Prediction of Vegetarian Food Preferences for the Aging Society

Abstract

Abstract The objective of this research is to predict vegetarian food preferences from chronic disease among the elderly by using a hybrid method that includes both an artificial neural network (ANN) and particle swarm optimization (PSO), called ANN-PSO. ANN is a mathematical model that mimics the human brain that is intelligent in learning, prediction, recognition, classification by practice, and solving complex problems. In this study, data collection of vegetarian food preferences, including gender (male and female), a chronic disease selected from the diseases that are common among the elderly, and a vegetarian menu suitable for the chronic disease. Data were collected by interviewing 100 elderly people. Then, the data were analysed using artificial neural networks and applied the particle swarm optimization method to determine the appropriate parameters (weights) for the neural network. The results indicate that the application of PSO along with ANN can accurately predict vegetarian preferences for the aging society. The accurate vegetarian prediction model resulted in increasing consumption of vegetarian food and allowed manufacturers to produce meals or present menus tailored to the individual preferences of the elderly.