Real-Time Monitoring System of Exercise Status Based on Internet of Health Things Using Safety Architecture Model

Long Qin,Yinming Xie

doi:10.1109/access.2021.3058247

Long Qin, Yinming Xie

Open Access

https://doi.org/10.1109/access.2021.3058247

Copy DOI

Abstract

As an emerging field of information technology, the Internet of Health Things has attracted great attention from governments, scholars, and related enterprises, and is seen as a major opportunity for development and change in the information field. The European Commission believes that the development and application of the Internet of Health Things will make a significant contribution to solving modern social problems in the next 5 to 15 years. In this paper, the corresponding motion detection algorithms such as pacing detection algorithm, sleep quality and sedentary reminder detection algorithm are designed for real-time detection of motion status. In addition, this paper builds a new safety architecture model based on real-time motion detection, and proposes a time-domain feature-based motion detection method for walking, walking upstairs and walking downstairs. The original acceleration signal is smoothed and denoised using a sliding-average filter. The acceleration signal is segmented by a rectangular window with 50% overlap, and the variance, X-quartile difference, and X-axis bias coefficient are extracted from a single time window.

Highlights

INTRODUCTIONThis article mainly studies motion detection algorithms, including exercise intensity classification and detection methods for three daily activities of walking, going upstairs and going downstairs; and designed and implemented software to monitor student exercise intensity, including wearable devices and transit base stations
The basic idea of the Internet of Health Things (IoHTs) emerged in the late 1990s and was first mentioned in 1999 in a networked radio frequency identification (RFID) system proposed by the Massachusetts Institute of Technology’s (MIT) Automatic Identification Center (Auto-K) [1]
The calculations of the algorithms proposed by the researchers are generally too large, and are not suitable for implementation on low-power wearable devices. These algorithms cannot quantitatively obtain the physical activity status of students, so it is necessary to study the motion detection algorithm to monitor the amount of exercise of students and detect the type of exercise, and comprehensively consider the calculation and calculation of the algorithm based on the algorithm research. the complexity

Summary

INTRODUCTION

This article mainly studies motion detection algorithms, including exercise intensity classification and detection methods for three daily activities of walking, going upstairs and going downstairs; and designed and implemented software to monitor student exercise intensity, including wearable devices and transit base stations. The calculations of the algorithms proposed by the researchers are generally too large, and are not suitable for implementation on low-power wearable devices These algorithms cannot quantitatively obtain the physical activity status of students, so it is necessary to study the motion detection algorithm to monitor the amount of exercise of students and detect the type of exercise, and comprehensively consider the calculation and calculation of the algorithm based on the algorithm research. If A(t) is the imaging of the same object in the video, is a smooth curve

EXTRACTION OF FEATURES

SYSTEM SECURITY ARCHITECTURE ANALYSIS

Findings

CONCLUSION