Applied Mechanics and Materials Vols. 411-414

Abstract: The complexity of map scenes of computer games has important influence to the degree of games difficulty, and it is also the key factor of pathfinding performance. In this paper, a kind of maps complexity metric index which based on the accumulation of xor is defined. The index calculates map complexity through accumulating the xor-value of each adjacent cells line by line. The experimental results demonstrates that the metric index is highly relative with the efficiency of A* and HPA* algorithm. It can provide reference for the design of game maps.

Abstract: This paper defined the full connect map and contact surface, and proposed a new map complexity measure, and compared with measurement methods based on Hamming distance and relative Hamming distance. We further research on the relationship between the complexity measure and the map connectivity. The complexity measures based on Hamming distance and contact surface are applicable to full connectivity map, and the new measurement can reflects the difficulty of the pathfinding algorithm more accurately, especially in a higher complexity.

Abstract: The parallel programming approaches were in the focus of research efforts due to an expected increase in efficiency of iterative processing in the parallel computational environment. On this end the parallel evolutionary asymmetric subset-hood product fuzzy-neural inference system has been developed to take advantage of parallelization in message passing. This paper study the structure of the neural network and the time series forecasting with neural network, the results could help us to obtain the optimal solutions to higher complexity of the problem.

Abstract: in this paper, we analyzed three dimensional evaluation index systems on coordinated development of ethnic regions in China. The analysis was conducted by means of an AHP-based Fuzzy Approach which builds a system analysis technique for multiple criteria decision making,and by Biological carrying capacity, Economic carrying capacity and Social carrying capacity.The result show that evaluation index system based on Fuzzy AHP Algorithm in ethnic regions has good reliability.

Abstract: In this article, we present a new negative selection algorithm which the self-data is organized as a R-Tree structure. And the negative selection process could be transformed into the data query process in the self-R-Tree, if a new detector is indexed in any leaf node it will be dropped. As the time complexity of data query process in the tree is in the log level, the negative selection process of our algorithm is superior to the linearly comparation procedure in the traditional negative selection algorithms.

Abstract: The traveling salesman problem is analyzed with genetic algorithms. The best route map and tendency of optimal grade of 500 cities before the first mutation, best route map after 15 times of mutation and tendency of optimal grade of the final mutation are displayed with algorithm animation. The optimal grade is about 0.0455266 for the best route map before the first mutation, but is raised to about 0.058241 for the 15 times of mutation. It shows that through the improvements of algorithms and coding methods, the efficiency to solve the traveling problem can be raised with genetic algorithms.

Abstract: In this paper, we discuss the cooperation behaviors of intelligent virtual agents with autonomous and cooperative ability .Based on the theory of fluent calculus, we have designed an agent reasoning model .In this model, intelligent virtual agent could automatically judge the next action in the action queue and constructs the dynamic environment quickly with limited information from sensor. Furthermore, a type of request/server cooperation function has been designed for the cooperation among virtual agents to solve the conflicts and to realize the joint goals. Experiment results obtained demonstrated that intelligent virtual agents could cooperate well by our reasoning model.

Abstract: In this paper, the model base and objects to be identified are classed as information granules by the information granulation idea. A proper system of polar coordinates is established. The fuzzy pattern recognition problem is studied by the L-series of formation in the abstract analytic number theory. A method is given to evaluate the model base type of the information granules, which consist of massive data. Additionally,it is used to analyze the relation between process parameters and weld appearance in the welding process.

Abstract: In power supply enterprises, providing intelligent service for the residential users is a very crucial approach to increase the customer satisfaction. Taking the demand of residential users as the center, analyze the basic design goal of the intelligence service system and the functions of four subsystems. This paper apply the SOA design idea in building the frame structure of the intelligent service system in power supply enterprises, and the content of every layer in this frame structure is introduced. Then the safe electricity utilization expert system, which belongs to a newly built service, is given an explanation on. Through this intelligent service system, it is convenient for the power supply enterprises to provide users with accurate, efficient, on-demand, proactive and security intelligence services. The application of SOA design idea can make more efficient use of the existing resources and also can make the system have good extensibility, to lay a foundation for the future development of intelligence service in the power supply enterprises.

Abstract: The number of fuzzy rules directly determines the complexity and efficiency of Fuzzy Neural Network (FNN). The Iterative Pruning (IP) algorithm belongs to the Pruning Method, and it spends much time computing adjusting factors of the remaining weights. So the Improved Iterative Pruning (IIP) algorithm is put forward, which adopts dividing blocks strategy and uses the Generalized Inverse Matrix (GIM) algorithm to replace the Conjugate Gradient Precondition Normal Equation (CGPCNE) algorithm for updating the remaining weights. The IIP algorithm is applied in the rule-reasoning layer of FNN to simplify its rules and structure in a great extent and preserve a good level of accuracy and generalization ability without retraining after pruning. The simulation results demonstrate the effectiveness and the feasibility of the algorithm.