paper, an approach to diagnosis of discrete-event systems in a hierarchical way is proposed, inspired by the concept "D-holon" and the concept "Silent Closure" presented in the literatures recently. Each extended silent closure can be seen as a special type of D-holons, called SCL-D-holon. Every hierarchical level is an SCL-D-holon built off line. When on line diagnosing a discrete-event system, only related SCL-D-holons will be called instead of all the SCL-D-holons generally, thus the space complexity is reduced. In comparison to on line creating silent closures, the efficiency is improved as well.
This paper first gives an analysis of data aggregation and data compression based on energy consumption of sensor nodes, after which an approach is proposed to construct an aggregation tree in the case of non-perfect ...
详细信息
This paper first gives an analysis of data aggregation and data compression based on energy consumption of sensor nodes, after which an approach is proposed to construct an aggregation tree in the case of non-perfect aggregation, since GIT considers only the case of perfect aggregation and it does not work well if the aggregation is non-perfect. An assessment scheme that can get the information of hops from the aggregation point to the sink and the hops from the aggregation point to the source node is used to construct such an aggregation tree. Moreover, the energy consumption of the aggregation is also considered. This scheme can be used when perfect aggregation cannot be performed. In this paper, an approach to reduce the cost of reinforcement is also proposed, in which the reinforcement work is done by the source nodes themselves, not by the sink node. Simulation result shows that this approach can save more energy than GIT when the aggregation ratio is small. This result also provides a theoretical limit of aggregation to tell when GIT will lose its superiority and thus gives a direction to choose among the aggregation algorithms. Another result shows that the further the sources are away from the sink, the less reinforcement messages are needed. Finally a guidance to tell when to use the EGA (energy consumption assessment) scheme is given.
Cascading failures often occur in congested networks such as the Internet. A cascading failure can be described as a three-phase process: generation, diffusion, and dissipation of the congestion. In this account, we p...
详细信息
Cascading failures often occur in congested networks such as the Internet. A cascading failure can be described as a three-phase process: generation, diffusion, and dissipation of the congestion. In this account, we present a function that represents the extent of congestion on a given node. This approach is different from existing functions based on betweenness centrality. By introducing the concept of ''delay time'', we designate an intergradation between permanent removal and nouremoval. We also construct an evaluation function of network efficiency, based on congestion, which measures the damage caused by cascading failures. Finally, we investigate the effects of network structure and size, delay time, processing ability and packet generation speed on congestion propagation. Also, we uncover the relationship between the cascade dynamics and some properties of the network such as structure and size.
Proper ontology definition is the prerequisite for efficient knowledge acquisition. For the complex knowledge that could not be described by simple binary relation, we advocated a methodology for aggregated knowledge ...
详细信息
ISBN:
(纸本)9781424430536;9780769531519
Proper ontology definition is the prerequisite for efficient knowledge acquisition. For the complex knowledge that could not be described by simple binary relation, we advocated a methodology for aggregated knowledge acquisition, describing how to define the ontology for such aggregated knowledge concept and how to acquire knowledge basing on such definition. Experiment shows that this methodology is effective in automatic knowledge acquisition from Chinese free text.
An efficient collision detection method based on separating bounding volume (SBV) is proposed. The positions and shapes of SBVs are determined by the optimal separating support hyper planes of two objects. SBVs not on...
详细信息
To obtain the optimal partition of a data set, a hybrid clustering algorithm, PKPSO, based on PSO is proposed. In the proposed PKPSO the PSO algorithm is effectively integrated with the K means algorithm. Among the po...
详细信息
To obtain the optimal partition of a data set, a hybrid clustering algorithm, PKPSO, based on PSO is proposed. In the proposed PKPSO the PSO algorithm is effectively integrated with the K means algorithm. Among the population, selected candidate solutions are further optimized to improve the accuracy by the K-means algorithm. By analyzing the algorithm, the criterions for control parameters selection are determined. Partional clustering result by the proposed PKPSO is compared with that by PSO or by K-means algorithm, and results show that the global convergent property of PKPSO is better than that of the other algorithms. The PKPSO can not only overcome the shortcoming of local minimum trapping of the K-means, but also the solution precision and algorithm stability are better than that of the other two algorithm.
In this paper, a kind of object representation model global structure constraint is presented, in which objects are described as constellations of points satisfied with their intrinsic specific global structure constr...
详细信息
In this paper, a kind of object representation model global structure constraint is presented, in which objects are described as constellations of points satisfied with their intrinsic specific global structure constraints. The spatial relations among all the patches of small color variations are extracted as shape model and the representative color information of patches are encoded and clustered as color model with color cluster information. Then, in the searching phase, mutual information is used as measurement with optimal algorithm to locate target objects in images by finding out the exactly matched position. In the experiment, we tested the approach on a collection of human face images and the results demonstrated the approach is simple, effective and efficient.
A hybrid of graph-based and neural network recognition system is developed. The part information is taken from the B-rep solid date library then broken down into sub-graph. Once the sub-graphs are generated, they are ...
详细信息
A hybrid of graph-based and neural network recognition system is developed. The part information is taken from the B-rep solid date library then broken down into sub-graph. Once the sub-graphs are generated, they are first checked to see whether they match with the predefined feature library. If so, a feature vector is assigned to them. Otherwise, base faces are obtained as heuristic information and used to restore the missing faces and update the sub-graphs. The sub-graphs are transformed into vectors, and these vectors are presented to the neural network, which classifies them into feature classes. The scope of instances variations of predefined feature that can be recognized is very wide. A new BP algorithm based on the enlarging error is also presented.
暂无评论