A Regional-Memory-Pattern Artificial Idiotypic Network and its Application in Multi-spectral Remote Sensing Image Classification

Based on idiotypic immune network theory, a Regional-memory-pattern Artificial Idiotypic NetworkiquestRAINiquestwas proposed to classify multi-spectral remote sensing image. The immune memory antibodies of RAIN model were divided into two regions: specific memory antibody and free memory antibody. Specific memory antibody had several specific subregions sensitive to specific antigens, while free memory antibody region supplied kinds of specific memory antibodies for the former region. The adjustment and optimization of RAIN were realized according to antibody metdynamics. The initialization and training of RAIN were realized in the primary immune response process, and information extraction was executed in the second immune response process. At last, RAIN was used for the classification of ETM data. Overall accuracy and Kappa coefficient of our method are 92.6% and 0.91 respectivelyiquestwhile that of traditional Parallelepiped, Maximum Likelihood and Minimum Distance were 81.8%, 82.2%, 71.8%, and 0.78, 0.78, 0.65. The results show that RAIN is superior to three traditional classification algorithms.