Bing Xiang Liu

Ceramic Microstructure Image Segmentation by Mean Shift

In order to effectively assist the researchers conduct quantitative analysis of ceramic microstructures, a segmentation algorithm based on mean shift is used for the ceramic microstructure image. Since the collection and transfer process of microscopic image will inevitably be subject to uneven distribution of light, electronic noise and other interference factors which make the image quality deterioration, it is necessary to reduce noises and enhance edges for ceramic microscopic image processing at first. Therefore, the median filter is used to remove the noises in the ceramic microstructure images. Then the component with similar feature is separated and merged by the mean shift segmentation algorithm. Experiments show the proposed algorithm of using median filter and mean shift clustering gives satisfactory results.

A Ceramic Crack Test Method Based on the Maximum Variance Ratio of Inter-Class and Intra-Class

This paper presents a method for inter-class ceramic crack detection threshold than the maximum variance within the class-based segmentation. Ceramics crack detection methods are mainly obtained by ceramic image data, image pre-processing, image segmentation, feature extraction and object recognition constitutes five links. Experimental results show that the method can be detected quickly and accurately detect whether the standard ceramic.

A Recognition Method of License Plate Number Based on BP Neural Network

According to the current technological deficiency of license plate recognition, this paper uses digital graphic processing technique and BP Neural Network algorithm fusion to achieve automatic recognition of license plate. Input the image settled in the previous period in the trained BP neural network to obtain the final license plate character through simulation. The validity and feasibility of the algorithm can be verified through the simulation experiment of standard license plate image.

Research and Implementation of General Online Examination System

At present most of the test systems are limited to a certain subject or specialty, with its universality being ignored. This thesis analyzes on the function and business process of examination system, and designs five system functional modules including test base management, online exam and automatic grading. Also, it shows the realization of key modules, and finally achieved a General online exam system.

RMB Exchange Rate Forecasting Model Based on Exponential Smoothing and Gray Correlation

This paper through the establishment of a Holts linear trend exponential smoothing model, make use of SPSS Clementine for 2005-2010 analysis and forecast of RMB against the U.S. dollar exchange rate, the predicted curve is better than the expectations of the prediction accuracy. To further analyze the dynamic changes of the RMB against the U.S. dollar, method of gray correlation factors that affect the exchange rate is used

Marketing Model Investigation of Cable Television Service Based on BP Neural Network and Decision Tree

This paper takes more than four hundred records of some cable television system for example, makes data mining according to users data record, uses BP neural network and decision tree method respectively to have model building and finds the best model fits for users to order press service. The results of the experiment validate the methods feasibility and validity.

Forecasting Model Based on Improved Grey-Markov

It is great significance to forecast the water quality of Poyang Lake in the construction of Poyang Lake Ecological Economic Zone.On the condition of limited historical data,for resolving the prediction,by combining the advantages of both grey prediction and Markov theory,an improved grey-Markov model is established.First the sequence is moved average,and then unbiased grey-Markov prediction is established to imitate the development tendency of the forecast system.Divide system state into five parts by Markov chain in order to inprove the prediction accuracy. By analying an example,comparing the predicted values and real measured values,The results show that the model has a certain accuracy and reliability

Water Quality Model Parameters Estimation Based on Particle Swarm Optimization Algorithm

Water quality parameter is the basic data of the river water quality mathematical model for forecasting river water quality status. In this paper, the parameter estimation problem of the analytical model, which is used to describe one-dimensional tracing test data of river streams with tracers instantaneously injected, is converted to the function optimization problem. And particle swarm optimization algorithm is applied to solve this problem. The experimental results show that the particle swarm optimization algorithm can estimate the water quality model parameter values regardless of whether the randomly sampling data has noise.

Application of Improved Genetic Algorithm in Determination of Parameters of S-P Water Quality Model

Determination of parameters is an important work for establishing the water quality model to perform the mathematical simulation. In this paper, the improved genetic algorithm is applied in evaluation of the parameters of S-P water quality model. This method has overcome the shortages of parameters estimation as before. The computed results have indicated this method with a very high precision and easy realized by the computer.

Forecasting Model Based on SAGA and LS-SVM for the Water Quality of Poyang Lake

According to the nonlinearity and uncertainty of the water quality data samples, a forecasting model based on Simulated Annealing Genetic Algorithm(SAGA)and least squares support vector machines(LS-SVM) is proposed. Through adaptively optimizing the model parameters of LS-SVM by SAGA, we can apply the model to forecast water quality of Poyang Lake. The experimental results indicate that compared to the typical LS-SVM,the model is very practical and with higher precision.