Low Cost Architecture of Digital Circuit for FPGA Implementation Based ICA Training Algorithm of Blind Signal Separation

In this paper, we have illustrated the design of the computation of implementation which is principally based on finding correct values of the convergence of the update weights based on Independent Component Analysis (ICA) training algorithm that performs the application of Blind Signal Separation (BSS). We targeted simple computation of implementation, which yields to less complex architecture of the digital of implementation. Over the adjustment of the update weight with the mutual information approach, we reduced the high computation needed for the calculation of ICA training algorithm. The simulation results, obtained from a case study of FPGA implementation, demonstrated the correctness of the adjustment of the update weight with high performance of hardware implementation for BSS algorithm.