Earticle

초록

영어

Modern technology is developing by leaps and bounds, and more and more people begin using wearable technology devices. Recently, users have been using this kind of devices such as Fitbit, Apple Watch and Samsung wrist trackers so as to keep track of their health data such as consumed calories, running miles and steps, and even sleeping time. Many users wear their devices nearly 24/7, providing a thorough weekly health analysis in the devices’ applications installed in their mobile phones. However, few people really use wearable devices to diagnose or identify common diseases which can be captured by the fluctuations or major changes in data captured by the devices. Hence, integrating with machine learning technology, we attempt to figure out a solution to detect and diagnose some diseases based on the daily health data collected by wearable devices. Aiming at this, we collected data and experimented using a classification-based machine learning method, namely Support Vector Machine, to simulate a verisimilar ambient to monitor certain users’ health conditions.

목차

Abstract
 1. Introduction
 2. Disease Diagnosis Based on Data Analysis of Wearable Devices
  2.1. Types of Health Data Captured by Wearable Devices
  2.2. Types of Disease to Be Diagnosed
  2.3. Introduction of SVM Classifier
 3. Experiments
  3.1. Division of Health Data
  3.2. Data Collection
  3.3. Modeling of SVM Classifier
  3.4. Experimental Results
 4. Conclusion
 References

키워드

저자

• Haolun Zhang [ Harbin No.3 High School, Harbin, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Advanced Science and Technology

• 간기

  월간

• pISSN

  2005-4238

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605