面向智能环境的活动模式迁移学习

汪成亮; 王云鹏

doi:10.13700/j.bh.1001-5965.2015.0085

面向智能环境的活动模式迁移学习

doi: 10.13700/j.bh.1001-5965.2015.0085

汪成亮^1,2, ,,
王云鹏¹

1.
重庆大学计算机学院, 重庆 400044
2. 重庆大学信息物理社会可信服务计算教育部重点实验室, 重庆 400044

基金项目: 国家自然科学基金(61004112);中央高校基本科研业务费专项资金(CDJZR12180006)

详细信息

作者简介:
汪成亮男,博士,教授。主要研究方向:无线传感网络、车联网和智能环境等。Tel.:023-65111874 E-mail:wangcl@cqu.edu.cn

通讯作者:
汪成亮,Tel.:023-65111874 E-mail:wangcl@cqu.edu.cn

中图分类号: TP393
计量
- 文章访问数: 739
- HTML全文浏览量: 49
- PDF下载量: 546
- 被引次数: 0
出版历程
- 收稿日期: 2015-02-06
- 网络出版日期: 2016-02-20

Transfer learning for activity pattern in smart environment

WANG Chengliang^{1,2
, ,},
WANG Yunpeng¹

1.
College of Computer Science, Chongqing University, Chongqing 400044, China
2. Key Laboratory of Dependable Service Computing in Cyber Physical Society, Ministry of Education, Chongqing University, Chongqing 400044, China

摘要

摘要: 针对智能环境中活动模式的学习和挖掘花销大、难以实际操作等问题,提出了能够有效地将已有活动模式迁移到新环境的整体框架。迁移学习框架将活动模式的迁移过程分解为轨迹的迁移和触发持续时间的迁移,首先对已有活动模式中的活动轨迹以及触发持续时间模糊化;然后采用备选轨迹生成(ATSG)算法在新环境中生成备选轨迹集;最后采用相似度计算(SC)算法进行活动模式中的轨迹与备选轨迹间的匹配,利用活动轨迹映射(TM)算法和触发持续时间迁移(TDT)算法对活动信息进行迁移,从而在新环境中得到活动模式。理论分析和实验结果表明,相比于基于频繁模式挖掘得到活动模式的方法,本文方法大幅度地降低了得到活动模式所需的时间开销,同时,利用本文方法获取的活动模式取得了较好的活动识别效果。
- 智能环境 /
- 迁移学习 /
- 活动模式 /
- 活动轨迹 /
- 触发持续时间
Abstract: Due to huge costs and operational difficulties in learning and mining activity patterns in smart environment, we propose a framework for activity pattern transfer. The process of activity pattern transfer is divided into two parts: trajectory transfer and trigger duration transfer. Firstly, fuzzify the trajectories and trigger durations in the existing activity patterns. Secondly, generate alternative trajectory set through alternative path set generation (ATSG) algorithm in a new environment. Finally, map the trajectories from activity patterns and trajectories from alternative trajectory set through similarity computing (SC) algorithm, and transfer activities' information through trajectory mapping (TM) algorithm and trigger duration transfer (TDT) algorithm. Thus, activity patterns are transferred to the new environment. Theoretical analysis and experimental results show that, compared to frequent pattern mining, the method in our paper can substantially reduce time overhead of obtaining activity patterns in new environment. At the same time, it performs well in recognizing activities.
- smart environment /
- transfer learning /
- activity pattern /
- activity trajectory /
- trigger duration

HTML全文

参考文献(15)

[1]	PARISA R,DIANE J C,LAWRENCE B H,et al.Discovering activities to recognize and track in a smart environment[J].IEEE Transactions on Knowledge and Data Engineering,2011,23(4):527-539.
[2]	FANG H Q,HU C.Recognizing human activity in smart home using deep learning algorithm[C]//201433rd Chinese Control Conference,CCC.Piscataway, NJ:IEEE Press, 2014:4716-4720.
[3]	KEVIN B,DANY F S,SEBASTIEN G,et al.Accurate RFID trilateration to learn and recognize spatial activities in smart environment[J].International Journal of Distributed Sensor Networks,2013,19(2):1-15.
[4]	ZHANG S,SALLY M,BRYAN S,et al.Using duration to learn activities of daily living in a smart home environment[C]//International Conference on Pervasive Computing Technologies for Healthcare.Piscataway,NJ:IEEE Press,2010:1-8.
[5]	WANG C L,ZHENG Q,PENG Y Y,et al.Distributed abnormal activity detection in smart environments[J].International Journal of Distributed Sensor Networks,2014,2014(3):1-15.
[6]	PAN S J L,YANG Q.A survey on transfer learning[J].IEEE Transactions on Knowledge and Data Engineering,2010,22(10):1345-1359.
[7]	BAYLOR W. Transfer learning in spatial reasoning puzzles[C]//IJCAI 2011-22nd International Joint Conference on Artificial Intelligence.California:International Joint Conference on Artificial Intelligence,2011:2864-2865.
[8]	HUANG P P,WANG G,QIN S Y.Boosting for transfer learning from multiple data sources[J].Pattern Recognition Letters,2012,33(5):568-579.
[9]	PARISA R,DIANE J C.Activity knowledge transfer in smart environment[J].Pervasive and Mobile Computing,2011,7(3):331-343.
[10]	HU D H,YANG Q.Transfer learning for recognition via sensor mapping[C]//IJCAI 2011-22nd International Joint Conference on Artificial Intelligence.California:International Joint Conference on Artificial Intelligence,2011:1962-1967.
[11]	FRANCISCO J O,GWENN E,PAULA D T,et al.In-home activity recognition:Bayesian inference for hidden Markov models[J].IEEE Pervasive Computing,2014,13(3):67-75.
[12]	WANG C L,DEBRAJ D,SONG W Z.Trajectory mining from anonymous binary motion sensors in smart environment[J].Knowledge-Based Systems,2013,37(2):346-356.
[13]	PROVOTAR A I,LAPKO A V,PROVOTAR A A.Fuzzy inference systems and their applications[J].Cyberbetics and Systems Analysis,2013,49(4):517-525.
[14]	THIERRY M.A Measurement-theoretic axiomatization of trapezoidal membership functions[J].IEEE Transactions on Fuzzy Systems,2007,15(2):238-242.
[15]	THOMAS H C,CHARLES E L,RONALD L R,et al.Introduction to algorithm[M].3rd ed.Cambridge,MA:Massachusetts Institute of Technology,2009:643-683.