Blind signals separation with genetic algorithm and particle swarm optimization based on mutual information

Radioelectronics and Communications Systems (Impact Factor: 0.19). 06/2011; 54(6):315-324. DOI: 10.3103/S0735272711060045


Blind source separation technique separates mixed signals blindly without any information on the mixing system. In this paper,
we have used two evolutionary algorithms, genetic algorithm and particle swarm optimization for blind source separation. In
these techniques a novel fitness function that is based on the mutual information and high order statistics is proposed. In
order to evaluate and compare the performance of these methods, we have focused on separation of noisy and noiseless sources.
Simulations results demonstrate that the proposed method for employing fitness function has rapid convergence, simplicity
and a more favorable signal to noise ratio for separation tasks based on particle swarm optimization and continuous genetic
algorithm than binary genetic algorithm. Also, particle swarm optimization enjoys shorter computation time than the other
two algorithms for solving these optimization problems for multiple sources.

19 Reads
  • Source
    • "This algorithm is susceptible to the local minima problem during the learning process and is limited in many practical applications such as BSS that requires a global optimal solution. Also, the neural networks have been proposed which their operation depends on an update formula and activation function that are updated for maximizing the independence between estimated signals [12]. Neural network approaches have the drawback of possibly being trapped into near-optimal solutions in situations where, the search space presents many local minima. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Recently, several techniques have been presented for blind source separation using linear or non-linear mixture models. The problem is to recover the original source signals without knowing apriori information about the mixture model. Accordingly, several statistic and information theory-based objective functions are used in literature to estimate the original signals without providing mixture model. Here, swarm intelligence played a major role to estimate the separating matrix. In our work, we have considered the recent optimization algorithm, called Artificial Bee Colony (ABC) algorithm which is used to generate the separating matrix in an optimal way. Here, Employee and onlooker bee and scout bee phases are used to generate the optimal separating matrix with lesser iterations. Here, new solutions are generated according to the three major considerations such as, 1) all elements of the separating matrix should be changed according to best solution, 2) individual element of the separating matrix should be changed to converge to the best optimal solution, 3) Random solution should be added. These three considerations are implemented in ABC algorithm to improve the performance in Blind Source Separation (BSS). The experimentation has been carried out using the speech signals and the super and sub-Gaussian signal to validate the performance. The proposed technique was compared with Genetic algorithm in signal separation. From the result, it was observed that ABC technique has outperformed existing GA technique by achieving better fitness values and lesser Euclidean distance.
  • [Show abstract] [Hide abstract]
    ABSTRACT: In recent years, much research emerged to modify Stone’s BSS method for solving a blind source separation problem; Stone’s method used to recover original signals from the mixture. In this work, new direction has been opened to use an intelligent soft computing technique (Fast Genetic Algorithm) with the temporal predictability of signals based on Stone’s BSS method. Proposed algorithm has been compared with wellknown BSS algorithms (JADE, FICA, and Stone’s BSS) over super-Gaussian, sub-Gaussian, and Gaussian signals with linear mixture combination. Then eight voices have mixed randomly; and the proposed approach has successfully recovered the voices with high efficiency. Interpretation based on the responses of two different linear scalar filters to the same set of signals, which indicate to Short-term and Long-term linear predictors with tuned Half-life values (hL, hS) genetically is a powerful new technique for solving BSS problem. In addition to the benefits of the Stone’s method, the proposed algorithm overcomes the local minima problem by successfully jump out of the potential local minimum. Usually recovery methods depend on the difference between signals and mixture proprieties; generally, there are three famous properties for any signal: (1) Gaussian probability density function based on the central limit theorem (2) Degree of statistical independence (3) Temporal predictability. So (1&2) proprieties, have previously been used as a base for separation but in this work only 3rd property has been used. In order to check the effectiveness of the proposed algorithm two performance indexes are used: Interference to signal ratio (ISR), and Integral square error (ISE).
    Signal Processing (ICSP), 2012 IEEE 11th International Conference, Beijing; 10/2012
  • [Show abstract] [Hide abstract]
    ABSTRACT: Optimal design of the decoupled sliding mode control (SMC) is a great and worthwhile challenge by regarding appropriate design parameters and objective function. In the present study, Genetic Algorithm (GA) is employed as an effectual smart evolutionary algorithm to design optimally the control coefficients of an Inverted Pendulum (IP) and to eliminate tedious and repetitive trial-and-error process. When decoupled SMC is used to address the problem, there has to be a trade-off between the error of the position and the error of the angle. Hence, a Multi-objective Genetic algorithm is used to design optimally the Pareto front of the problem by regarding the errors as objective functions. Moreover, simulation has been done by considering the case with external disturbance and without external disturbance. Then, the results implemented in the MATLAB software environment are contrasted with the experimental results. Numerical results and comparison analysis elucidates the superiority of the optimal robust proposed controller over the traditional decoupled sliding mode controller in terms of attenuating the chattering and actuator variations.
    Innovations in Intelligent Systems and Applications (INISTA), 2013 IEEE International Symposium on; 01/2013
Show more


19 Reads
Available from