This paper introduced a Particle Swarm Optimization-Radial Basis Function Neural Networks (PSO-RBFNN)-based system for heart disease detection that used the PSO algorithm to optimize RBFNN parameters. The newly developed signal digital algorithm presents the results of a new image contrast enhancement approach using Double Density Discrete Wavelet transform DDDWT for extraction of features, using adaptive DDDWT for the elimination of noise, and the use of PSO and ANN methods to classify the output from the Electrocardiogram (EGGS). It also provides identification of all techniques and MATLAB codes used to improve the processes.
This approach merged the global search power of the PSO algorithm with the high efficiency of RBFNN's local optimums, overcome the inconsistency of the PSO algorithm and the RBFNN downside, quickly leading to a local minimum. The results show that, as compared to other approaches, the PSO-RBFNN model of heart disease diagnosis is highly accurate in detecting and predicting.