DEEP LEARNING-BASED PREDICTION OF OBESITY LEVELS ACCORDING TO EATING HABITS AND PHYSICAL CONDITION

Abstract

Obesity occurs as a result of excessive fat storage in the body and brings along physical and mental problems [1]. The physical function has been associated with impaired quality of life in various areas such as distress in society, sexual function, self-esteem, and work-related quality of life [2]. The prevalence of obesity has been steadily increasing over the past few decades and is now unprecedented. This increase has occurred in almost all ages, genders, and races. These data show that the segments of individuals in the highest weight categories i.e. (BMI> 40 kg / m2) increased proportionally more than those in the lower BMI categories (BMI <35 kg / m2) [3]. Given the numerous and important health consequences associated with obesity, there is an urgent need to develop highly effective interventions aimed at reversing these “obesogenic” drivers, including both government policies and health education and development programs. It is important to implement measures to be taken, including both government policies and health education and development programs, especially during the COVID-19 pandemic process we are in. In this study, the data set on the open-source access website was used for the prediction of obesity levels and consists of patient records of 17 variables created by the deep learning repository. In addition, the performance of deep learning methods in the prediction of obesity levels was examined and determined. Performance evaluation of models is compared in terms of accuracy, Fleiss's kappa, classification error, and absolute error.

Keywords

• Obesity
• Obesity Levels
• Deep Learning.

References

1. S. Deniz, H. Şirin, M. Kıvrak, Z. Kaplan, G. Ketrez, and S. Üner, "Factors associated with overweight and obesity in students of 5-14 age group in Mersin," Gülhane Tip Dergisi, vol. 62, no. 4, p. 245, 2020.
2. K. R. Fontaine, S. J. Bartlett, and I. Barofsky, "Health‐related quality of life among obese persons seeking and not currently seeking treatment," International Journal of Eating Disorders, vol. 27, no. 1, pp. 101-105, 2000.
3. S. M. Wright and L. J. Aronne, "Causes of obesity," Abdominal Radiology, vol. 37, no. 5, pp. 730-732, 2012.
4. G. B. o. D. Study, "Global Burden of Disease Study 2015 (GBD 2015) Obesity and Overweight Prevalence 1980–2015," ed: United States: Institute for Health Metrics and Evaluation (IHME) Seattle, 2017.
5. G. M. Singh et al., "The age-specific quantitative effects of metabolic risk factors on cardiovascular diseases and diabetes: a pooled analysis," PloS one, vol. 8, no. 7, p. e65174, 2013.
6. F. Mendoza Palechor and A. de la Hoz Manotas, "Dataset for estimation of obesity levels based on eating habits and physical condition in individuals from Colombia, Peru, and Mexico," Data, in brief, 25,104344, 2019.
7. Y. Li, X. Nie, and R. Huang, "Web spam classification method based on deep belief networks," Expert Systems with Applications, vol. 96, pp. 261-270, 2018.
8. J. Gu et al., "Recent advances in convolutional neural networks," Pattern Recognition, vol. 77, pp. 354-377, 2018.

9. W. A. Scott, "Reliability of content analysis: The case of nominal scale coding," Public opinion quarterly, pp. 321-325, 1955.
10. J. Cohen and p. measurement, "A coefficient of agreement for nominal scales," Educational and psychological measurement, vol. 20, no. 1, pp. 37-46, 1960.
11. J. L. Fleiss, "Measuring nominal scale agreement among many raters," Psychological Bulletin, vol. 76, no. 5, p. 378, 1971.
12. C. B. Read and B. Vidakovic, "Encyclopedia of statistical sciences." John Wiley & Sons, 2006.
13. Ş. Yaşar, A. Arslan, C. Colak, and S.Yoloğlu, "A Developed Interactive Web Application for Statistical Analysis: Statistical Analysis Software," Middle Black Sea Journal of Health Science, vol. 6, no. 2, pp. 227-239.
14. M. Campbell, "RStudio Projects," in Learn RStudio IDE: Springer, 2019, pp. 39-48.
15. M. Hofmann and R. Klinkenberg, RapidMiner: Data mining use cases and business analytics applications. CRC Press, 2016.
16. S. Yadav and S. Shukla, "Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification," in 2016 IEEE 6th International conference on advanced computing (IACC), 2016, pp. 78-83: IEEE.