Recommended weight prediction system based on BMI, BMR, food calorie and a neural network

This paper presents a Recommended Weight Prediction System (RWPS) to be used in predicting the number of days needed for a person to attain a normal weight state based on his or her Body Mass Index (BMI), Basal Metabolic Rate (BMR), Daily Food calorie Intake (DFI) and a backpropagation neural network (BPNN). By using the BMI value, the system estimates the weight value of a person, where the individual with a normal BMI has a weight value of zero. Based on the BMR, the Daily Needed Calorie (DNC) of a person is calculated, and from the DNC, the weight value and the DFI, the number of days needed for a person to attain a “normal” BMI state could be predicted. The same could be applied when an underweight person under 30 years of age is being considered. The person in the later case would be checked for any eating disorders by the BPNN before applying the day prediction section of the system. The experimental results showed that the proposed approach could be an effective way for predicting any eating disorders and the number of days needed for a person to regain normal BMI.