Seminar on Computational Learning and Adaptation

Negative Selection Algorithm for Anomaly Detection

Dipankar Dasgupta
University of Memphis, Tennessee
Visiting Scholar, NASA Ames Research Center

The biological immune system is a complex adaptive system which efficiently employs several mechanisms for defense against foreign pathogens. Self-nonself (or danger) discrimination is one of the important tasks the immune system performs during the process of pathogenic recognition and responses. This discrimination is achieved in part by T-cells, which have receptors on their surface that can detect foreign proteins (antigens). During the generation of T cells, receptors are made by a pseudo-random genetic rearrangement process. Then they undergo a censoring process, called negative selection, in the thymus where T cells that react against self-proteins are destroyed; so only those that do not bind to self-proteins are allowed to leave the thymus. These matured T cells then circulate throughout the body and work as distributed novel pattern recognizer. The talk will present an immunity-based negative selection algorithm (and discuss negative detector generation techniques), and its application in anomaly and fault detection.

Return to the seminar schedule