Unsupervised Segmentation and Labeling for Smartphone Acquired Gait Data

As the population ages, prediction of falls risk is becoming an increasingly important research area. Due to built-in inertial sensors and ubiquity, smartphones provide an attractive data collection and computing platform for falls risk prediction and continuous gait monitoring. One challenge in continuous gait monitoring is that significant signal variability exists between individuals with a high falls risk and those with low risk. This variability increases the difficulty in building a universal system which segments and labels changes in signal state. This paper presents a method which uses unsupervised learning techniques to automatically segment a gait signal by computing the dissimilarity between two consecutive windows of data, applying an adaptive threshold algorithm to detect changes in signal state, and using a rule-based gait recognition algorithm to label the data. Using inertial data, the segmentation algorithm is compared against manually segmented data and is capable of achieving recognition rates greater than 71.8%.