Abstract—This study was performed to extract rules for reducing body fat mass for preventing lifestyle-related diseases. Lifestyle-related diseases have been increasing in Japan, even among younger people. Body fat mass is related to lifestyle-related diseases. Hence, finding rules for reducing body fat mass is very meaningful. We obtained lifestyle time-series data from five male subjects who are in their 20s and not obese. The data includes the amount of body fat mass in each subject and a variety of features. We used Inductive Logic Programming (ILP) to apply this data because ILP can more flexibly learn rules than other machine-learning methods. As a result of applying the data to ILP, our ILP system has successfully extracted rules to decrease body fat mass based on limited data. Learned rules indicate that a combination of sufficient sleep and low intake of carbohydrates; a combination of duration of protein and low intake of fat;, or a combination of sufficient protein intake, low fat intake, and sufficient vitamin D intake is the most effective lifestyle in decreasing body fat mass. Earlier studies have amply demonstrated that nutrient intake alone is effective in decreasing body fat mass using statistical analysis. However, this study revealed a new finding that a combination of sufficient sleep and low intake of carbohydrates is also effective, and we can infer that a combination with some nutrients is more effective in decreasing body fat mass than nutrients alone.
Index Terms—Inductive logic programming, knowledge discovery and data mining, machine learning, lifestyle-related diseases.
Sho Ushikubo, Katsutoshi, Kanamori, and Hayato Ohwada are with Tokyo University of Science, Noda city, Chiba prefecture, Japan (e-mail: 7415605@ed.tus.ac.jp, katsu@rs.tus.ac.jp, ohwada@rs.tus.ac.jp).
Cite: Sho Ushikubo, Katsutoshi Kanamori, and Hayato Ohwada, "Extracting Lifestyle Rules for Reduction of Body Fat Mass Using Inductive Logic Programming," International Journal of Machine Learning and Computing vol.6, no. 2, pp. 101-104, 2016.