Journal
COMPUTER COMMUNICATIONS
Volume 150, Issue -, Pages 62-71Publisher
ELSEVIER
DOI: 10.1016/j.comcom.2019.11.008
Keywords
Wearable health monitoring; Human motion state recognition; Triaxial acceleration sensor
Ask authors/readers for more resources
The wearable health monitoring system is a typical application of wearable computing in the medical field. However, existing research often does not consider the characteristics of human physiological characteristics and exercise state in practical applications, and only judges the health of users from physiological data. The lack of information on the state of motion at that time caused a certain degree of misjudgment. For the coexistence of multiple types of devices and multiple transmission methods, this paper first proposes a wearable health monitoring system architecture based on human motion state recognition. Secondly, according to the characteristics of short-term persistence of daily activities of the human body, its motion state is divided into a steady state and an unstable state. The three-axis acceleration vector value is converted into the acceleration amplitude change amount, which eliminates the wearing correlation of the sensor coordinate system. Finally, we conducted a simulation experiment. The experimental results show that the algorithm achieves high accuracy in state recognition, and the recognition accuracy of running and walking is better than decision tree identification algorithm.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available