Abstract
Infinite impulse response (IIR) system identification problem is defined as an IIR filter modeling to represent an unknown system. During a modeling task, unknown system parameters are estimated by metaheuristic algorithms through the IIR filter. This work deals with the self-adaptive search-equation-based artificial bee colony (SSEABC) algorithm that is adapted to optimal IIR filter design. SSEABC algorithm is a recent and improved variant of artificial bee colony (ABC) algorithm in which appropriate search equation is determined with a self-adaptive strategy. Moreover, the success of the SSEABC algorithm enhanced with a competitive local search selection strategy was proved on benchmark functions in our previous studies. The SSEABC algorithm is utilized in filter modelings which have different cases. In order to demonstrate the performance of the SSEABC algorithm on IIR filter design, we have also used canonical ABC, modified ABC (MABC), best neighbor-guided ABC, and an ABC with an adaptive population size (APABC) algorithms as well as other algorithms in the literature for comparison. The obtained results and the analysis on performance evolution of compared algorithms on several filter design cases indicate that SSEABC outperforms all considered ABC variants and other algorithms in the literature.
Highlights
Finite impulse response (FIR) and infinitive impulse response (IIR) filters, which are the most important types of linear digital filters, are widely used in fields such as signal processing, communication, and parameter estimation [1]
In order to assess the performance of the search-equation-based artificial bee colony (SSEABC) on adaptive IIR filter design, three benchmark systems extensively used in many studies are selected [13, 17,18,19,20, 34]
For SSEABC, artificial bee colony (ABC) [21], modified ABC (MABC) [35], NABC [36], and APABC [37], the results are obtained with 100 independent runs with 7500 function evaluations (FEs) for each sample
Summary
Finite impulse response (FIR) and infinitive impulse response (IIR) filters, which are the most important types of linear digital filters, are widely used in fields such as signal processing, communication, and parameter estimation [1]. Similar works have been done with metaheuristics such as cuckoo search algorithm, differential evolution (DE), and craziness-based PSO where adaptive IIR filter designs have been realized to determine the optimal parameters of an unknown system [18,19,20]. The self-adaptive search-equation-based artificial bee colony (SSEABC) algorithm was designed for this purpose and achieved successful results in several types of benchmark continuous optimization functions [28, 29]. The transfer function of the unknown system is monitored by the transfer function of the filter to determine the most appropriate filter coefficients This process turns into an optimization problem by minimizing output errors generated by applying the same input signal to both the unknown system and the filter. L n=1 n=1 where L is the total number of input samples, y(n) and y(n) are outputs of IIR filter and unknown systems for sample input n , respectively
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
