Open Access Open Access  Restricted Access Subscription or Fee Access

Obesity Indonesia Children Detection According to Macronutrients by Using Binary Logistic Regression and Radial Basis Function Neural Networks

Brodjol Sutijo Suprih Ulama, Hanny Adiati

Abstract


Childhood obesity is a health problem in Indonesia. Based on Health Research, prevalence obesity of children age 6-12 years was 9.2%in 2010, the rate increased in 2013 to double to 18,8%. Obesity is a disease that has multifactorcauses.Theone of contributing obesity factor is determined by intake of nutrients. Macronutrients (energy, protein, fat and carbohydrate)that enter the body is a major obesity factor. Children obesity status can be detected by using macronutrients variables.Binary Logistic Regression and Radial Basis Neural Network (RBFNN) are methods that can be use to classify object. One of the important things in RBFNN is the weigh ofhidden nodes. Self Organizing Maps (SOM) is a method to determinedweight of hidden nodes on RBFNN (SOM-RBFNN). Based on RBFNN models, 2 nodes inhidden layer of RBFNN give the best classification object. Binary logistic regression give the classification accuracy 90.00% for boys and 93.40% for girl. SOM-RBFNN give the classification accuracy 90.023% for boys and 93.43% for girl.

Keywords


Obesity, Macronutrients, Logistic Regression, SOM-RBFNN

Full Text:

PDF


Disclaimer/Regarding indexing issue:

We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.