The Method of Selecting the Evaluation Model for the State of Children's Growth Based on Machine Learning

Children's growth has always been the focus of social attention. Health problems can be found and solved as soon as possible through health risk evaluation. So it can promote the healthy growth of children. In this paper, a model selection method is proposed, which can select the suitable model from different factors, different grading standards and different models for the classification evaluation of children's growth. Factors including height, weight, head circumference, arm circumference, body mass index, subscapular skinfold thickness and triceps skinfold thickness. Grade results including bottom, above bottom, middle, below top and top. And we did experiments in KNN, Naive Bayes, logistic regression, decision tree, random forest, AdaBoosting and GBDT classifier models. The method proposed in this paper can certainly select children's growth evaluation model which can effectively evaluate children's growth status under given conditions.