Enhanced Pain Detection and Movement of Motion with Data Augmentation based on Deep Learning

Abstract

Pain is what anyone would experience, regardless of age or gender. Facial pain tracking technology is a successful tool since it is user-friendly with high precision. Auto pain monitoring benefits include that it will support patients and care professionals, including physicians and nurses. This paper suggests 2D facial expression and movement for pain perception with data augmentation utilizing deep learning approaches. We used approximately 50, 000 UNBC sequential photos in this study. Deep learning is applied to train data and activity approach to assist patient orientation. Our method can separate pain thresholds into three levels: painless, beginning to be painful, and painful. Our work is the standard method for detecting discomfort before heading to the hospital. It is easy, cost-effective, and readily grasped by the general public and healthcare professionals.