 |
    |
MILA – Multilevel Immune Learning Algorithm
Dipankar Dasgupta, Senhua Yu, and Nivedita Sumi Majumdar
Computer Science Division,
University of Memphis,
Memphis, TN 38152, USA
{dasgupta,senhuayu,nmajumdr}@memphis.edu
Abstract. The biological immune system is an intricate network of specialized tissues, organs, cells, and chemical molecules. T-cell-dependent humoral immune response is one of the complex immunological events, involving interaction of B cells with antigens (Ag) and their proliferation, differentiation and subsequent secretion of antibodies (Ab). Inspired by these immunological principles, we proposed a Multilevel Immune Learning Algorithm (MILA) for novel pattern recognition. It incorporates multiple detection schema, clonal expansion and dynamic detector generation mechanisms in a single framework. Different test problems are studied and experimented with MILA for performance evaluation. Preliminary results show that MILA is flexible and efficient in detecting anomalies and novelties in data patterns.
LNCS 2723, p. 183 ff.
lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2003