%0 Conference Proceedings
%4 sid.inpe.br/sibgrapi/2021/09.14.17.45
%2 sid.inpe.br/sibgrapi/2021/09.14.17.45.23
%T Estimativa dos Níveis de Obesidade com Base em Hábitos Alimentares e Condição Física Através de Técnicas de Aprendizado de Máquina
%D 2021
%A Lopes, Leonardo Ferreira,
%A Oliveira, Adonias Caetano de,
%A Brito, Rhyan Ximenes de,
%A Oliveira, Saulo Anderson Freitas de,
%A Raposo Neto, Luiz Torres,
%@affiliation IFCE
%@affiliation IFCE
%@affiliation IFCE
%@affiliation IFCE
%@affiliation IFCE
%E Paiva, Afonso,
%E Menotti, David,
%E Baranoski, Gladimir V. G.,
%E Proença, Hugo Pedro,
%E Junior, Antonio Lopes Apolinario,
%E Papa, João Paulo,
%E Pagliosa, Paulo,
%E dos Santos, Thiago Oliveira,
%E e Sá, Asla Medeiros,
%E da Silveira, Thiago Lopes Trugillo,
%E Brazil, Emilio Vital,
%E Ponti, Moacir A.,
%E Fernandes, Leandro A. F.,
%E Avila, Sandra,
%B Conference on Graphics, Patterns and Images, 34 (SIBGRAPI)
%C Gramado, RS, Brazil (virtual)
%8 18-22 Oct. 2021
%I Sociedade Brasileira de Computação
%J Porto Alegre
%S Proceedings
%K Obesidade, Máquinas de Vetores de Suporte, Floresta Aleatória.
%X Obesity is a chronic disease that affects several countries, causing damage such as respiratory and locomotor difficulties, metabolic changes, cardiovascular problems, and even death, in the extreme case. In this perspective, this initial study aims to evaluate the classifiers' performance, namely, Random Forest and Support Vector Machine, when estimating obesity levels, with data from the set 'Estimation of obesity levels based on eating habits and physical condition Data Set'. Under cross-validation and Hold-Out, preliminary results indicate an average accuracy with SVM around 87.84% and RF around 95.18%. Furthermore, we noticed that our approach recognizes overweight and obesity cases better, while such cases, in the latest work, are more critically neglected, misclassifying the most severe degree of obesity. Thus, comparing our results with related works, we concluded that the models studied are suitable to the problem, given the achieved results.
%@language pt
%3 versao_final.pdf