An application of immune algorithm in FIR filter design

Frequency sampling is one of the usual methods in FIR digital filter design. In frequency sampling method the value of transition band samples, which are usually obtained by searching for table, must be determined in order to make the attenuation within the stopband maximal. However, the value obtained by searching for table can not be ensured to be optimal. Immune algorithm (IA) based on antigen-antibody reaction of immune system in biology can lead to global optimal solutions to complex problems. In this paper an application of IA to frequency sampling method is introduced. The detail processes of realizing IA and experimental results of FIR filter design examples are presented. Experimental results have illustrated that the value of transition band samples obtained by IA can be ensured to be optimal and the performance of the filter is improved. A comparison is made between IA and genetic algorithm (GA), which shows the convergent speed of IA is faster than that of GA.