Applied Mechanics and Materials Vol. 610

Abstract: Gradually similar method is putted forward in the paper. The rules of selecting the independents are analyzed. And the foundations of that the variable has been permitted to enter to or eliminate from the model are described. The idea is to forecast medium and long term load of shanxi Province with using this method, and reasonable to select the economic indicators having influence on the power load. Then, these economic indicators were screened by the gradually similar method. Gradually similar method new putted forward is used for the optimization selection of the model input variables, and forecasting accuracy is discussed .Simulation results show that the method brought forward is right and feasible.

Abstract: This paper presented a novel method for detection of organic pollutions based on artificial neural networks combining domain transform techniques. Domain transform techniques are mathematical methods that allow the direct mapping of information from one domain to another. The most effectively used domain transform technique is wavelet packet transform (WPT). Wavelet packet representations of signals provided a local timefrequency description and separation ability between information and noise. The quality of the noise removal can be further improved by using best-basis algorithm and thresholding operation. Artificial neural network (ANN) is a form of artificial intelligence that mathematically simulates biological nervous system. Generalized regression neural network (GRNN) is a kind of ANN and is applied for overcoming the convergence problem met in back propagation training and facilitating nonlinear calculation. In the case a method named WPT-based generalized regression neural network (WPTGRNN) was used for analyzing overlapping spectra.

Abstract: In this paper, we propose novel sub-band spectral centroid weighted wavelet packet cepstral coefficients (W-WPCC) for noise-robust speech emotion recognition. Experimental results show that the W-WPCC feature demonstrates better noise-robustness in noisy environments.

Abstract: Parameter measurement of the solid state nuclear track occupies an extremely important position in the field of nuclear technology while limitation of the traditional manual counting method is very large. In recent years, DSP and image processing techniques are increasingly applied in the field of nuclear technology. This paper describes an automatic counting system for nuclear track based on DSP image processing platform which uses DSP hardware platform and mathematical morphology algorithm. This system can effectively separate the track point from the background and remove noise, and also accurately count helping to reduce the visual error of manual counting.

Abstract: In this paper, a novel algorithm for mining maximal frequent itemsets is presented, which has a pre-processing phase where a digraph is constructed. The digraph represents the frequent 2-itemsets which play an important role on the performance of data mining. Then the search for maximal frequent itemsets is done in the digraph. Experiments show that the proposed algorithm is efficient for all types of data.

Abstract: The type inspection of surface mounted devices (SMD) components is an important part of the numerical control (NC) placement machine’s vision system. In order to improve the detection speed, accuracy rate and versatility, a detection method based on moment features and neural network is proposed. Firstly, component images are preprocessed in order to eliminate the influence of non-uniform illumination and simplify the calculation, so component lead images can be obtained, and then seven invariant moments and a zero-order Zernike moment of the lead images are extracted. Next, the moment features are corrected and normalized. Finally, back propagation (BP) neural network based on the Levenberg-Marquardt algorithm is taken as a classifier for training and testing the 8-dimensional mixed moment feature vectors, 0 and 1 are used to represent the degree of belonging of each image. The experimental results show that this method doesn’t need complex lighting system and has good versatility, and the correct rate can be up to 100%.

Abstract: MCL is a graph clustering algorithm. With the characteristics of the MCL computational process, MCL is prone to producing small clustering and separating edge nodes from the group. A hybrid clustering based on MCL combined with KNN algorithm is proposed. Hybrid algorithm improves the quality of clustering by reclassification of elements in small clustering by using KNN classification characteristics and Clustering tables required by MCL clustering. Experiment proves the improved algorithm can enhance the quality of clustering.

Abstract: A face recognition method on mobile terminals based on manifold learning was proposed. Firstly, the modified Snake model was set in order to improve the accuracy and effectiveness of facial feature point labeling. Then, the partial mapping method was carried out to map the face images to a subspace for further analysis. Finally, the nearest neighbor classifier was enhanced to show the recognition results. The experimental results indicate that the performance of this method is excellent. It is boasts a higher accuracy rate and bigger robustness than the ordinary methods.

Abstract: Deductive synthesis is a method of software development where an algorithm is derived from a formal problem specification which guarantees the reliability of final product. The paper introduces a program synthesis method PAR most of whose synthesis steps are mechanical and some of them can be done interactively by human-computer interaction, and formally synthesizes a dependable algorithm for a selection problem supported by PAR method and PAR platform. Program synthesis based on PAR covers a number of classical algorithm design tactics, develops algorithmic programs together with their proof of correctness, and makes the algorithm more reliable and solving idea more understandable.

Abstract: Identification of vulnerable groups in water resource conflicts is to improve the identification of vulnerable groups in the allocation of water rights and water markets water rights system. There are two difficulties: one is how to determine the weight of evaluation indexes; another is how to effectively deal with the subjectivity of the evaluation process and the low resolution. Therefore, this paper proposes “Information Entropy Based Fuzzy Pattern Recognition Model for Identification of Vulnerable Groups in Water Resource Conflicts (EFPQ-VRWC)” according to the fuzzy pattern recognition based on the combination of the maximum entropy principle and genetic algorithms. And identifying vulnerable groups of Daling River Basin in Liaoning Province, it illustrates the method of application value. And evaluation results have continuity, comparability and versatility so that can accurately reflect the level of vulnerable groups in water resource conflicts.