基于众包数据的室内定位方法和平台

doi:10.3724/SP.J.1047.2016.01476

地球信息科学学报 ›› 2016, Vol. 18 ›› Issue (11): 1476-1784.doi: 10.3724/SP.J.1047.2016.01476

基于众包数据的室内定位方法和平台

黄正宇^1,^2,³(), 陈益强^1,^2,^3,*^*(), 刘军发^2,³, 蒋鑫龙^2,^3,⁴, 胡春雨^2,^3,⁴

1. 湘潭大学信息工程学院,湘潭 411105
2. 中国科学院计算技术研究所,北京 100190
3. 北京市移动计算与新型终端重点实验室,北京 100190
4. 中国科学院大学,北京 100190

收稿日期:2016-07-25 修回日期:2016-09-29 出版日期:2016-11-20 发布日期:2016-11-20
作者简介:
作者简介：黄正宇(1991-),男,湖南岳阳人,硕士生,主要从事室内定位和信息检索方面研究。E-mail: huangzhengyu@ict.ac.cn
基金资助:
国家自然科学基金项目(61572004、61472399);中国科学院科研装备研制项目“面向可穿戴行为感知的精准模型测试仪研制”(YZ201527)

Indoor Localization Method and Platform Based on Crowdsourcing Data

HUANG Zhengyu^1,^2,³(), CHEN Yiqiang^1,^2,^3,^*(), LIU Junfa^2,³, JIANG Xinlong^2,^3,⁴, HU Chunyu^2,^3,⁴

1. College of Information Engineering, Xiangtan University, Xiangtan Hunan 411105, China
2. Institute of Computing Technology Chinese Academy of Sciences, Beijing 100190, China
3.Beijing Key Laboratory of Mobile Computing and Pervasive Device, Beijing 100190, China
4. University of Chinese Academy of Sciences, Beijing 100190, China

Received:2016-07-25 Revised:2016-09-29 Online:2016-11-20 Published:2016-11-20
Contact: CHEN Yiqiang

摘要/Abstract

摘要：

随着WLAN的普及,基于Wi-Fi的室内定位方法逐渐成为研究与应用的热点。虽然,其中基于位置指纹的定位算法研究相对广泛,应用效果较好,然而现有的指纹定位方法或系统仍存在以下3个问题：① 离线阶段的数据标定和定位模型的训练需要耗费大量人力物力,以及时间消耗,使系统很难得到实际应用;② 真实环境中WLAN信号波动呈现高动态性,采集的数据存在显著的时效性,无法提供长时间的有效定位保证;③ 实际环境中AP设备变动频繁,导致训练数据与定位数据特征维度不等长,造成模型失效。针对上述问题,本文提出了一种基于众包数据的模型更新方法,通过不断融合增量数据,使定位模型保持实时有效。该方法主要包括半监督极速学习机(SELM)、具有时效机制的增量式定位方法(TMELM)和特征自适应的在线极速学习机(FA-OSELM)3部分。基于上述方法,本文设计并实现了基于众包数据的室内定位平台系统。实际应用表明,本文提出的方法能够显著降低模型训练阶段的数据采集工作量,有效提升模型训练速度,并且长时间保持较高的定位精度。

关键词: 室内定位, 增量学习, 极速学习机, 特征自适应, 时效机制, 众包数据

Abstract:

As WLAN getting more and more popular and pervasive, Wi-Fi based indoor localization is becoming a hot issue in research and application fields. Among various kinds of up-to-date indoor localization methods, fingerprint based methods are most widely used because of the good performance. However, the existing fingerprint based methods still have following three common problems: Firstly, fingerprint based methods require a vast amount of calibration work, which need huge human and time consumption both in offline and online phases. It makes the systems difficult to be applied in the practical applications. Secondly, the Wi-Fi signals in the environment change frequently, bringing the significant timeliness in collected data. So it cannot guarantee to provide a long term effective localization. Thirdly, the Wi-Fi access points change frequently in real scene. Thus, the feature dimensions of training data and testing data are unequal. The traditional algorithms cannot well handle the feature dimension changing problem caused by increase or decrease in APs’ number. To solve these problems mentioned above, we proposed a crowdsourcing based indoor localization method, including Semi-supervised ELM, Timeliness Managing ELM and Feature Adaptive Online Sequential ELM. We also developed an indoor localization platform. Applications show that our method can reduce human effort in data calibration and improve the model training speed. Moreover, our method can maintain the high location accuracy for a long time.

Key words: indoor localization, incremental learning, extreme learning machine, feature adaptive, timeline managing, crowdsourcing data

黄正宇, 陈益强, 刘军发, 蒋鑫龙, 胡春雨. 基于众包数据的室内定位方法和平台[J]. 地球信息科学学报, 2016, 18(11): 1476-1784.DOI:10.3724/SP.J.1047.2016.01476

HUANG Zhengyu,CHEN Yiqiang,LIU Junfa,JIANG Xinlong,HU Chunyu. Indoor Localization Method and Platform Based on Crowdsourcing Data[J]. Journal of Geo-information Science, 2016, 18(11): 1476-1784.DOI:10.3724/SP.J.1047.2016.01476

图/表 7

图1

图2

图3

图4

图5

图6

图7

参考文献 21

[1]	Torteeka P, Chundi X I U. Indoor positioning based on wi-fi fingerprint technique using fuzzy k-nearest neighbor[C]. Applied Sciences and Technology (IBCAST), 2014 11th International Bhurban Conference on. IEEE, 2014:461-465.
[2]	Youssef M, Agrawala A.The Horus WLAN location determination system[C]. Proceedings of the 3rd international conference on Mobile systems, applications, and services. ACM, 2005:205-218.
[3]	Sjöberg M, Koskela M, Viitaniemi V, et al. Indoor location recognition using fusion of SVM-based visual classifiers[C]. Machine Learning for Signal Processing (MLSP), 2010 IEEE International Workshop on. IEEE, 2010:343-348.
[4]	Wu K, Xiao J, Yi Y, et al. Fila: Fine-grained indoor localization[C]. INFOCOM, 2012 Proceedings IEEE. IEEE, 2012:2210-2218.
[5]	Sen S, Radunovic B, Choudhury R R, et al. You are facing the Mona Lisa: spot localization using PHY layer information[C]. Proceedings of the 10th international conference on Mobile systems, applications, and services. ACM, 2012:183-196.
[6]	Fang S H, Lin T N.Principal component localization in indoor WLAN environments[J]. Mobile Computing, IEEE Transactions on, 2012,11(1):100-110. doi: 10.1109/TMC.2011.30
[7]	Zheng V W, Xiang E W, Yang Q, et al. Transferring Localization Models over Time[C]. AAAI. 2008:1421-1426.
[8]	Sun Z, Chen Y Q, Qi J, et al. Adaptive localization through transfer learning in indoor wi-fi environment[C]. Machine Learning and Applications, 2008. ICMLA'08. Seventh International Conference on. IEEE, 2008:331-336.
[9]	Liu J F, Chen Y Q, Liu M J, et al. SELM: semi-supervisedELM with application in sparse calibrated location estimation[J]. Neurocomputing, 2011,74(16):2566-2572. doi: 10.1016/j.neucom.2010.12.043
[10]	刘军发,谷洋,陈益强,等.具有时效机制的增量式无线定位方法[J].计算机学报,2013,36(7):1448-1455. doi: 10.3724/SP.J.1016.2013.01448
	[ Liu J F, Gu Y, Chen Y Q, et al. Incremental Localization in WLAN Environment with Timeliness Management[J]. Chinese Journal of Computers, 2013,36(7):1448-1455. ] doi: 10.3724/SP.J.1016.2013.01448
[11]	Jiang X L, Liu J F, Chen Y Q, et al. Feature adaptive online sequential extreme learning machine for lifelong indoor localization[J]. Neural Computing and Applications,2016,27(1):215-225.
[12]	Huang G B, Zhu Q Y, Siew C K.Extreme learning machine: a new learning scheme of feedforward neural networks[C]. Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on. IEEE, 2004,2:985-990.
[13]	Huang G B, Zhu Q Y, Siew C K.Extreme learning machine: theory and applications[J]. Neurocomputing, 2006,70(1):489-501. doi: 10.1016/j.neucom.2005.12.126
[14]	Huang G B, Chen L, Siew C K.Universal approximation using incremental constructive feedforward networks with random hidden nodes[J]. Neural Networks, IEEE Transactions on, 2006,17(4):879-892. doi: 10.1109/TNN.2006.875977 pmid: 16856652
[15]	Rao C R, Mitra S K.Generalized inverse of matrices and its applications[M]. New York: Wiley, 1971.
[16]	Serre D, Matrices: Theory and Applications[M]. New York: Springer, 2002.
[17]	Chung, F R.Spectral graph theory[C]. Vol. 92. American Mathematical Soc, 1997.
[18]	Belkin M, Matveeva I, Niyogi P.Regularization and semi-supervised learning on large graphs[C]. Proceedings of 17th Conference on Learning Theory(COLT), 2004,3120:624-638.
[19]	Belkin M, Niyogi P, Sindhwani V.Manifold regularization: A geometric framework for learning from labeled and unlabeled examples[J]. Journal of machine learning research, 2006,7(11):2399-434. doi: 10.1007/s10846-006-9077-x
[20]	Reddi S J, Sra S, Poczos B, et al. Fast Incremental Method for nonconvex optimization[J]. arxiv preprint arxiv:2016:1603.06159.
[21]	Ma R, Guo Q, Hu C, et al. An improved wi-fi indoor positioning algorithm by weighted fusion[J]. Sensors, 2015,15(9):1824-21843. doi: 10.3390/s150921824 pmid: 26334278

基于众包数据的室内定位方法和平台

Indoor Localization Method and Platform Based on Crowdsourcing Data

RichHTML

PDF (PC)

赞

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 21

相关文章 3

Metrics

本文评价

推荐阅读 0

[1]	左溪冰, 刘智, 金飞, 林雨准, 王淑香, 刘潇, 李美霖. 面向高光谱影像小样本分类的全局-局部特征自适应融合方法[J]. 地球信息科学学报, 2023, 25(8): 1699-1716.
[2]	承达瑜, 秦坤, 裴韬, 欧阳, 王蒙, 徐连明. 基于室内定位数据的群体时空行为可视化分析[J]. 地球信息科学学报, 2019, 21(1): 36-45.
[3]	刘涛, 张星, 李清泉, 方志祥, 李秋萍. 一种运动恢复结构和航位推算结合的室内行人视觉定位方法[J]. 地球信息科学学报, 2017, 19(6): 744-753.