Missing Value Imputation in Stature Estimation by Learning Algorithms Using Anthropometric Data: A Comparative Study

Abstract

Estimating stature is essential in the process of personal identification. Because it is difficult to find human remains intact at crime scenes and disaster sites, for instance, methods are needed for estimating stature based on different body parts. For instance, the upper and lower limbs may vary depending on ancestry and sex, and it is of great importance to design adequate methodology for incorporating these in estimating stature. In addition, it is necessary to use machine learning rather than simple linear regression to improve the accuracy of stature estimation. In this study, the accuracy of statures estimated based on anthropometric data was compared using three imputation methods. In addition, by comparing the accuracy among linear and nonlinear classification methods, the best method was derived for estimating stature based on anthropometric data. For both sexes, multiple imputation was superior when the missing data ratio was low, and mean imputation performed well when the ratio was high. The support vector machine recorded the highest accuracy in all ratios of missing data. The findings of this study showed appropriate imputation methods for estimating stature with missing anthropometric data. In particular, the machine learning algorithms can be effectively used for estimating stature in humans.

Morphology, body composition and maturity status of young Colombian athletes from the Urabá subregion: A k-Medoids and hierarchical clustering analysis

“…Thus, we believe that complementary skills in programming and data science are mandatory for the enrichment analysis that might take place in sports studies for talent identification, especially because clustering is not the only valuable type of machine learning that can be explored. For instance, there have been recent proposals to measure anthropometrical features by means of image processing and machine learning algorithms, such as sub-pixel processing and finding convexity hull defects (Nguyen, Nguyen, & Zhukov, 2015), machine learning regressions (i.e., support vector regression, Gaussian processes regression, and neural network regression) instead of conventional linear regressions to estimate stature and body mass (Rativa, Fernandes, & Roque, 2018), or imputation methods based on naïve Bayes classifier, artificial neural networks, and support vector machine to estimate stature in humans (Son & Kim, 2020).…”

Comparison of Selection Criteria for Model Selection of Support Vector Machine on Physiological Data with Inter-Subject Variance

“…Statistical analysis was conducted to verify the effectiveness of LSSC compared with other selection criteria. The t-test was used as a statistical analysis tool to identify whether the difference between classification accuracies by the LSSC and others was significant [43]. The dataset of classification accuracies was constructed for each selection criterion and used in the analysis.…”

Imputation Techniques in Machine Learning – A Survey

“…The evaluation of each imputation method encompasses an assessment of the imputation quality as well as the influence of imputation on the performance of downstream ML tasks. Youngdoo Son et al [9], assessed the accuracy of height estimations derived from anthropometric data using three distinct imputation methods. Across various levels of missing data, the support vector machine consistently exhibited the highest accuracy.…”