Optimization of Self Set and Detector Generation base on Real-value Negative selection Algorithm
The Artificial Immune System (AIS) community has been vibrant and active for a number of years now. Artificial Immune Systems (AIS) are a type of intelligent algorithm inspired by the principles and rocesses of the human immune system. Aplications of AIS have been studied in various fields. In the application of anomaly detection, negative selection algorithms of AIS have been successfully applied. Real-valued Negative selection algorithms generate their detector sets based on the points of self data. This paper mainly focuses on self set existing problems and solutions, definite the detector radius according to self radius, and propose negative selection algorithm which is decided by detector radius according to self radius, this way of improved RNS may avoid the detector boundary cross problem. Experiments show that the effect of self region optimized is prominent, and performances of detectors is highly efficient.
network security artificial immune system anomaly detection Real-value Negative selection
Xin Yue Fengbin Zhang Liang Xi Dawei Wang
Computer Science & Technology College, Harbin University of Science and Technology, Harbin, China Co Computer Science & Technology College, Harbin University of Science and Technology, Harbin, China
国际会议
成都
英文
12-15
2010-06-12（万方平台首次上网日期，不代表论文的发表时间）