Human activity recognition in big data smart home context

被引：0
作者：
Azzi, Sabrina [1 ]
Dallaire, Cindy [1 ]
Bouzouane, Abdenour [1 ]
Bouchard, Bruno [1 ]
Giroux, Sylvain [2 ]
机构：
[1] Univ Quebec Chicoutimi, Dept Math & Comp Sci, Chicoutimi, PQ, Canada
[2] Univ Sherbrooke, Dept Math & Comp Sci, Sherbrooke, PQ, Canada
来源：
2014 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA) | 2014年
关键词：
Big data; smart home; data mining; activity recognition;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In smart homes, a few millions of data are sent by different sensors and RFID per day. It thus constitutes a Big Data warehouse with all the problems that come from and in our work, we are interested in the problem of managing huge data in streaming. In this paper, we propose to use very fast decision tree(VFDT) for activity recognition. We formulate Activity Recognition as a classification problem where classes correspond to activities. The performance of the VFDT and other classifiers is compared.
引用
收藏
页数：8
相关论文
共 38 条
  • [1] ALBERT B, 2010, J MACHINE LEARNING R, V11, P44
  • [2] Andrew C., 1996, DR DOBBS J
  • [3] [Anonymous], 2014, C4. 5: programs for machine learning
  • [4] [Anonymous], 2001, P WORKSH EMP METH AR
  • [5] [Anonymous], 1979, Expert syst microelectron age
  • [6] [Anonymous], 2005, AAAI
  • [7] BERND H, 2001, FACE RECOGNITION SUP, P688
  • [8] BILL G, 2012, UNLOCKING VALUE FRAG
  • [9] A tutorial on Support Vector Machines for pattern recognition
    Burges, CJC
    [J]. DATA MINING AND KNOWLEDGE DISCOVERY, 1998, 2 (02) : 121 - 167
  • [10] Measuring daily behavior using ambulatory accelerometry: The activity monitor
    Bussmann, JBJ
    Martens, WLJ
    Tulen, JHM
    Schasfoort, FC
    van den Berg-Emons, HJG
    Stam, HJ
    [J]. BEHAVIOR RESEARCH METHODS INSTRUMENTS & COMPUTERS, 2001, 33 (03): : 349 - 356
1234