Title :
A Dendritic Cell Algorithm for real-time anomaly detection
Author :
Yuan, Song ; Chen, Qi-juan
Author_Institution :
Coll. of Power & Mech. Eng., Wuhan Univ. Wuhan, Wuhan, China
Abstract :
The analysis process of the classical Dendritic Cell Algorithm (DCA) is performed offline, which has constrained its application in the area of anomaly detection. In order to continuously detect abnormal behaviors as soon as they occur, a real-time analysis algorithm is proposed, when an antigen has been presented by sufficient dendritic cells, it will be immediately output and assessed, thus the purpose of real-time or near-to real-time analysis can be achieved. Sufficient assessments will reduce the influence of the errors, and the antigen and signal pool of temporal correlation will eliminate the mutual interference of the antigens and signals, which are far apart. The results of the experiments show that the realtime analysis algorithm proposed has the considerable detection accuracy.
Keywords :
artificial immune systems; security of data; DCA; analysis process; antigen; classical dendritic cell algorithm; continuous abnormal behavior detection; detection accuracy; mutual interference; real-time analysis algorithm; real-time anomaly detection; temporal correlation; Accuracy; Algorithm design and analysis; Context; Educational institutions; Green products; Immune system; Real time systems; anomaly detection; artificial immune; danger theory; dendritic cell algorithm; real-time analysis;
Conference_Titel :
Computer Science and Automation Engineering (CSAE), 2012 IEEE International Conference on
Conference_Location :
Zhangjiajie
Print_ISBN :
978-1-4673-0088-9
DOI :
10.1109/CSAE.2012.6272635