Blind Source Separation of Super and Sub-Gaussian Signals with ABC Algorithm

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.