Research On Adaptive Model Of Neighborhood Immune Detector

Artificial immune system is one of the important branches of artificial intelligence technology.As an intelligent method inspired by the biological immune system and imitating its immune function,it is widely used in many fields such as anomaly detection,data mining,and machine learning.Anomaly detection detects abnormalities by establishing pattern contours of normal behavior and is widely used in various fields.In the field of network security,the self-tolerance generation detector distinguishes self-non-self to detect system security threats,In the field of network security,it uses the self-tolerance generation detector to distinguish self-non-self to detect system security threats.It has shown good problem-handling ability and robustness,and has made great progress.Immunity-based anomaly detection technology Become a research hotspot in this field.The detector is its core knowledge set,and its generation,optimization,and detection operations determine the application effect of artificial immunity.At present,the shape space of artificial immunity is mainly real-valued shape space,but there is a "black hole" problem in real-valued non-self space.Since the matching strategy in real-valued space is based on the Euclidean distance and Manhattan distance between samples,the increase in the number of detector attributes brings the problem of "dimensional disaster".At the same time,the increase of the spatial dimension will cause the time complexity and space complexity of the detector to increase,which will cause the detector to generate slowly.These issues make the artificial immune detection less effective.In view of this,this paper uses neighborhood shape space and improves the neighborhood negative selection algorithm(NNSA).It introduces chaos theory and genetic algorithm when generating candidate detectors,and proposes a multi-source-inspired neighborhood negative selection algorithm(MSNNSA).Based on this,a method for generating and detecting a multi-source-inspired immune detector in a neighborhood shape space is proposed to improve the structure and generation mechanism of the detector in a neighborhood shape space to make it more targeted.In order to make the obtained detector have better distribution,the adaptive mechanism is introduced to optimize the performance of the detector model,improve its generation efficiency and overall detection performance,and solve the problems existing in the real-valued shape space above.The experimental results show that the method in this paper provides an effective solution to improve the generation efficiency of the detector,and the performance and stability of the detection.It is significant for the practical application of anomaly detection.