Posture Recognition Using the Interdistances Between Wearable Devices

Recognition of user's postures and activities is particularly important, as it allows applications to customize their operations according to the current situation. The vast majority of available solutions are based on wearable devices equipped with accelerometers and gyroscopes. In this article, a different approach is explored: The posture of the user is inferred from the interdistances between the set of devices worn by the user. Interdistances are first measured by using ultra-wideband transceivers operating in two-way ranging mode and then provided as input to a classifier that estimates current posture. An experimental evaluation shows that the proposed method is effective (up to ~98.2% accuracy), especially when using a personalized model. The method could be used to enhance the accuracy of activity recognition systems based on inertial sensors.