Obesity diagnosis using biomedical signals has received increasing attention in recent years and requires advanced signal processing techniques in order to accurately classify obesity. In this context, this study proposes an intelligent diagnostic system for obesity classification using flash electroretinogram (fERG) signals, with a specific focus on cone responses. A novel feature extraction method based on Wavelet Packet Decomposition (WPD) is employed to decompose the cone responses into high- and low-frequency components, enabling detailed time-frequency analysis with high resolution. Subsequently, statistical features, such as mean, standard deviation, skewness, and kurtosis, are extracted from the decomposed signals and refined to enhance the training of artificial neural networks (ANNs). To optimize model performance, Particle Swarm Optimization (PSO) is integrated with ANN, resulting in an ANN-PSO hybrid model. The experimental dataset, comprising fERG signals from 47 subjects across diverse obesity categories, was utilized to evaluate the proposed hybrid model. The ANN-PSO model demonstrated high classification performance, achieving average accuracies of 95.74%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$95.74\%$$\end{document} and 96.60%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$96.60\%$$\end{document} for right and left eye signals, respectively, outperforming traditional ANN models. These findings highlight the effectiveness of WPD in capturing intricate signal characteristics relevant to obesity levels and confirm the potential of the ANN-PSO model as a robust, efficient, and reliable diagnostic tool for clinical applications beyond conventional BMI assessments.