Activity recognition using semi-Markov models on real world smart home datasets

被引:89
作者
van Kasteren, T. L. M. [1 ]
Englebienne, G. [1 ]
Krose, B. J. A. [1 ]
机构
[1] Intelligent Syst Lab Amsterdam, NL-1098 XG Amsterdam, Netherlands
关键词
Duration modelling; semi-Markov conditional random fields; hidden semi-Markov model; human activity recognition;
D O I
10.3233/AIS-2010-0070
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Accurately recognizing human activities from sensor data recorded in a smart home setting is a challenging task. Typically, probabilistic models such as the hidden Markov model (HMM) or conditional random fields (CRF) are used to map the observed sensor data onto the hidden activity states. A weakness of these models, however, is that the type of distribution used to model state durations is fixed. Hidden semi-Markov models (HSMM) and semi-Markov conditional random fields (SMCRF) model duration explicitly, allowing state durations to be modelled accurately. In this paper we compare the recognition performance of these models on multiple fully annotated real world datasets consisting of several weeks of data. In our experiments the HSMM consistently outperforms the HMM, showing that accurate duration modelling can result in a significant increase in recognition performance. SMCRFs only slightly outperform CRFs, showing that CRFs are more robust in dealing with violations of the modelling assumptions. The datasets used in our experiments are made available to the community to allow further experimentation.
引用
收藏
页码:311 / 325
页数:15
相关论文
共 29 条
[1]  
Abowd G., 2002, P AAAI WORKSH AUT CA
[2]  
[Anonymous], UBICOMP 08, DOI DOI 10.1145/1409635.1409637
[3]  
[Anonymous], 2002, THESIS U EDINBURGH
[4]  
[Anonymous], THESIS CARNEGIE MELL
[5]  
[Anonymous], INTRO CONDIONAL RAND
[6]  
[Anonymous], 2006, Pattern recognition and machine learning
[7]  
[Anonymous], PERVASIVE
[8]  
AUGUSTO JC, 2006, LECT NOTES COMPUTER, V4008
[9]  
Cook D., 2004, Smart Environments: Technology, Protocols and Applications
[10]   Efficient duration and hierarchical modeling for human activity recognition [J].
Duong, Thi ;
Phung, Dinh ;
Bui, Hung ;
Venkatesh, Svetha .
ARTIFICIAL INTELLIGENCE, 2009, 173 (7-8) :830-856