IIR filter design using incremental artificial bee colony with powell´s CDS

This paper proposes incremental artificial bee colony with local search (IABCLS) to digital infinite impulse response (IIR) filter design for parameter identification. Unknown filter parameters are considered as a vector to be optimized. The basic version of ABC and three variants of ABC algorithms are also applied to filter design for comparison. The computational experiments show that the proposed method is more accurate to estimate the filter parameters than other methods, and reduces the mean squared errors. IABCLS can be efficiently used to digital IIR filter design.