Post on 15-Jan-2016
description
Posture Recognition with
G-Sensors on Smart Phones
2012 15th International Conference on Network-Based Information Systems
Professor: Yih-Ran SheuStudent : Chan-jung WU
Hui-Huang Hsu , Kang-Chun TsaiDept of Computer Science and Information Engineering Tamkang
University
Zixue Cheng, Tongjun HuangSchool of Computer Science and Engineering University of Aizu
Digital Object Identifier :10.1109/NBiS.2012.135Date of Conference: 26-28 Sept. 2012Page(s):588 - 591
Abstract Introduction Posture Recognition App Experimental Results and Implementation Conclusion and Future Work References
Outline
Using smart phone to recognize the posture of the user. The app can record the postures of the user for the whole day and estimate the burned calories accordingly.
Abstract
Weight control is a major issue in health management since overweighting is a very serious social problem in developed countries
Introduction 1/3
Use the signals from G-sensor in the mobile phone to identify the postures of the user
Introduction 2/3
Introduction 3/3
System architecture
Example posture signals
Posture Recognition App 1/3
Artificial Neural Networks(ANN)
Posture Recognition App 2/3
sampling period of 0.04seconds
Artificial Neural Networks
Posture Recognition App 2/3
Posture Recognition App 2/3
摩托車
腳踏車
開車
搭車
Hidden note
It is basically the weight (in Kg) of the user times the duration of the posture state (in hour) and a posture factor
Posture Recognition App 3/3
Calorie consumption
Experimental Results and Implementation 1/3
The sampling rate is 5 times per seconds. There are totally 20445 data points in the posture dataset
Experimental Results and Implementation 2/3
The overall classification accuracy is 97 percent
Experimental Results and Implementation 3/3
The user can be aware of his/her daily activities in a better way and possibly move more to enjoy a healthier life.
The user’s activity signals are collected and used to train a personalized neural network model for posture classification. This should be able to make the classification accuracy nearly perfect.
Conclusion and Future Work
[1]http://www.airitilibrary.com/Publication/alDetailedMesh?docid=16086961 -200812-200907210037-200907210037-286-298[2] http://developer.android.com/about/index.html[3] http://developer.android.com/tools/sdk/eclipse-adt.html[4] http://www.csie.nctu.edu.tw/~kensl/AIrpt.html[5] http://developer.android.com/guide/components/index.html
REFERENCES