Classification of a known sequence of motions and postures from accelerometry data using adapted Gaussian mixture models

TLDR

Accelerometry offers an inexpensive, long‑term ambulatory monitoring option for elderly patients, and accurate classification of everyday movements can enhance system intelligence, improving fall detection and health tracking. The study aims to develop robust, flexible methods for classifying postures and motions from a single waist‑mounted triaxial accelerometer, with a focus on detecting short‑duration movements and adapting to individual users. Two classification approaches were examined: a rule‑based heuristic system and a Gaussian mixture model (GMM) system that incorporates a novel time‑domain feature extraction method and an adaptation technique to address limited user‑specific training data, evaluated during a three‑month field trial with six elderly subjects. The GMM system achieved 91.3 % accuracy across three postures and five movements, outperforming the heuristic system (71.1 %) and improving to 92.2 % with adaptation—a 20.2 % relative gain over non‑adapted tests and 4.5 % over limited subject data, indicating a significant step toward a more robust ambulatory classification system.

Abstract

Accelerometry shows promise in providing an inexpensive but effective means of long-term ambulatory monitoring of elderly patients. The accurate classification of everyday movements should allow such a monitoring system to exhibit greater 'intelligence', improving its ability to detect and predict falls by forming a more specific picture of the activities of a person and thereby allowing more accurate tracking of the health parameters associated with those activities. With this in mind, this study aims to develop more robust and effective methods for the classification of postures and motions from data obtained using a single, waist-mounted, triaxial accelerometer; in particular, aiming to improve the flexibility and generality of the monitoring system, making it better able to detect and identify short-duration movements and more adaptable to a specific person or device. Two movement classification methods were investigated: a rule-based Heuristic system and a Gaussian mixture model (GMM)-based system. A novel time-domain feature extraction method is proposed for the GMM system to allow better detection of short-duration movements. A method for adapting the GMMs to compensate for the problem of limited user-specific training data is also proposed and investigated. Classification performance was considered in relation to data gathered in an unsupervised, directed routine conducted in a three-month field trial involving six elderly subjects. The GMM system was found to achieve a mean accuracy of 91.3%, distinguishing between three postures (sitting, standing and lying) and five movements (sit-to-stand, stand-to-sit, lie-to-stand, stand-to-lie and walking), compared to 71.1% achieved by the Heuristic system. The adaptation method was found to offer a mean accuracy of 92.2%; a relative improvement of 20.2% over tests without subject-specific data and 4.5% over tests using only a limited amount of subject-specific data. While limited to a restricted subset of possible motions and postures, these results provide a significant step in the search for a more robust and accurate ambulatory classification system.