Skip to main content
SpringerLink
Log in

Ensembled artificial neural networks to predict the fitness score for body composition analysis

  • JNHA: Nutrtion
  • Published:
The journal of nutrition, health & aging

Abstract

Objectives

To predict the nutrition and health status of staff and students in Yuan Ze University and select the influential variables from the total body composition variables, which should have similar predictive ability with the whole factors.

Design

Spontaneous and voluntary physical examination.

Setting

Sanitary & Health Care Section of Yuan Ze University in Taiwan.

Participants

1227 staff and students.

Measurements

With the help of Inbody720TM, 139 body composition variables were measured and 60 variables were retained after data pre-processing. An ensembled artificial neural networks (EANN) prediction model was established and seven different methods for assessing variables importance were applied. Besides, classical linear and logistic regression models were developed for comparison with EANN prediction results.

Results

The prediction performance of EANN model was satisfactory (RMSE (train) = 0.2686, RMSE (validation) = 0.2648, RMSE (test) = 0.3492). Since both the actual and simulation fitness score were at the range of 0 to 100, according to rounding off rule, the simulated value was almost the same with actual value. Besides, 12 important variables were obtained by seven methods for quantifying variable importance in EANN, which had similar predictive capability with 60 variables (RMSE (train) = 0.3263, RMSE (validation) = 0.322, RMSE (test) = 0.3226). The linear and logistic regression models results were both evidently worse than EANN results.

Conclusion

The results confirm that EANN is appropriate to approximate such a complicated, non-invasive and highly non-linear problem as body composition analysis. It can be helpful for nutritionists to manage and improve the nutrition and health condition of staff and students, by adjusting the 12 most important variables.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Compston JE, Bhambhani M, Laskey MA, Murphy S, Khaw KT. Body composition and bone mass in post-menopausal women. Clin Endocrinol (Oxf) 1992; 37: 426–431.

    Article  CAS  Google Scholar 

  2. Douchi T, Kuwahata R, Matsuo T, Uto H, Oki T, Nagata Y. Relative contribution of lean and fat mass component to bone mineral density in males. J Bone Miner Metab 2003; 21: 17–21.

    Article  PubMed  CAS  Google Scholar 

  3. Cui L-H, Shin M-H, Kweon S-S, Park K-S, Lee Y-H, Chung E-K, Nam H-S, Choi JS. Relative contribution of body composition to bone mineral density at different sites in men and women of South Korea. J Bone Miner Metab 2007; 25:165–171.

    Article  PubMed  Google Scholar 

  4. Tomouma HY, Badawy NB, Hassan NE, Alian KM. Anthropometry and body composition analysis in children with cerebral palsy. Clinical Nutrition 2009; 10:1–5.

    Google Scholar 

  5. Van Loan MD. Body composition in disease: what can we measure and how can we measure it? Acta Diabetol 2003; 40:154–157.

    Article  Google Scholar 

  6. Gordon MM, Boppl MJ, Easter L, Miller GD, Lyles MF, Houston DK, nicklas BJ, Kritchevsky SB. Effects of dietary protein on the composition of weight loss in postmenopausal women. J Nutr Health Aging 2008; 12:505–509.

    Article  PubMed  CAS  Google Scholar 

  7. Shaw D, Kavanal BK. Development of a multiple regression equation to predict judo performance with the help of selected structural and body composition variables. Conf Proc IEEE Eng Med Biol Soc 1995; 3:97–98.

    Google Scholar 

  8. Wimberly MG, Manore MM, Woolf K, Swan PD, Carroll SS. Effects of habitual physical activity on the resting metabolic rates and body compositions of women aged 35 to 50 years. J Am Diet Assoc 2001; 101(10): 1181–1188.

    Article  Google Scholar 

  9. Lek S, Delacoste M, Baran P, Dimopoulos I, Lauga J, Aulagnier S. Application of neural networks to modelling nonlinear relationships in ecology. Ecol Modell 1996; 90: 39–52.

    Article  Google Scholar 

  10. Paruelo JM, Tomasel F. Prediction of functional characteristics of ecosystems: a comparison of artificial neural networks and regression models. Ecol Modell 1997; 98:173–186.

    Article  Google Scholar 

  11. Ramos-Nino ME, Ramirez-Rodriguez CA, Clifford MN, Adams MR. A comparison of quantitative structure-activity relationships for the effect of benzoic and cinnamic acids on Listeria monocytogenes using multiple linear regression, artificial neural network and fuzzy systems. J Appl Microbiol 1997; 82:168–176.

    PubMed  CAS  Google Scholar 

  12. Manel S, Dias JM, Ormerod SJ. Comparing discriminant analysis, neural networks and logistic regression for predicting species distributions: a case study with a Himalayan rive rbird. Ecol Modell 1999; 120:337–347.

    Article  Google Scholar 

  13. Starrett SK, Adams GL. Using artificial neural networks and regression to predict percentage of applied nitrogen leached under turfgrass. Communications in Soil Science Plant Analytical 1997; 28: 497–507.

    Article  Google Scholar 

  14. Yang S, Browne A. Neural network ensembles: Combining multiple models for enhanced performance using a multistage approach. Expert Systems 2004; 24: 279–288.

    Article  Google Scholar 

  15. Linder R, Mohamed EI, Lorenzo AD, Pöppl SJ. The capabilities of artificial neural networks in body composition research. Acta Diabetol 2003; 40:9–14.

    Article  Google Scholar 

  16. Julian DO, Michael KJ, Russell G.D. An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecol Modell 2004; 178: 389–397.

    Article  Google Scholar 

  17. Gevrey M, Dimopoulos I, Lek S. Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecol Modell 2003; 160: 249–264.

    Article  Google Scholar 

  18. Hunter A, Kennedy L, Henry J, Ferguson I. Application of neural networks and sensitivity analysis to improved prediction of trauma survival. Comput Methods Programs Biomed 2000; 62: 11–19.

    Article  PubMed  CAS  Google Scholar 

  19. Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagation error. Nature 1986; 323:533–536.

    Article  Google Scholar 

  20. Lin CT, Lee CSG. Neural Fuzzy Systems-A Neuro-Fuzzy Synergism to Intelligent Systems. Prentice Hall International, Inc. 1999.

  21. Freeman JA, Skapura DM. Neural network: Algorithms, Applications, and Programming Techniques. Reading, MA: Addison-Wesley 1991.

    Google Scholar 

  22. Amari S, Murata N, Müller K, Finke M, Yang HH. Asymptotic statistical theory of overtraining and cross-validation. IEEE Trans Neural Netw 1997; 8: 985–996.

    Article  PubMed  CAS  Google Scholar 

  23. Wang C, Venkatesh SS, Judd JS. Optimal stopping and effective machine complexity in learning. Adv Neural Inf Process Syst 1995; 6: 303–310.

    Google Scholar 

  24. Finnoff W, Hergert F, Zimmermann HG. Improving model selection by nonconvergent methods. Neural Netw 1993; 6: 771–783.

    Article  Google Scholar 

  25. Prechelt L. Automatic early stopping using cross validation: quantifying the criteria. Neural Netw 1998; 11:761–767.

    Article  PubMed  Google Scholar 

  26. Hansen LK, Salamon P. Neural network ensembles. IEEE Trans. Pattern Anal. Machine Intelligence 1990; 12: 993–1001.

    Article  Google Scholar 

  27. Zhou ZH, Wu J, Tang W. Ensembling neural networks: Many could be better than all. Artificial Intelligence 2002; 137: 239–263.

    Article  Google Scholar 

  28. Lek S, Belaud A, Dimopoulos I, Lauga J, Moreau J. Improved estimation, using neural networks, of the food consumption of fish populations. Marine Fresh water Research 1995; 46: 1229–1236.

    Article  Google Scholar 

  29. Lek S, Belaud A, Baran P, Dimopoulos I, Delacoste M. Role of some environmental variables in trout abundance models using neural networks. Aquatic Living Resources 1996; 9: 23–29.

    Article  Google Scholar 

  30. Lek S, Delacoste M, Baran P, Dimopoulos I, Lauga J, Aulagnier S. Application of neural networks to modelling nonlinear relationships in ecology. Ecol Modell 1996; 90: 39–52.

    Article  Google Scholar 

  31. Scardi M, Harding LW. Developing an empirical model of phytoplankton primary production: a neural network case study. Ecol Modell 1999; 120: 213–223.

    Article  Google Scholar 

  32. Olden JD, Jackson DA. Illuminating the “black box”: understanding variable contributions in artificial neural networks. Ecol Modell 2002; 154:135–150.

    Article  Google Scholar 

  33. Garson GD. Interpreting neural-network connection weights. Artif Intell Expert 1991; 6: 47–51.

    Google Scholar 

  34. Hilbe J M. Logistic Regression Models. Chapman & Hall/CRC Press 2009.

  35. Masters T. Practical neural network recipes in C++. Academic Press, Boston. MA 1994.

    Google Scholar 

  36. Bigaard J, Tjonneland A, Thomsen BL, et al. Waist circumference, BMI, smoking, and mortality in middle-aged men and women. Obes Res 2003; 11: 895–903.

    Article  PubMed  Google Scholar 

  37. Yusuf S, Hawken S, Ounpuu S, et al. Obesity and the risk of myocardial infarction in 27,000 participants from 52 countries: a case-control study. Lancet 2005; 366:1640–1649.

    Article  PubMed  Google Scholar 

  38. Reid IR, Plank LD, Evans MC. Fat mass is an important determinant of whole body bone density in premenopausal women but not in men. J Clin Endocrinol Metab 1992; 75: 779–782.

    Article  PubMed  CAS  Google Scholar 

  39. Wang MC, Bachrach LK, Van Loan M, Hudes M, Flegal KM, Crawford PB. The relative contributions of lean tissue mass and fat mass to bone density in young women. Bone (NY) 2005; 37: 474–481.

    CAS  Google Scholar 

  40. Reid IR, Ames R, Evans MC, Sharpe S, Gamble g, France JT, Lim TM, Cundy TF. Determinants of total body and regional bone mineral density in normal postmenopausal women-a key role for fat mass. J Clin Endocrinol Metab 1992; 75: 45–51.

    Article  PubMed  CAS  Google Scholar 

  41. Douchi T, Yamamoto S, Nakamura S, Oki T, Maruta K, Nagata Y. Bone mineral density in postmenopausal women with endometrial cancer. Maturitas 1999; 31:165–170.

    Article  PubMed  CAS  Google Scholar 

  42. Reid IR. Relationships among body mass, its components, and bone. Bone (NY) 2002; 31: 547–555.

    CAS  Google Scholar 

  43. Wang W, Jones P, Partridge D. Assessing the impact of input features in a feed forward neural network. Neural Comput & Applic 2000; 9: 101–112.

    Article  Google Scholar 

  44. Cang S, Partridge D. Feature ranking and best feature subset using mutual information. Neural Comput & Applic 2004; 13: 175–184.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Information Engineering, Wuhan University of Technology, Wuhan, P.R. China

    X. R. Cui & Q. Liu

  2. School of Engineering and Design, Brunel University, West London, UK

    M. F. Abbod

  3. Department of Mechanical Engineering, Yuan Ze University, Chungli, Taiwan

    Jiann-Shing Shieh

  4. Sanitary & Health Care Section, Office of Student Affairs, Yuan Ze University, Chungli, Taiwan

    T. Y. Chao, C. Y. Hsieh & Y. C. Yang

  5. Department of Mechanical Engineering, Yuan Ze University, 135 Yuan-Tung Rd., Chung-Li, Taoyuan, 320, Taiwan

    Jiann-Shing Shieh

Authors
  1. X. R. Cui
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. F. Abbod
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Q. Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jiann-Shing Shieh
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. T. Y. Chao
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. C. Y. Hsieh
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Y. C. Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jiann-Shing Shieh.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Cui, X.R., Abbod, M.F., Liu, Q. et al. Ensembled artificial neural networks to predict the fitness score for body composition analysis. J Nutr Health Aging 15, 341–348 (2011). https://doi.org/10.1007/s12603-010-0260-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12603-010-0260-1

Key words

Search

Navigation