Shubhendu Kumar Sarangi

Design of 1-D and 2-D recursive filters using crossover bacterial foraging and Cuckoo search techniques

Recently, there has been an increasing interest on the application of the evolutionary algorithms in order to solve the drawbacks of traditional filter design methods. Unlike classical methods, they offer the advantage of not requiring a good initial estimate of filter parameters to proceed. This paper presents design of one-dimensional (1-D) and two-dimensional (2-D) recursive filters using crossover bacterial foraging (COBFO) and Cuckoo Search (CS) techniques. Design of 1-D and 2-D recursive filters is considered here as a constrained optimization problem to ensure stability. The solution is obtained through convergence of a biased random search using crossover bacterial foraging optimization technique to ensure quality. A faster solution is also obtained through the convergence of a meta heuristic search technique called the Cuckoo search technique. Inbuilt constraint handling capability makes our proposal attractive in the design of recursive filters. Results are compared with genetic algorithm (GA) and bacteria foraging optimization (BFO) techniques.

Swarm intelligence based techniques for digital filter design

Two novel modifications to QPSO proposed.Time dependency of constriction factor taken care.Improved methods for IIR filter design proposed and validated. This paper deals with the problem of digital IIR filter design. Two novel modifications are proposed to Particle Swarm Optimization and validated through novel application for design of IIR filter. First modification is based on quantum mechanics and proved to yield a better performance. The second modification is to take care of time dependency character of the constriction factor. Extensive simulation results validate the superior performance of proposed algorithms.

Adaptive Channel Equalization Using Decision Directed and Dispersion Minimizing Equalizers Trained by Variable Step Size Firefly Algorithm

This paper signifies to present a design methodology for equalization of nonlinear channels for weights adaptation. Adaptive algorithms such as PSO, FFA, and VSFFA-based channel equalizer aimed to minimize inter-symbol interference associated with broadcast channel. In this paper, we implemented various channel equalizers such as decision directed equalizer, dispersion minimizing equalizer using PSO, FFA, and VSFFA which are principally derivative-free optimization tools. These algorithms are appropriately used to update weights of equalizers. Accomplishment of proposed diverse channel equalizers are evaluated in terms of mean square error (MSE) and BER plots and assessments are made using evolutionary algorithms applied to equalizers. It is observed that proposed equalizer-based adaptive algorithms, mostly VSFFA trained equalizers, offer improved performance so far as accurateness of reception is taken into account.

A new modified firefly algorithm for function optimization

This paper intends to provide a modified firefly algorithm based on firefly algorithm and improved particle swarm optimization. This firefly algorithm is a category of nature-enthused algorithm of swarm intelligence, i.e. depends on the response of a firefly to the light of other fireflies and also perform well on various numerical optimization problems. The modified algorithm uses the improved velocity concept of particle swarm optimization to enhance the searching behavior of standard algorithm. A comparison of the firefly algorithm with that of modified firefly algorithm is performed for some standard benchmark functions through simulations. The algorithms are also checked in various standard dimensions for providing effective output. The simulated results prove the superiority of modified firefly algorithm as compared to the traditional firefly algorithm in standard benchmark functions and in all dimensions. The results give an idea that the proposed modified algorithm enriches performance of the standard firefly algorithm and converges more quickly with less time to produce optimum solution.

Functional Link Artificial Neural Network-Based Equalizer Trained by Variable Step Size Firefly Algorithm for Channel Equalization

In this work, FLANN structure is presented which can be utilized to construct nonlinear channel equalizer. This network has a modest structure in which nonlinearity is instigated by the functional expansion of input pattern by trigonometric and Chebyshev polynomials. This work also defines evolutionary approaches coined as firefly algorithm (FFA) along with modified variable step size firefly algorithm for resolving channel equalization complixeties using artificial neural network. This paper recapitulates techniques with simulated results acquired for given channel with certain noise conditions and justify the efficacy of proposed FLANN-based channel equalizer using VSFFA over FFA and PSO in terms of MSE curves and BER plots.

Design of optimal high pass and band stop FIR filters using adaptive Cuckoo search algorithm

Abstract This paper presents an efficient design of digital FIR high pass and band stop filters using an adaptive cuckoo search algorithm (ACSA). The important features of ACSA are — (i) the step size is independent and (ii) it is accurately decided from the current fitness value. The step size is decided according to the current fitness value within the iteration process. This increases the convergence speed. The other five global optimizers are also used for optimization. The optimal solutions obtained by the ACSA are compared with the other global optimizers. CEC 2005 benchmark test functions are considered for the comparison. The results are compared in terms of the convergence speed, accuracy, deviation from the desired response, minimum stop-band attenuation and maximum pass-band attenuation. The statistical analysis, i.e. t -Test is performed to claim the superiority of the proposed approach. The simulation results presented in this paper reveal the fact that the performance of the ACSA is better than the other algorithms.

A MLP equalizer trained by variable step size firefly algorithm for channel equalization

The paper intends to present a recent methodology for equalization of nonlinear channels employing Multilayer Perceptron Neural Networks. A hardback methodology regarding instructing the neural network using computational techniques is reported. The presented method used a modified firefly algorithm i.e. variable step size firefly for better equalization. The simulated results validate the superiority of variable step size firefly as compared to the traditional firefly and Particle swarm optimization. The outcomes give an idea that the proposed modified algorithm enriches performance of the proposed equalization process as compared to other two mentioned algorithms and it converges faster with less error to produce optimum solution.

System identification by Crazy-cat swarm optimization

Adaptive filtering and system identification by traditional derivative based algorithms create stability issues when used in infinite impulse response (IIR) systems. In this paper, the identification of IIR system is used as an optimization task. A modification is approached to cat swarm optimization by introducing the concept of craziness to produce Crazy cat swarm optimization(Crazy-CSO) algorithm. The new modified version of the algorithm has been utilized to find a better solution. The efficiency of the modified algorithm is verified by identification of few standard IIR systems through simulation study. The new method exhibits finer identification performance as compared to particle swarm optimization (PSO) and cat swarm optimization (CSO) based identification by providing superior outputs.

Biomedical Image Registration Using Genetic Algorithm

This paper focuses on the state-of-the-art technology which is useful for medical diagnosis and proper treatment planning. Using this scheme, different data formats such as MRI (magnetic resonance image), CT (computed tomography), PET (positron emission tomography), and SPECT (specialized positron emission tomography) of the same patient can be registered. These medical images provide complementary information which is conflicting occasionally due to nonalignment problem. However, the registered image provides more information for medical personals. In the registration process, images are aligned with each other and the size of the object is made equal. So in this process, the nonaligned image is transformed with respect to the reference image. Here, we have registered the biomedical images by maximizing the mutual information. Genetic algorithm (GA) is used to optimize rotation, scaling and translation parameters. Results presented reveal the suitability of the proposed method for biomedical image registration.

Design of Linear Phase FIR High Pass Filter Using PSO with Gaussian Mutation

In this paper, a new optimization technique i.e. particle swarm optimization with Gaussian mutation (PSOGM) is used for the design of digital FIR High Pass filter and this technique is used to optimize filter coefficients. PSO with GM, the much improved version of particle swarm optimization algorithm (PSO), is a population based global search algorithm which finds near optimal solution in terms of a set of filter coefficients. Effectiveness of this algorithm is justified with a comparative study with real coded genetic algorithm (GA) and particle swarm optimization algorithm.