Fall Detection by Using K-Nearest Neighbor Algorithm on WSN Data

被引:8
作者
Erdogan, Senol Zafer [1 ]
Bilgin, Turgay Tugay [1 ]
Cho, Juphil [2 ]
机构
[1] Maltepe Univ, Fac Engn, Istanbul, Turkey
[2] Kunsan Natl Univ, Coll Engn, Jeollabuk Do, South Korea
来源
2010 IEEE GLOBECOM WORKSHOPS | 2010年
关键词
Wireless sensor networks; fall detection; data mining; KNN algorithm;
D O I
10.1109/GLOCOMW.2010.5700306
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Falls are serious problem especially for elderly people. Day by day the elderly people are living alone and the children of these people want to get information in dangerous situations. With the alarm systems, someone in difficulty can be detected and emergency aid can be sent. We propose a system to detect falls by using a data mining approach on WSN data. The proposed system evaluated using data stream collected from sensor device and fall detection accuracy and precision are calculated. Our solution demonstrated promising results on WSN data stream.
引用
收藏
页码:2054 / 2058
页数:5
相关论文
共 14 条
[1]  
[Anonymous], 1991, Nearest neighbor (NN) norms: NN pattern classification techniques
[2]  
[Anonymous], IGI GLOBAL
[3]  
[Anonymous], 2006, IEEE T INFORM TECHNO
[4]  
[Anonymous], 29 ANN INT C IEEE EM
[5]  
[Anonymous], INTRO DATA MINING CO
[6]  
DAELEMANS W, 1993, LECT NOTES COMPUTER
[7]   Maintaining stream statistics over sliding windows [J].
Datar, M ;
Gionis, A ;
Indyk, P ;
Motwani, R .
SIAM JOURNAL ON COMPUTING, 2002, 31 (06) :1794-1813
[8]  
JIANG LX, 2005, LECT NOTES COMPUTER, V3584
[9]  
Levis P., 2006, TINYOS PROGRAMMING
[10]  
LI Q, 2009, SN 09 P 2009 6 INT W