中图分类号：TP391.4         文献标识码：A         文章编号：2096-4706（2020）05-0147-05

Intelligent Spatial Behavior Recognition Method Based on Mutation Detection

ZANG Yuanyuan¹，WANG Shouxin¹，TONG Meizhu²，WANG Jianxing³

（1.Aerospace ShenZhou Smart System Technology Co.，Ltd.，Beijing 100029，China； 2.Beijing Jiaotong University Beijing 100029，China；3.China National Aviation Fuel Group Limited Beijing 100088，China）

Abstract：Behavior recognition based on non embedded sensor data is very important for home equipment control and abnormal behavior monitoring. It is a research hotspot of behavior recognition in intelligent space environment. It is not only conducive to privacy protection but also can accumulate data for a long time to meet individual behavior preferences. Aiming at the problem of identifying behavior boundary in sensor data sequence and improving the effect of online behavior recognition in turn，based on the idea of behavior mutation detection to identify the similarity degree of continuous behavior，KL diver-gence is used to realize mutation detection，and genetic algorithm is used to automatically set the threshold of mutation detection. Using RF，QSVM，weighted KNN （wKNN）and DT algorithm to verify the time-domain feature of mutation point can effectively improve the ability of online behavior recognition，which proves the effectiveness of this method.

Keywords：smart home；non-invasive sensor；online activity recognition；change point detection；threshold automation

参考文献：

[1] ALAM MR，REAZ MBI，ALI MAM. A Review of Smart Homes-Past，Present，and Future [J]. Systems，Man，and Cybernetics，Part C：Applications and Reviews，IEEE Transactions on，2012，42（6）：1190-1203.

[2] FINDEISEN M，MEINEL L，RICHTER J，et al. An omnidirectional stereo sen-sor for human behavior analysis in complex indoor environments [C].2015 IEEE International Conference on Consumer Electronics （ICCE），Las Vegas，NV，USA，2015：17-19.

[3] GEORGE D，BRIAN K. H，MARJORIE S，et al. Senior residents’ perceived need of and preferences for “smart home”sensor technologies [J]. Interna-tional Journal of Technology Assessment in Health Care，2008，24（1）：120-124.

[4] CHO M，KIM Y，LEE Y H. Contextual Relationship-based Activity Segmenta-tion on an Event Stream in the IoT Environment with Multi-user Activities [C]. Proceedings of the 3rd Workshop on Middleware for Context-Aware Applications in the IoTDecember，2016：7-12.

[5] AMINIKHANGHAHI S，COOK D J. Using Change Point Detection to Automate Daily Activity Segmentation [C].13th Workshop on Context and Activity Modeling and Recognition. IEEE，2017.

[6] KRISHNAN N C，COOK D J. Activity recognition on streaming sensor data [J]. Pervasive and Mobile Computing，2014（10）Part B：138-154.

[7] ZHANG Q，KARUNANITHI M，BRADFORD D，et al. Activity of Daily Living as-sessment through wireless sensor data [C].Engineering in Medicine and Biology Society （EMBC），2014 36th Annual International Conference of the IEEE. S.l.：s.n.，2014：1752-1755.

[8] YATBAZ H Y，ERASLAN S，YESILADA Y，et al. Activity Recognition Using Binary Sensors for Elderly People Living Alone：Scanpath Trend Analysis Ap-proach [J].IEEE Sensors Journa，2019，19（17）：7575-7582.

[9] HONDA Y，YAMAGUCHI H，HIGASHINO T. Daily Activity Recognition based on Markov Logic Network for Elderly Monitoring [C].2019 16th IEEE Annual Consumer Communications & Networking Conference（CCNC），Las Vegas，NV，USA，2019：1-6.

[10] MINOR B，COOK D J. Regression tree classification for activity predic-tion in smarthomes [C].2014 ACM International Joint Conference on Pervasive and Ubiquitous Computing，New York，USA ，2014：441-450.

[11] RAEISZADEH M，TAHAYORI H. A novel method for detecting and predicting resident’s behavior in smart home [C].IEEE 2018 6th Iranian Joint Congress on Fuzzy and Intelligent Systems（CFIS），Kerman，2018：71-74.