Prediction framework for upper body sedentary working behaviour by using deep learning and machine learning techniques

Public health experts and healthcare professionals are gradually identifying sedentary activity as a population-wide, pervasive health risk. The purpose of this paper is to propose a method to identify the changes in posture during sedentary work and to give feedback by analysing the identified posture of the upper body, i.e. hands, shoulder, and head positioning. After capturing the image of the human pose, pre-processing of the image takes place with a bandpass filter, which helps to reduce the noise and morphological operation, which is used to carry out the process of dilation, erosion and opening of an image. To predict the results easily with the use of texture feature extraction, it helps to extract the image’s feature. Then, accuracy is predicted by using the deep neural network techniques, to predict the result accurately. After prediction and analysis, the feedback system is developed to alert individuals through the alarm system. The proposed method is formulated by using DNN for prediction in the MATLAB software tool. The results show accuracy, sensitivity and specificity of the prediction using a deep neural network are 97.2%, 88.7% and 99.1%. The proposed method is compared with the existing methods SVM, Random Forest and KNN algorithms. The accuracy, sensitivity and specificity of the existing algorithms are SVM with 77.6%, 57.4 and 97.8%; Random Forest with 80.6%, 63.7% and 97.5%; and KNN with 65.8%, 61.2%, and 95.1%. This concept helps to prevent the impact of sedentary activity on fatal and non-fatal cardiovascular and musculoskeletal diseases, respectively.