Paper Info
Title
Irun: A Smartphone-Based System To Alert Runners To Warm Up Before Running
Abstract
Running is a good way to keep healthy and relax, while many runners suffer from injuries because of a lack of running knowledge and ignoring the importance of warm-up. Inspired by the fact that more and more people run with smartphones tied up to their arms, we propose a novel system named iRun to alert people to warm up before running. iRun is based on the sensors built in most off-the-shelf smartphones like accelerometers, and it uses human activity recognition (HAR) methods to detect whether the runners warm up or not. The most challenging work is to choose the features that can represent the characteristic of various warm-up actions because different people have different exercise habits. By carefully designing the feature vector which contains features from multi-domains and doing a series of experiments to decide the slide window size and classifier, iRun can achieve 91.4% true positive (TP) rate in average to distinguish every warm-up action from other movements like running, walk, going upstairs, etc.
Year
DOI
Venue
2016
10.1007/978-3-319-42836-9_17
WIRELESS ALGORITHMS, SYSTEMS, AND APPLICATIONS, WASA 2016
Keywords
Field
DocType
Human activity recognition, Health, Machine learning, Smartphone sensing
Feature vector,Activity recognition,Computer science,Accelerometer,Computer network,Artificial intelligence,Classifier (linguistics),Machine learning
Conference
Volume
ISSN
Citations 
9798
0302-9743
0
PageRank 
References 
Authors
0.34
11
6
Name
Order
Citations
PageRank
Zhenhua Zhao160.80
Zehao Sun2194.07
Liusheng Huang31082123.52
Hansong Guo4143.39
Jianxin Wang52163283.94
Hongli Xu650285.92