Over the last decade, there has been a great effort to use technology to make exercise more interactive, measurable and gamified. However, in order to improve the accuracy of the detections and measurements needed, these efforts have always translated themselves into multiple sensors including purpose specific hardware, which results in extra expenses and induces limitations on the final mobility of the user. In this paper we aim to optimize a sensorless system that estimates the real-time user heartrate and performs better than the current wearable technology, for further calorie and other vital indicators calculations. The findings here will be applied on a posture correction system for a dance and fitness application.

Keywords : Sensorless heartrate estimation – Artificial Intelligence (A.I.) – Machine learning – Posenet – DenseNet – Real-time heartrate estimation – Heartrate at a distance– Dance – K-pop – E-sports – South Korea.