A fuzzy logic approach to predict human body weight based on AR model

• Published in: 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011) pp. 1022 - 1025
• Main Authors: Tanii, Hideaki, Nakajima, Hiroshi, Tsuchiya, Naoki, Kuramoto, Kei, Kobashi, Syoji, Hata, Yutaka
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2011
• Subjects: autoregressive model; body weight; Brain modeling; Correlation; Data models; healthcare system; Mathematical model; prediction model; Predictive models; time-series data; Weight measurement
• ISBN: 9781424473151; 1424473152
• ISSN: 1098-7584
• DOI: 10.1109/FUZZY.2011.6007361

This paper proposes a body weight prediction method using auto regressive (AR) model and Fuzzy-AR model. First, we employ 6 persons body weight change data of 365 days. AR model predicts body weight of a day from these time-series data. We calculate an order of AR model for each person by Akaike's Information Criterion. In the experiment, we predicted body weight change of next day for those subjects. The AR model obtained 0.798 in correlation coefficient between predicted and truth values. Second, we propose a Fuzzy-AR model that predicts body weight of next p days from last p days, where p is the order of AR model. In this method, we propose a Fuzzy-AR model with the fuzzy membership function using last p days data. In the experiment, the Fuzzy-AR model obtained 0.558 in correlation coefficient on 2 subjects.