Applied Mechanics and Materials Vols. 462-463

Abstract: As for diesel engine fault diagnosis, it is more difficult to select the appropriate feature. In the paper, using the main parts state such as cylinder, piston and piston ring to diagnosis the fault of diesel engine. Eigenvalue is vital to the precision and efficiency fault diagnosis, the normal method to find the fault diagnosis eigenvalue is simulation experiment. Since the number of experiment cannot be too much, bootstrap is introduced in the paper, then using Genetic Algorithm, an optimum parameter combination has been received.

Abstract: The current of single-phase grounding fault in NUGS is very small, so correctly detecting earthing fault line is hard to achieve on the system with insulated neutral point. The existing different grounding fault line selecting methods have some limitations and shortcomings and lack credibility. In order to solve the problem, in the paper comprehensively various methods method of each fault detection in small current grounding system based on information fusion and intelligent process is proposed , and select fault line many times, achieve the desired effect of fault locating. A multi-criteria fault line selecting method is presented by using information fusion and intelligent process is proposed. A fuzzy comprehensive evaluation is given. The simulation results show the proposed method of fuzzy data fusion from multiple line selecting has higher credibility.

Abstract: The demerits and current demand of the traditional decision support system (DSS) for power dispatching are analyzed,and the advantages of incorporating the agent technology and the intelligent decision support system (IDSS) are expatiated in detail. A new intelligent decision system model is put forward consequently and the models framework is also given. An example of the integration of three existed expert systems for power system dispatching management into one MAS is given,and the cooperation activities between the agents are described.

Abstract: Multiple classifier system trains different classifiers and combines their predictions to improve the accuracy of classification. This paper explains the popular algorithms and strategies in multiple classifier system, and points out the key factors to affect the performance of the application of multiple classifier system. The experiments are carried out on given environmental audio data in order to compare the singular classifier methods with multiple classifier system such as Random Forest and MCS, as well as Bagging and AdaBoost. The experimental results show that the multiple classifiers technology outperforms the singular classifier and obtains better performance in environmental audio data classification. It provides an effective way to guarantee the performance and generalization of classification.

Abstract: A novel human hand tracking algorithm based on a single-view camera is put forward. First, we remove the deformity gesture before tracking employing hand physical constraint and motion constraint. Second, we get data from digital glove in the process of hand grasping object, then we obtain the polynomial law of joint motion by analyzing the data to reduce the dimension. Finally, we fuse the behavioral model and optimized particle filter to improve the result of tracking. The innovation of this paper is to establish the behavioral model of grasping object. The experiments show that the proposed algorithm can track movement of hand accurately and quickly.

Abstract: A blind sub-carrier recognition algorithm of TT&C communication is proposed based on Negentropy-maximization in terms of recognition of TT&C signals for military TT&C communication information scout. First, the basic principle of the ICA is discussed in this paper. Using maximum Negentropy approximation of differential Negentropy, an objective function for ICA is introduced and a Fast-ICA algorithm based on maximum Negentropy is presented. Based on analyzing Fast-ICA algorithm deeply, this paper expounds a new method to adopt it in the recognition of TT&C signals of satellite. Simulation results in MATLAB show its better performance and efficiency in the mixed TT&C signals of satellite recognition, proving its good convergence and robust.

Abstract: Retracted paper: Highly-available models and IPv4 have garnered improbable interest from both statisticians and experts in the last several years. Here, we show the emulation of suffix trees. We motivate an algorithm for suffix trees, which we use to demonstrate that e-business and replication can interact to solve this challenge.

Abstract: Multiple data streams clustering aims to clustering multiple data streams according to their similarity while tracking their changes with time . This paper proposes M_SCCStream algorithm based on cloud model. Algorithm introduces data cloud node structure with hierarchical characteristics to represent different granularity data sequence and takes the entropy indicated the degree of data changes. Algorithm finds micro_clustering with the minimum distance and then obtains the clustering result of multiple data streams through calculating the correlation degrees of micro_clustering. The experiment proves that the algorithm has higher quality and stability.

Abstract: For the relative motion between an imaging system and its objects, it results in motion-blurred images in acquiring images. The physical theory of motion-blurred images for moving objects are analyzed in this paper, then the motion-blurred process is researched to establish blurring-model and the essential elements of the process are extracted to form the expressions. The every grey scale value of images pixels is computed and processed to form the motion-blurred images, then based on the contradictorily computing analysis, the restoring model of blurring imaging is established and the restoring expressions are gained. The processing courses of motion-blurred and restoring images are achieved by computing program VC++. The simulation experiments show that the method of images process can be used to make motion-blurred images and restoring images when the objects motion is two dimensions uniform velocity rectilinear motion effectively.

Abstract: Segmentation of brain tissues from magnetic resonance (MR) images plays a crucial role in medical image processing. In this paper, we propose an automatic unsupervised segmentation method integrating wavelet transform with self-organizing map for brain MR image. Firstly, a multi-dimensional feature vector is constructed based on the intensity, the low-frequency subband of wavelet transform and spatial position information. Then, an adaptive growing self-organizing tree map (AGSOTM) is presented, which adaptively captures the complicated spatial layout of the individual tissues, and overcomes the problem of overlapping grey-scale intensities for different tissues. The proposed method is validated by extensive experiments using both simulated and real T1-weighted MR images, and compared with other algorithms.