Fuzzy Wavelet Neural Network with Social Spider Optimization Algorithm for Pattern Recognition in Medical Domain

Document Type


Publication Date



Providing accurate and accessible diagnoses is an important challenge for global healthcare system. The recently developed artificial intelligence (AI) and machine learning (ML) have emerged as powerful tools for solving medical data classification problems. The current research article presents a new Fuzzy Wavelet Neural Network (FWNN) with Social Spider Optimization (SSO) algorithm to recognize the medical data. The aim of FWNN is to utilize both WNN and Adaptive Fuzzy Neuro Inference System (ANFIS) to increase the convergence rate and achieve better approximation abilities. But a number of parameters should be adjusted in due course. In addition, the fuzzy rules enable the technique to tackle uncertainty, whereas the wavelets contribute to enhancing the accuracy of the input output map. SSO algorithm is applied to optimize the architectural parameters of FWNN model such as learning parameters, weights, dilation, and translation. The application of SSO algorithm helps in determining the hyperparameters of FWNN model during medical diagnosis. This is the novelty of current work and it assists in improving the classification performance. The SSO-FWNN model was experimentally validated using three medical benchmark datasets namely, breast cancer, heart disease, and hepatitis. The outcome of simulations indicates that the SSO-FWNN model achieved maximum outcome on all the applied datasets over existing methods in a significant way.

Publication Title

Studies in Fuzziness and Soft Computing

First Page Number


Last Page Number




This document is currently not available here.