Position Matters: Sensor Placement for Sitting Posture Classification

Prolonged sitting behavior and postures that cause strain on the spine and muscles have been reported to increase the probability of low back pain. To address this issue, many commercially available sensors already provide feedback about whether a person is 'slouching' or 'not slouching'. However, they do not provide information on a person's posture, which would give insights into the strain caused by a specific posture. Hence, in this pilot study, we attempt to find the optimum number of inertial measurement unit sensors required and the best locations to place them using six mock postures. Data is collected from these sensors and features are extracted. The number of features are reduced and the best features are selected using the Recursive Feature Elimination method with Cross-Validation. The reduced number of features is then trained and tested on Logistic Regression, Support Vector Machine and Hierarchical Model. Among the three models, the Support Vector Machine algorithm had the highest accuracy of 93.68%, obtained for the thoracic, hip and sacral region sensor combinations. While these findings will be validated in a larger study in an uncontrolled environment, this pilot study quantitatively highlights the importance of sensor placement in shaping discriminative performance in sitting posture classification tasks.