Combining ontological and temporal formalisms for composite activity modelling and recognition in smart homes

被引:56
作者
Okeyo, George [1 ]
Chen, Liming [2 ]
Wang, Hui [3 ]
机构
[1] Jomo Kenyatta Univ Agr & Technol, Sch Comp & Informat Technol, Juja, Kenya
[2] De Montfort Univ, Sch Comp Sci & Informat, Leicester LE1 9BH, Leics, England
[3] Univ Ulster, Sch Comp & Math, Coleraine BT52 1SA, Londonderry, North Ireland
来源
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE | 2014年 / 39卷
关键词
Composite activities; Interleaved activities; Concurrent activities; Activity recognition; Activity modelling; Ontologies; Smart homes; CONCURRENT ACTIVITIES; OWL;
D O I
10.1016/j.future.2014.02.014
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Activity recognition is essential in providing activity assistance for users in smart homes. While significant progress has been made for single-user single-activity recognition, it still remains a challenge to carry out real-time progressive composite activity recognition. This paper introduces a hybrid ontological and temporal approach to composite activity modelling and recognition by extending existing ontology-based knowledge-driven approach. The compelling feature of the approach is that it combines ontological and temporal knowledge representation formalisms to provide powerful representation capabilities for activity modelling. The paper describes in detail ontological activity modelling which establishes relationships between activities and their involved entities, and temporal activity modelling which defines relationships between constituent activities of a composite activity. As an essential part of the model, the paper also presents methods for developing temporal entailment rules to support the interpretation and inference of composite activities. In addition, this paper outlines an integrated architecture for composite activity recognition and elaborated a unified activity recognition algorithm which can support the recognition of simple and composite activities. The approach has been implemented in a feature-rich prototype system upon which testing and evaluation have been conducted. Initial experimental results have shown average recognition accuracy of 100% and 88.26% for simple and composite activities, respectively. (C) 2014 Elsevier B.V. All rights reserved.
引用
收藏
页码:29 / 43
页数:15
相关论文
共 54 条
[1]   MAINTAINING KNOWLEDGE ABOUT TEMPORAL INTERVALS [J].
ALLEN, JF .
COMMUNICATIONS OF THE ACM, 1983, 26 (11) :832-843
[2]  
Augusto JC, 2004, FRONT ARTIF INTEL AP, V110, P778
[3]  
Baader F, 2008, FOUND ARTIF INTELL, P135, DOI 10.1016/S1574-6526(07)03003-9
[4]  
Bartos A., 2010, CESK NEUROLOGIE NEUR, V73
[5]  
Batsakis S, 2011, LECT NOTES COMPUT SC, V6881, P558, DOI 10.1007/978-3-642-23851-2_57
[6]  
Batsakis S, 2011, LECT NOTES COMPUT SC, V6826, P242, DOI 10.1007/978-3-642-22546-8_19
[7]  
Bellifemine F., 2001, Proceedings of the Fifth International Conference on Autonomous Agents, P216, DOI 10.1145/375735.376120
[8]  
Bouchard B, 2006, J COMPUT, V1, P53
[9]  
Bucks R.S., 2002, EXPERT REV NEUROTHER, V2
[10]  
Bucks R.S., 1996, AGE AGEING, V25