Applied Mechanics and Materials Vols. 687-691

Abstract: With the rapid development of information technology, the amount of data accumulated by people is increasing sharply. Data mining technology is an effective method to find useful information from vast amounts of data and increase the utilization of information. After thousands of years of development, traditional Chinese medicine has accumulated a wealth of theoretical knowledge and a lot of books and records, more and more Chinese medicine databases are created. Using data mining technology to mine the unknown knowledge and rules and put forward assumptions for experiment and theory can be a good auxiliary research of traditional Chinese medicine. This article analyzes the data mining methods of traditional Chinese medicine at first. Then, the application of data mining technology in traditional Chinese medicine data analysis is introduced which includes the data mining of traditional Chinese medicine literatures, diagnosis and clinic of traditional Chinese medicine and prescription and medication of traditional Chinese medicine. At last, the aspects which need to be paid attention to in the data mining of traditional Chinese medicine are pointed out.

Abstract: This paper makes an empirical research of the forestry comprehensive development in 31 provinces in China according to the 14 indexes of forestry development. Based on the relevant 14 indexes, it sets up a system which can be used to evaluate the level of forestry comprehensive development in China. This paper also makes a cluster analysis to learn the cluster situation in all regions. Meanwhile, it shows the average of these indexes according to their cluster situation and makes an analysis on the relationship between region and forest based on the average.

Abstract: K-means algorithm is a simple and efficient data mining clustering algorithm. For the current status of the bank card customer relationship management, based on data mining technology, design based on K-means clustering algorithm banking customer classification system. Data mining techniques can extract vast amounts of customer information data bank card implicit knowledge and spatial relationship model will represent the bank customers feature set of data objects automatically classified into each composed of clusters of similar objects, bank card customers in the banking system classification. This paper analyzes the existing spatial clustering methods summary and conclusion, based on the combined data bank card customers, according to the volatility of funds used to different customer groups, the use of K-means analysis to study characteristics of client groups, providing appropriate financial services.

Abstract: Word similarity computing is widely used in many fields, such as question answer,text clustering and so on. This paper synthesizes previous research achievement and proposes an improved word similarity computing method based on Hownet. The improvement is mainly shown in the following aspects: We make a difference between the antonym and common words ,and define the value range of sememe similarity as [-1, 1]; what’s more we not only consider the hyponymy, but the depth and density as we compute the sememe similarity, then makes the result more distinctly; besides we introduce the concepts of weak and supplement sememes, and lower the effect of the weak and supplement sememes by reducing the weight of weak and supplement as we compute the concept similarity. Experiment shows that the improved method makes the word similarity more practically.

Abstract: Information security is a matter of concern in any sector and industry, and the vulnerability is the important factor which caused this issue. Therefore it is necessary to analyze and predict the occurrence of vulnerability. This paper used the datas of CNNVD vulnerability database and Apriori algorithm to analyze and predict the occurrence of software vulnerability. In the data preprocessing stage by changing the level of vulnerability rule we can dig out more concept association. In the evaluation stage of association rules by designing filters we can find the rules in line with the degree of user interest. Finally, this papper could demonstrate the effectiveness of of this method by experiments.

Abstract: In this paper, the homotopy analysis method is used for solving a prey-predator system with holling IV functional response. The approximation solutions were obtained by homotopy analysis method, and contain the auxiliary parameter h which provides us with a convenient way to adjust and control convergence region and rate of solution series. This result showed that this method is valid and feasible for the system.

Abstract: We adopt analog simulation method of Monte Carlo in this paper. Under the circumstance of different prior information, in this paper we also make researches on the value assessment accuracy of the samples’ total parameters of up-and-down and langlie methods, and figure out the application condition and range of these two sensitivity experimental methods.

Abstract: With the rapid development of network information technology, much attention has been paid to the database content security problems,such as how to prevent data theft, illegal copying, certification of copyright, etc. In order to protect the database copyright, digital watermarking technology is becoming a new research hotspot. In this paper, first of all, on the basis of summary current development of data and database watermarking technology, and then introduces genetic algorithm in data watermark technology, finally validates the effectiveness of the model with an example.

Abstract: The grey prediction method is simple in principle, the sample size was small and simple, suitable for load forecasting.But grey model has some limitations, the data dispersion degree is more bigger,the gray is also more bigger, it will reduce the accuracy of prediction.This paper adopts the moving average method to improve the raw data , so as to increase the data weights, while avoiding predicted value excessive volatility .Through a city of China's power load is instantiated to verify, and Then analyze the results, found that after the GM (1,1) model improved by moving average method can effectively improve the accuracy of load forecasting.

Abstract: Based on Web data, the paper regarded data series mining technology as research content, researched and realized sequence GSP algorithm with higher mining efficiency on sequence pattern, tested the algorithm and analyzed mining pattern. Moreover, the paper realized a scheme that used data warehouse (DW) to excavate sequence of Web visit to use entirely, tested the scheme by adopting logs of real business sites, analyzed mining results and drew a conclusion that this algorithm had an excellent application effect.