Classifying and using motion in organic indoor positioning

Current mobile devices continuously estimate their locations, allowing users to “check in”, find nearby friends and interests, and determine routes to their destinations. While underlying satellite, cell, and WiFi-based positioning systems can return an accurate and meaningful position in many cases, extending them to work energy-efficiently, particularly indoors, remains an open problem. In this work, we study energy-efficient and robust human-scale motion classifiers and their use in room-grain, collaborative indoor positioning systems. Previous work on improving energy-efficiency in positioning systems has assumed sensor input from an energy-cheaper alternative: using an accelerometer in lieu of GPS, for example. Unfortunately, even these alternative sensors are not practical for everyday use because of their own energy consumption, at least when sampled continuously. After studying what accelerometer sampling rates are feasible, we compare six methods for motion classification, two of which are new. We find that the existing simple statistical methods are not sufficiently robust with respect to different kinds of movement and different users, because the thresholds between movement and non-movement are too tight. In contrast we find that the two new, more sophisticated models, one based on Page-Hinkley statistics, and the other inspired by the Discrete Fourier Transform, provide a clearer differentiation between the two states. Only the Page-Hinkley-based one is as energy-efficient as the simple statistical methods, however. Through a WiFi geolocation system that relies on motion detection, we show how the choice of the underlying motion classifier can have a significant impact on user-perceived performance.