《计算机应用研究》|Application Research of Computers

基于可穿戴设备的无监督室内/室外场景探测方法

Unsupervised method for indoor/outdoor detection by wearable device in environmental sensing

免费全文下载 (已被下载 次)  
获取PDF全文
作者 周楠树,赵甦,王海洋
机构 1.上海交通大学 电子信息与电气工程学院 区域光纤通信网与新型光通信系统国家重点实验室,上海 200240;2.上海市电力公司信息通信公司,上海 200122
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2017)08-2258-06
DOI 10.3969/j.issn.1001-3695.2017.08.004
摘要 提出了一种基于多传感器可穿戴设备的无监督室内/室外场景的区分方法。首先,该方法对多维的传感数据进行时间序列建模,通过分析该时间序列挖掘出场景切换的模式并对该时序数列进行分段分析;接着,建立相似性测量模型对每个分段时间序列进行室内/室外场景相似度计算,根据计算的结果识别出室内/室外场景。通过实验分析,该方法对室内/室外场景区分准确度高达90.1%,相较于其他方法准确度提高了13%~33%。该方法无须对数据人工标记,实现了较高的场景区分准确率,适用于大规模数据采集场景。
关键词 室内/室外探测;可穿戴设备;场景切换模式;相似性测量
基金项目 国家自然科学基金资助项目(61371084)
国家电网公司科技资助项目(52090F160007)
本文URL http://www.arocmag.com/article/01-2017-08-004.html
英文标题 Unsupervised method for indoor/outdoor detection by wearable device in environmental sensing
作者英文名 Zhou Nanshu, Zhao Su, Wang Haiyang
机构英文名 1.StateKeyLaboratoryofAdvancedOpticalCommunicationSystems&Networks,SchoolofElectronicInformation&ElectricalEngineering,ShanghaiJiaoTongUniversity,Shanghai200240,China;2.Information&TelecommunicationCompany,ShanghaiMunicipalElectricPowerCompany,Shanghai200122,China
英文摘要 This paper presented an unsupervised method for indoor/outdoor (IO) detection in environmental sensing via wea-rable devices equipped with multiple sensors. Firstly, the method constructed the context model on multi-dimensional time series sensor data. And it captured the context switching patterns(CSP) from the perspective of local trends resulted from IO context switching. Secondly, it built a simple yet efficient model to measure the similarity between a multi-dimensional outdoor reference time series and the sensor data collected by the wearable devices. As a result, the data could be classified into indoor and outdoor categories by the proposed model. It validated this method in a real environment with the sensors. The result shows that the classification accuracy of the proposed method is about 90.1% which is 13%~33% better than other alternatives. The method doesn’t require manually labeled training datasets. It achieves classification with high precision during the large scale collection.
英文关键词 indoor/outdoor detection; wearable devices; context switching pattern; similarity measurement
参考文献 查看稿件参考文献
  [1] Giudice N A, Walton L A, Worboys M. The informatics of indoor and outdoor space:a research agenda[C] // Proc of the 2nd ACM SIGSPATIAL International Workshop on Indoor Spatial Awareness. New York:ACM Press, 2010:47-53.
[2] Marina M K, Radu V, Balampekos K. Impact of indoor-outdoor context on crowdsourcing based mobile coverage analysis[C] // Proc of the 5th Workshop on All Things Cellular:Operations, Applications and Challenges. New York:ACM Press, 2015:45-50.
[3] Yang Zheng, Shangguan Longfei, Gu Weixi, et al. Sherlock:micro-environment sensing for smartphones[J] . IEEE Trans on Parallel & Distributed Systems, 2014, 25(12):3295-3305.
[4] Flynn J I, Coe D P, Larsen C A, et al. Detecting indoor and outdoor environments using the ActiGraph GT3X+ light sensor in children[J] . Medicine & Science in Sports & Exercise, 2014, 46(1):201-206.
[5] Zhou Pengfei, Zheng Yuanqing, Li Zhenjiang, et al. IODetector:a generic service for indoor outdoor detection[C] //Proc of the 10th ACM Conference on Embedded Network Sensor Systems. New York:ACM Press, 2012:361-362.
[6] Zou Han, Jiang Han, Luo Yiwen, et al. BlueDetect:an iBeaconena-bled scheme for accurate and energy-efficient indoor-outdoor detection and seamless location-based service[J] . Sensors, 2016, 16(2):268.
[7] Anagnostopoulos G G, Deriaz M. Automatic switching between indoor and outdoor position providers[C] //Proc of International Conference on Indoor Positioning and Indoor Navigation. 2015.
[8] Conte G, De Marchi M, Nacci A A, et al. BlueSentinel:a first approach using iBeacon for an energy efficient occupancy detection system[C] //Proc of the 1st ACM International Conference on Embedded Systems for Energy-Efficient Buildings. New York:ACM Press, 2015:1009-1013.
[9] Wang He, Sen S, Elgohary A, et al. No need to war-drive:unsupervised indoor localization[C] //Proc of the 10th International Confe-rence on Mobile Systems, Applications, and Services. New York:ACM Press, 2012:197-210.
[10] Chintalapudi K, Padmanabha I A, Padmanabhan V N. Indoor localization without the pain[C] //Proc of the 16th International Confe-rence on Mobile Computing and Networking. New York:ACM Press, 2010:173-184.
[11] Ravindranath L, Newport C, Balakrishnan H, et al. Improving wireless network performance using sensor hints[C] //Proc of the 8th USENIX Conference on Networked Systems Design and Implementation. Berkeley:USENIX Association, 2011:281-294.
[12] Edelev S, Prasad S N, Karnal H, et al. Knowledge-assisted location-adaptive technique for indoor-outdoor detection in e-learning[C] //Proc of IEEE International Conference on Pervasive Computing and Communication. 2015.
[13] Radu V, Katsikouli P, Sarkar R, et al. A semi-supervised learning approach for robust indoor-outdoor detection with smartphones[C] //Proc of the 12th ACM Conference on Embedded Network Sensor Systems. New York:ACM Press, 2014:280-294.
[14] Pour G M, Troped P J, Evans J J. Environment feature extraction and classification for context aware physical activity monitoring[C] //Proc of Sensors Applications Symposium. 2013:123-128.
[15] Nguyen J L, Schwartz J, Dockery D W. The relationship between indoor and outdoor temperature, apparent temperature, relative humidity, and absolute humidity[J] . Indoor Air, 2014, 24(1):103-112.
[16] Jin Ming, Zou Han, Weekly K, et al. Environmental sensing by wearable device for indoor activity and location estimation[C] //Proc of Industrial Electronics Society Conference. 2014:5369-5375.
[17] 詹艳艳, 徐荣聪, 陈晓云, 等. 基于斜率提取边缘点的时间序列分段线性表示方法[J] . 计算机科学, 2006, 33(11):139-142.
[18] MacQueen J. Some methods for classification and analysis of multivariate observations[C] //Proc of Berkeley Symposium on Mathematical Statistics and Probability. 1967:281-297.
[19] Shi Jianbo, Malik J. Normalized cuts and image segmentation[J] . IEEE Trans on Pattern Analysis and Machine Intelligence, 1997, 22(8):888-905.
收稿日期 2016/10/15
修回日期 2016/11/28
页码 2258-2263
中图分类号 TP391.4
文献标志码 A