Abstract:
Diabetes is one of metabolic diseases which effects on productivity and lowers the human resources quality. This disease can be controlled by maintaining and regulating a balanced and healthy lifestyle especially, for daily diet. There are many techniques and tools which suggest the best diets according to patient's health situation and preferences. A diabetic needs a healthy diet that ensures maintaining blood sugar levels to avoid any complications that harm his health. This does not mean that he is deprived of eating various types of foods, but he should choose less harmful foods and avoid foods that can cause high blood sugar levels.
In this thesis, the researcher will presenta type 2 fuzzy logic diet recommendation system for Sudanese Diabetesto learn from data a prediction model for Basal Metabolic Rate which also allows to evaluate whether the rules used to calculate the amount of energy expended per day at rest (basal metabolic rate) for patients can help them to obtain health information leading to healthy lifestyle and healthy diet in controlling this disease. The proposed system was trained and tested using real world data set collected from Jabir Abu-Eliz Centre in Khartoum. I use the Fuzzy C-Means (FCM) clustering technique to extract parameters of fuzzy membership functions of Type-1 and Type-2 Fuzzy Logic System and they learned the rules from data. The Big Bang-Big Crunch (BBBC) algorithms is used to optimize the proposed model’s parameters of fuzzy logic membership functions and the number of fuzzy rules. The BB-BC used with type-1 and type 2 fuzzy logic system. The best results were achieved for the type-2 fuzzy logic systems, and they are better than type 1 fuzzy system.The BB-BC optimized type-2 Fuzzy Logic prediction System gained 80.6% prediction accuracy in our testing dataset which is better than its counterpart’s Type-1 and non-optimized Type-2 Fuzzy Logic prediction system. The results show that the optimized proposed Type-2 Fuzzy Logic System provides a more interpretable model that predicts the Basal Metabolic Rate
