Sung Ji Hoon, Choi Sun Tak, Lee Joo Young, We-Duke Cho

KIPS Transactions on Computer and Communication Systems, Vol. 8, No. 4, pp. 93-102, Apr. 2019
https://doi.org/10.3745/KTCCS.2019.8.4.93,   PDF Download:
Keywords: wearable device, Exercise Detection, Physiological Principal, Physiological Signal, Activity recognition
Abstract

As interest in wellness grows, There is a lot of research about monitoring individual health using wearable devices. Accordingly, a variety of methods have been studied to distinguish exercise from daily activities using wearable devices. Most of these existing studies are machine learning methods. However, there are problems with over-fitting on individual person’s learning, data discontinuously recognition by independent segmenting and fake activity. This paper suggests a detection method for exercise activity based on the physiological response principle of heart rate up and down during exercise. This proposed method calculates activity intensity and heart rate from triaxial and photoplethysmography sensor to determine a heart rate recovery, then detects exercise by estimating activity intensity or detecting a heart rate rising state. Experimental results show that our proposed algorithm has 98.64% of averaged accuracy, 98.05% of averaged precision and 98.62% of averaged recall.

Statistics
Cite this article