Enhancing BMI-Based Student Clustering by Considering Fitness as Key Attribute

  • Erik DovganEmail author
  • Bojan Leskošek
  • Gregor Jurak
  • Gregor Starc
  • Maroje Sorić
  • Mitja Luštrek
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11828)


The purpose of this study was to redefine health and fitness categories of students, which were defined based on body mass index (BMI). BMI enables identifying overweight and obese persons, however, it inappropriately classifies overweight-and-fit and normal-weight-and-non-fit persons. Such a classification is required when personalized advice on healthy life style and exercises is provided to students. To overcome this issue, we introduced a clustering-based approach that takes into account a fitness score of students. This approach identifies fit and not-fit students, and in combination with BMI, students that are overweight-and-fit and those that are normal-weight-and-non-fit. These results enable us to better target students with personalized advice based on their actual physical characteristics.


Improving BMI-based classification Fitness-based clustering Multiobjective problem 


  1. 1.
    Bacha, F., Saad, R., Gungor, N., Janosky, J., Arslanian, S.A.: Obesity, regional fat distribution, and syndrome X in obese black versus white adolescents: race differential in diabetogenic and atherogenic risk factors. J. Clin. Endocrinol. Metab. 88, 2534–2540 (2003)CrossRefGoogle Scholar
  2. 2.
    Deb, K., Pratap, A., Agrawal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)CrossRefGoogle Scholar
  3. 3.
    Eurofit: Eurofit Tests of Physical Fitness. Council of Europe, Strasbourg, 2 edn. (1993)Google Scholar
  4. 4.
    Farrell, S.W., Finley, C.E., Radford, N.B., Haskell, W.L.: Cardiorespiratory fitness, body mass index, and heart failure mortality in men. Circ. Hear. Fail. 6(5), 898–905 (2013)CrossRefGoogle Scholar
  5. 5.
    Kallioinen, M., Granheim, S.I.: Overweight and obesity in the western pacific region. Technical report, World Health Organization (2017)Google Scholar
  6. 6.
    Kanungo, T., Mount, D.M., Netanyahu, N.S., Piatko, C.D., Silverman, R., Wu, A.Y.: An efficient k-means clustering algorithm: analysis and implementation. IEEE Trans. Pattern Anal. Mach. Intell. 24, 881–892 (2002)CrossRefGoogle Scholar
  7. 7.
    Ortlepp, J.R., Metrikat, J., Albrecht, M., Maya-Pelzer, P., Pongratz, H., Hoffmann, R.: Relation of body mass index, physical fitness, and the cardiovascular risk profile in 3127 young normal weight men with an apparently optimal lifestyle. Int. J. Obes. 27, 979–982 (2003)CrossRefGoogle Scholar
  8. 8.
    Rokach, L., Maimon, O.: Clustering methods. In: Maimon, O., Rokach, L. (eds.) Data Mining and Knowledge Discovery Handbook, pp. 321–352. Springer, Boston (2005). Scholar
  9. 9.
    Shi, J., Malik, J.: Normalized cuts and image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 22, 888–905 (2000)CrossRefGoogle Scholar
  10. 10.
    Weber, D.R., Moore, R.H., Leonard, M.B., Zemel, B.S.: Fat and lean BMI reference curves in children and adolescents and their utility in identifying excess adiposity compared with BMI and percentage body fat. Am. J. Clin. Nutr. 98(1), 49–56 (2013)CrossRefGoogle Scholar
  11. 11.
    Zhang, T., Ramakrishnan, R., Livny, M.: Birch: an efficient data clustering method for very large databases. In: Proceedings of the 1996 ACM SIGMOD International Conference on Management of Data, pp. 103–114 (1996)Google Scholar
  12. 12.
    Zitzler, E., Thiele, L.: Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach. IEEE Trans. Evol. Comput. 3(4), 257–271 (1999)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Intelligent SystemsJožef Stefan InstituteLjubljanaSlovenia
  2. 2.Faculty of SportUniversity of LjubljanaLjubljanaSlovenia

Personalised recommendations