Entity

Time filter

Source Type


Bin Y.,Zhengzhou Information Technology College | Shichao C.,Zhengzhou Information Technology College
Communications in Computer and Information Science | Year: 2011

The problems of Mutual Information were analyzed when it was used for term extraction. In order to reduce the impact of problems, a method of candidate term filtration and extraction with threshold interval was proposed. And a determination algorithm was given, which can give the best upper and lower thresholds fast and accurately through data sampling, statistics and computing. Compared with the method of mutual information filtration with single threshold, the proposed method filtered and extracted candidate terms by setting two thresholds in the premise of not changing the calculating formula of mutual information. Experimental results show that the proposed method can improve the precise rate and F-measure significantly under the same conditions. © 2011 Springer-Verlag.


Zhang J.,Zhengzhou Information Technology College | Li Y.,Zhengzhou Information Technology College | Cao J.,Zhengzhou Information Technology College
Proceedings - 2011 IEEE International Conference on Computer Science and Automation Engineering, CSAE 2011 | Year: 2011

Due to endless system vulnerability, and uneasy administrators acquiring of Network security situation of customer host, how to automatically discover the vulnerability and frangibility of customer host on the Internet before attackers utilize the vulnerability becomes a crucial question of ensuring a secure Network. In allusion to the algorithms of multiple linear regression forecast model, this paper realizes the forecast of sensor security utilizing the least square to solve the equation of multiple linear regression firstly and t-test to test the significance of regression coefficient. Thus administrators of Network are able to know the whole status of sensor intuitively, and seek the lowest accident rate, the least loss and the best security investment results. © 2011 IEEE.

Discover hidden collaborations