DESIGN AND IMPLEMENTATION OF A DIET RECOMMENDER SYSTEM

Abstract

Healthy diet is important in maintaining a healthy life, in managing and reducing the risk of diet related diseases. Food provides our body with energy, vitamins, and other essential nutrients needed by the body to sustain us for our day-to-day activities and to function properly. Information Technology has proved its strength in the provision of effective and efficient solutions in diverse fields of human endeavor. This thesis proposes the Design and Implementation of a Diet Recommender System. The proposed system uses Fuzzy Logic because of its ability to work from approximate reasoning and ultimately find a precise solution to a given problem like humans to establish a diagnosis status, Content based recommendation, and Pearson Correlation Coefficient to recommend diet and compare food nutrients. The goal of the diet recommender system is to recommend a healthy diet and appropriate quantity to users by considering the users height, weight, activity level and food dislike or allergies. The system was implemented using Hypertext Preprocessor (PHP), JavaScript and Hypertext Mark-up Language (HTML) programming languages with My Structured Query Language (MySQL) as the Database Management System. Data of diabetic patients were collected from the Obafemi Awolowo University Teaching Hospitals Complex (OAUTHC), Ile-Ife, Osun State, Nigeria, and were used to test the functionalities of the proposed system. Standard metrics such as accuracy of the system, user friendliness of the system, ease of understanding the system were used to evaluate the performance of the proposed system and the results of the evaluation shows that the system is efficient in the diet recommendation. The system could be used by dieticians in the hospitals to assist them in diet recommendation for patients. It can also be used in different homes to suggest varieties of meals to users.