Advanced Materials Research Vols. 532-533

Abstract: The Extend Kalman Filter (EKF) is widely used in the tracking of high dynamic Doppler shift trajectories, but it has some flows when it is used to estimate the state of nonlinear systems. In this paper, we apply the Unscented Transformation (UT) based Unscented Kalman Filter (UKF) to the state estimation in the high dynamic Doppler environments. Two versions of the UKF estimators, augmented UKF estimator and nonaugemented UKF estimator are designed. To compare the performance of them, they are applied to tracking a common high dynamic trajectory, and simulation results declare that given different conditions, the performance of the estimators will be different.

Abstract: Now mature and effective algorithms for the numerical solution of inverse problem of line source are few, so the researching of algorithms for the problem is urgent and necessary. Firstly, a brief introduction to the characteristics of solving the inverse problem of the line source is given, and the mathematical solution model of inverse problem is established based on the Line source equation, Secondly a new algorithm (Range Particle algorithm) based on range searching algorithm is proposed for the numerical solving the inverse problem of the line source particle and the basic implementation steps and parameter adjustment of the algorithm also be discussed. Finally, simulated and measured data were used to test the effect of the algorithm. The results show that the range particle algorithm is an algorithm of high precision, fast convergence and computational stability for the solving the inverse problem of the line source and it do can be applied in Engineering.

Abstract: To make feature subset which can gain the higher classification accuracy rate, the method based on genetic algorithms and the feature selection of support vector machine is proposed. Firstly, the ReliefF algorithm provides a priori information to GA, the parameters of the support vector machine mixed into the genetic encoding,and then using genetic algorithm finds the optimal feature subset and support vector machines parameter combination. Finally, experimental results show that the proposed algorithm can gain the higher classification accuracy rate based on the smaller feature subset.

Abstract: A design method of reliability-based structural optimization has a powerful advantage because some random variables can be considered. However, the sensitivity analysis of reliability with respect to random variables is very complicated and its computational cost is very expensive. Thus, a response surface method is adopted for approximating the limit state function to improve computational efficiency. An iterative strategy is used to determine a response surface that is able to fit the limit state function in the neighborhood of the design point. A sequential response surface method is performed to satisfy the demand of accuracy in the process of reliability-based structural optimization. A numerical example is presented to demonstrate the computational efficiency of the proposed method.

Abstract: Support Vector Machine is widely used in data classification, but in the case of more training samples, the training time is longer. To solve this problem, use the ISODATA clustering algorithm to cluster samples to obtain the new cluster center, together with high similarity to the error for the sample to form a new cluster of training samples, training support vector machines. So that a solution of high similarity to repeat the training samples of similar problems, while focusing on the easily lead to wrong classification of the training samples. The support vector machine classification accuracy can be improved, and also reduces the training time, to make it more convenient for engineering application.

Abstract: According to the idea of genetic algorithm, a new image encryption algorithm is proposed. Define each pixel of the image as a gene, each row of the image as a chromosome, the whole image as an organism. Then we design a selection operator, which based on SVD. After the operation of selection, crossover and mutation of the image, we can get the encrypted image. The simulation results show that very nice encryption effects and good robustness are obtained and the high safety of the new algorithm are analyzed.

Abstract: As the daughter of modern wireless communication technology & computer network technology, Wireless Local Area Network(WLAN) is being used widely in many areas. It is well known that WLAN has the advantages such as simple network configuration, high transmission rate, good extensibility and mobility, and convenience to carry, etc. However, its security mechanism is not perfect to guarantee its security because of some design flaws in safety precautions. The application of AES in WLAN improves its data confidentiality. The work presented in this paper focuses on present AES encryption algorithm security problem and optimization of its S Box. The improved algorithm this paper put forward in WLAN, is proved to be efficient.

Abstract: Automated negotiation based on co-evolutionary algorithms is an emerging research field in recent years. This paper introduced the basic ideas of evolutionary and co-evolutionary algorithms, and discussed the main theories and approaches in the research of automated negotiation based on co-evolutionary algorithms. The five key elements in simulation of negotiation experiments are also presented in detail. Finally, the future work and research directions are pointed out.

Abstract: It is a significant process to automatically extract ellipses or elliptic image features in highly precise vision detection, especially to achieve rapid as well as accurate detection in complex environment. Fortunately, this paper provides an approach to solve the problem. We firstly detect the edge of images by using sub-pixel edge detection algorithm, and then determine the elliptical shapes, and eliminate the non-ellipses. For the complicated context and taking into account the occlusion of ellipses, we integrate the robust Hough transforms and slip window into randomized algorithm based on least square approach with the purpose of having got the veracious ellipse parameters, which proves that the approach is available for images in stability and accuracy.

Abstract: The paper mainly studies the algorithm of image segmentation. We divide an image into several areas using the method of combining segmentation algorithm based on edge with segmentation algorithm based on region, for the later use of image analysis and image understanding.