Sitting Posture Prediction and Correction System using Arduino-Based Chair and Deep Learning Model

Abstract

In this paper, we propose a system that applies deep learning to classify different postures of the users of our specially designed chair composed of Arduino hardware. The system provides users with information of their real-time posture and analytics for a given period of time, hence users can figure out their sitting habits. Moreover, the system suggests guidance videos of stretching body parts that help the users to correct their sitting postures.