Key Engineering Materials Vols. 460-461

Abstract: This article introduces a new calibration method for machine vision measurement system--calibration method using concentric circles planar template. This method not only considering lens distortion and random errors introduced by the process of calibration, but also overcome limitation of strict demands for the standard parts’ position and complexity in stereovision computation, it also capable of conduct calibration to the whole scene depth space, effectively improve the efficiency of calibration with its simple and high precision mean. A relatively high precision can be achieved by applying this new method to diameter measurement of cable line, which is suitable to conduct on-field industrial dimension measurement calibration.

Abstract: In this paper, a multi-level method has been adopted to optimize the holes machining process with genetic algorithm (GA). Based on the analyzing of the features of the part with multi-holes, the local optimal processing route for the holes with the same processing feature is obtained with GA, then try to obtain the global optimal route with GA by considering the obtained local optimal route and the holes with different features. That is what the multi-level method means. The optimal route means the minimum moving length of the cutting tool and the minimum changing times of the cutting tool. The experiment is carried out to verify the algorithm and the proposed method, and result indicates that with GA and using the multi-level method the optimal holes machining route can be achieved efficiently.

Abstract: This paper has studied the impact of personnel changes within the organs and institutions, proposed a risk cost function and a personnel-change impact function. By establishing a risk cost model which will show the relationship between the changes in personnel and the risk of the changes, what’s more, bring forward an N-order open-stack model which can provide an effective method to research the personnel changes in organs quantitatively, the author finally gave out a unified dual-drive model dealing with the personnel changes in organs and institutions and proved it effective with the Unmanned Aerial Vehicle Group of simulation modeling as well as the necessity to monitor and control the changes in personnel.

Abstract: Word sense disambiguation (WSD) is always an important and difficult problem that requires to be solved in Nature Language Processing. This paper presents a new WSD method which is based on soft pattern matching. The method can learn the soft patterns from the sense of the ambiguous word and its context, to construct a soft pattern - based database. At last the sense of the ambiguous word is labeled by choosing the sense with the maximum matching degree between the ambiguous word context and the soft pattern. The experiment result shows that the method has high precision.

Abstract: This paper studies the traits of Ant Colony Algorithm and BP neural network, at the same time it combines the ant colony optimization algorithm with BP neural network and applies them at the image restoration. This algorithm solves some problems of BP, such that the BP algorithm gets in local minimum easily, the speed of convergence is slowly and sometimes brings oscillation effect etc. that is reason the quality of restored image can be improved significantly. Besides, the article details ACO-BP algorithm’s theory and steps, and apply the improved algorithm in the image restoration. which reduces the MSE(Mean Square Error) of the optimization algorithm, and makes the speed of convergence of BP neural network faster. This algorithm is validated validly by the method of Simulation .

Abstract: Urban traffic networks (UT-Nets) and cellular metabolic networks (C-Nets) have many common functional characteristics and internal mechanisms. Based on the similarity and traffic conservation, we use extreme pathways (EPs) to analysis the state of UT-Nets. Experiments showed the EPs method for cell metabolism also can be used in urban traffic network analysis after defining some indicators.

Abstract: Among the many mining algorithms of association rules, Apriori Algorithm is a classical algorithm that has caused the most discussion; it can effectively carry out the mining association rules. However, based on Apriori Algorithm, most of the traditional algorithms exist "item sets generation bottleneck" problem, and are very time-consuming. An enhanced algorithm associating Apriori with transaction reduction and item reduction technique is put forward by the paper, in the algorithm candidate item sets generation and the support calculation are created after each transaction is compressed and connected, and the key word identifying is adopted in the candidate set, thus the process of pruning and string pattern matching is removed from Apriori algorithm. Original algorithm and improved algorithm implementation steps are presented by examples, the results show that the new algorithm reduces the storage space, improve the efficiency of the algorithm and improve the performance of data mining technology.

Abstract: In the view of the fact that the information of the fault characteristic of the train wheelset is submerged into the background noises and the conventional spectral analysis method has its own deficiency due to the fuzzy spectrum value created by the load variation and rotation speed fluctuation, the paper proposes a method of the characteristic spectrum analysis of the on-line fault diagnosis of the train wheelset. And the correspondent system is developed to meet the practical application. In the paper, the issues such as the signal sampling, signal processing and the inhabitation of the characteristic spectrum leakage besides the principle of the new method. The application indicates the method is reliable and effective since it can describe the fault characteristic more exactly than any other conventional ones.

Abstract: Visible/near-infrared spectroscopy (NIRS) is the millimeter wave ,It is the high speed and non-destructiveness method, high precision and reliable detection data, is a rapid and non-destructiveness method for discrimination varieties of Fragrant mushrooms by means of VIS/NIR spectroscopy was developed in this study. The relationship between the reflectance spectra and Fragrant mushrooms varieties was established. The spectral data was compressed by the wavelet transform (WT). The features from WT can be visualized in principal component (PC) space, appeared to provide a reasonable clustering of the varieties of Fragrant mushrooms. The fivet principal components computed by PCA had been applied as inputs to a back propagation neural network(BP) with one hidden layer. The 220 samples of four varieties were selected randomly to build BP model. This model was used to predict the varieties of 40 unknown samples. The predict recognition rate has achieved 99.5%. This model was reliable and practicable.

Abstract: This paper presents an algorithm to develop neighborhood, and the first time applies it into multi-relational (MR) data. The proposed algorithm is inspired by the idea of Locality Sensitiveness Hashing, whose idea is cell accumulating. The heuristics of parameterization are given, which are customized to MR data. Experiments demonstrate the proposed method behaves better than its peers on both MR data and common data.