Application of Shuffled Frog Leaping Algorithm and Wavelet Neural Network in Sound Source Location

Propose a wavelet neural network (WNN) sound source model based on Shuffled Frog Leaping Algorithm (SFLA). Utilize frog leaping algorithm to optimize weights and thresholds of WNN, obtain initial weights and thresholds possessing certain ergodicity and then train WNN. It overcomes disadvantages of neural network that has slower searching speed and easily falls into local extremum. Simulation results demonstrate that new WNN Algorithm has better convergence rate, positioning accuracy, favorable application prospect and further research value.