Application of Machine Learning Approaches for Classifying Sitting Posture Based on Force and Acceleration Sensors

Abstract

Occupational musculoskeletal disorders, particularly chronic low back pain (LBP), are ubiquitous due to prolonged static sitting or nonergonomic sitting positions. Therefore, the aim of this study was to develop an instrumented chair with force and acceleration sensors to determine the accuracy of automatically identifying the user's sitting position by applying five different machine learning methods (Support Vector Machines, Multinomial Regression, Boosting, Neural Networks, and Random Forest). Forty-one subjects were requested to sit four times in seven different prescribed sitting positions (total 1148 samples). Sixteen force sensor values and the backrest angle were used as the explanatory variables (features) for the classification. The different classification methods were compared by means of a Leave-One-Out cross-validation approach. The best performance was achieved using the Random Forest classification algorithm, producing a mean classification accuracy of 90.9% for subjects with which the algorithm was not familiar. The classification accuracy varied between 81% and 98% for the seven different sitting positions. The present study showed the possibility of accurately classifying different sitting positions by means of the introduced instrumented office chair combined with machine learning analyses. The use of such novel approaches for the accurate assessment of chair usage could offer insights into the relationships between sitting position, sitting behaviour, and the occurrence of musculoskeletal disorders.

Activity Level Assessment Using a Smart Cushion for People with a Sedentary Lifestyle

“…Barba et al [ 27 ] used 16 pressure sensors (8 on the seat and 8 on the backrest) connected to an Arduino board to develop an on-line posture recognition system to monitor users’ affective states, such as boredom, attention and nervousness, during learning scenarios. Zemp et al [ 28 ] developed an instrumented chair with force and acceleration sensors to identify the user’s sitting postures using machine learning methods. Sixteen force sensor values and the backrest angle (determined by the accelerometer fixed on the backrest) were used as the features for the classification.…”

Sensing and Changing Human Behavior for Workplace Wellness

“…As one way to sense the physical state sensing, we introduce the development of a posture sensing chair that can continuously measure an employee's posture while working. Although there * 12 https://jins-meme.com/en/ are related studies that used a depth camera [39], [40] and a motion sensor attached to a person [41], or pressure sensors installed on the seat surface [42], [43], [44], [45], [46], [47], it is difficult to take measurements during long periods without disturbing the work or reducing the comfort of the chair. Therefore, we proposed a method to estimate the posture from the deflection of the chair by attaching the acceleration sensors to the back of the seat surfaces [48].…”

The Influence of Different Levels of Cognitive Engagement on the Seated Postural Sway

“…Among the available solutions, a state-of-the-art solution is that of equipping chairs with sensors able to collect data on the posture of the user [18][19][20][21]: Ishac et al in [18] presented a cushion to be used in the backrest of the chair. The cushion is equipped with a pressure sensing array that allows the measurement of the pressure at 9 different points.…”

“…Zemp et al in [19] used an innovative approach based on machine learning to classify the data collected by 16 pressure sensors located on different parts of a chair (armrest, seat and backrest). While allowing an improved posture classification, the computational complexity of this algorithm is quite high.…”