LAUSR

The estimation of soft biometrics of a subject, including age, through the gait analysis is a challenging area of research due to variations in individuals’ gaits and the effect of ageing on gait patterns. In this paper, we present the results of age estimation based on the analysis of inertial data of human walk. We have recorded 6D accelerations and angular velocities of 86 subjects while performing standardized gait tasks using chest-mounted inertial measurement units. The recorded data were segmented to decompose the long sequences of signals into single steps. For each step, we compute a total of 50 spatio-spectral features from 6D components. We trained three different machine learning classifiers—random forests, support vector machines, and multi-layer perceptron—to estimate the human age. Two different types of cross validation strategies, i.e., tenfold and subjectwise cross validation were employed to gauge the performance of the estimators. The results reveal that it is possible to predict the age of a subject with higher accuracy. With a random forest regressor, when trained and validated on hybrid data, we achieved an average root mean square error of 3.32 years and a mean absolute error of 1.75 years under tenfold cross validation and average root mean square error of 8.22 years under subjectwise cross validation. Since our participants belong to two different demographical regions, i.e., Europe and South Asia, we confirm on broader empirical basis previous findings that age information is present in the human gait. Our proposed approach allows rather robust estimations of age based on the inertial data of a single step, as the used data consist of those collected on different ground surfaces, and the participants were also told to walk pretending different emotional states. The findings on the existing data point out the change of gait while aging, which will also imply that person identification using the gait depends on data that is not too old.