Posture detection using Deep Learning for Time Series Data

Health problems due to poor posture is becoming increasingly common among every age group in today's time. Sedentary workstyle, lack of physical exercise, unsupported or unbalanced sitting conditions are some of the factors that cause posture-related problems. The correct or inappropriate posture of the human body can be detected using a wearable sensor system, as discussed in this paper. In this work, three tri-axial accelerometers placed at the back of the subject were used to classify nine different postures in sitting and standing positions. A novel combined deep learning model consisting of a fully convolutional network (FCN) and long short-term model (LSTM) is proposed for posture classification. Experimental results show that combined FCN-LSTM network yields the highest average classification accuracy of 99.91%, whereas the individual FCN and LSTM networks yield classification accuracies of 97.88% and 88.47%, respectively. The models are also compared in terms of complexity and execution time.