The objective of this study was to investigate if the inertial data collected from normal human walk can be used to reveal the underlying terrain types. For this purpose, we recorded the gait patterns of normal human walk on six different terrain types with variation in hardness and friction using body mounted inertial sensors. We collected accelerations and angular velocities of 40 healthy subjects with two smartphones embedded inertial measurement units (MPU-6500) attached at two different body locations (chest and lower back). The recorded data were segmented with stride based segmentation approach and 194 tempo-spectral features were computed for each stride. We trained two machine learning classifiers, namely random forest and support vector machine, and cross validated the results with 10-fold cross-validation strategy. The classification tasks were performed on indoor–outdoor terrains, hard–soft terrains, and a combination of binary, ternary, quaternary, quinary and senary terrains. From the experimental results, the classification accuracies of 97% and 92% were achieved for indoor–outdoor and hard–soft terrains, respectively. The classification results for binary, ternary, quaternary, quinary and senary class classification were 96%, 94%, 92%, 90%, and 89%, respectively. These results demonstrate that the stride data collected with the low-level signals of a single IMU can be used to train classifiers and predict terrain types with high accuracy. Moreover, the problem at hand can be solved invariant of sensor type and sensor location.

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. INDEX TERMS Age estimation, inertial sensor based age estimation, human gait analysis, smartphone and wearable, soft biometrics.

Person re-identification (re-ID) is among the essential components that play an integral role in constituting an automated surveillance environment. Majorly, the problem is tackled using data acquired from vision sensors using appearance-based features, which are strongly dependent on visual cues such as color, texture, etc., consequently limiting the precise re-identification of an individual. To overcome such strong dependence on visual features, many researchers have tackled the re-identification problem using human gait, which is believed to be unique and provide a distinctive biometric signature that is particularly suitable for re-ID in uncontrolled environments. However, image-based gait analysis often fails to extract quality measurements of an individual’s motion patterns owing to problems related to variations in viewpoint, illumination (daylight), clothing, worn accessories, etc. To this end, in contrast to relying on image-based motion measurement, this paper demonstrates the potential to re-identify an individual using inertial measurements units (IMU) based on two common sensors, namely gyroscope and accelerometer. The experiment was carried out over data acquired using smartphones and wearable IMUs from a total of 86 randomly selected individuals including 49 males and 37 females between the ages of 17 and 72 years. The data signals were first segmented into single steps and strides, which were separately fed to train a sequential deep recurrent neural network to capture implicit arbitrary long-term temporal dependencies. The experimental setup was devised in a fashion to train the network on all the subjects using data related to half of the step and stride sequences only while the inference was performed on the remaining half for the purpose of re-identification. The obtained experimental results demonstrate the potential to reliably and accurately re-identify an individual based on one’s inertial sensor data.