Motion Recognition of Smartphone User Using Hybrid Model Classifier

Title
Motion Recognition of Smartphone User Using Hybrid Model Classifier
Authors
신범주김철기김재헌이석이택진
Keywords
smartphone; motion recognition; hybrid model classifier
Issue Date
2013-06
Publisher
International Conference on Data Mining and Intelligent Information Technology Applications
Abstract
We present a motion recognition solution for a smartphone user. It is difficult to recognize a motion of smartphone user by using single classifier. To solve this problem, we apply a hybrid model classifier consisting of decision tree (DT), artificial neuron network (ANN), and support vector machine (SVM). We exploit simple features obtained from output of sensors for each classifier. To demonstrate a performance of proposed classifier, we conduct a real test and compare a performance of proposed classifier with those of other single classifiers. Experimental results present that the results of proposed classifier shows more accurate recognition rate than others.
URI
http://pubs.kist.re.kr/handle/201004/45193
Appears in Collections:
KIST Publication > Conference Paper
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE