Genetic Algorithm Approach in Optimizing the Energy Intake for Health Purpose
Energy intake of individual have an important role to support daily activity and it must fulfill the energy requirement in appropriate amounts. Energy requirement is determined based on Basal Metabolic Rate (BMR)—which is affected by weights, heights, age and gender—and physical activity level (PAL). While energy intake is calculated based on calorie from each portion of food consumed. This food consists of five principal elements, namely main dish, vegetable side dish, meat, vegetable and fruit. In the daily life, the difference between energy requirement and energy intake must be set as minimum as possible in order to avoid overweight or underweight condition. However, an individual is still having difficulty in determining the ideal portion of every kind of food that will be consumed in everyday. Therefore it is important to develop a system which gives the information regarding an optimal portion of each kind of food for an individual consumption. Genetic Algorithm (GA) is used to find the best portion and composition of food so that it will provide a proportional energy intake according to individual requirement. In the analysis we compare the results from GA and linear programming approach, the experiment shows that GA is succeed in giving proportional portion and composition as well as providing the diversity of food based on individual requirement.
KeywordsNutrition Food suggestion Energy requirement Energy intake Genetic algorithm
The authors thank to Bina Nusantara University for the research grant and supporting this research.
- 1.Amine, E., Baba, N., Belhadj, M., Deurenbery-Yap, M., Djazayery, A., Forrester, T., Galuska, D., Herman, S., James, W., M‘Buyamba, J., Katan, M., Key, T., Kumanyika, S., Mann, J., Moynihan, P., Musaiger, A., Prentice, A., Reddy, K., Schatzkin, A., Seidell, J., Simpopoulos, A., Srianujata, S., Steyn, N., Swinburn, B., Uauy, R., Wahlqvist, M., Zhao-su, W., Yoshiike, N.: Introduction. Diet , nutrition and the prevention of chronic diseases. Joint WHO/FAO expert consultation report, pp. 1–3 (2003)Google Scholar
- 2.Gerrior, Shirley, Juan, Wenyen, Basiotis, Peter: An easy approach to calculating estimated energy requirements. Prev. Chronic Dis. 3(4), A129 (2006)Google Scholar
- 4.Kesehatan, D.: Pedoman Gizi Seimbang, pp. 99 (2014)Google Scholar
- 5.Mifflin, M.D., St Jeor, S.T., Hill, L.A., Scott, B.J., Daugherty, S.A., Koh, Y.O.: A new predictive equation in healthy individuals for resting energy. Am. J. Clin. Nutr. 51, 241–247 (1990)Google Scholar
- 6.Peddi, S.V.B., Yassine, A., Shervin, S.: Cloud based virtualization for a calorie measurement e-health mobile application. In: IEEE International Conference on Multimedia & Expo Workshops (ICMEW), June 2015Google Scholar
- 8.Rajasekaran, S., Vijayalakshmi Pai, G.A.: Neural networks, fuzzy logic and genetic algorithms: synthesis and applications. Prentice-Hall of India, New Delhi (2007)Google Scholar
- 9.Roza, A.M., Shizgal, H.M.: The Harris Benedict energy requirements equation reevaluated: resting and the body cell mass. Am. J. Clin. Nutr. 40, 168–182 (1984)Google Scholar
- 10.Wells, J.C.K., Williams, J.E., Haroun, D., Fewtrell, M.S., Colantuoni, A., Siervo, M.: Aggregate predictions improve accuracy when calculating metabolic variables used to guide treatment. Am. J. Clin. Nutr. 89(2), 491–499 (2009)Google Scholar
- 11.Whyte, G., Harries, M., Williams, C.: ABC of Sports and Exercise Medicine, vol. 83. Wiley (2009)Google Scholar