基于接收信號(hào)強(qiáng)度非齊性分布特征的半監(jiān)督學(xué)習(xí)室內(nèi)定位指紋庫構(gòu)建

李世寶; 王升志; 劉建航; 黃庭培; 張?chǎng)?/>
	<meta name=

doi:10.11999/JEIT180599

基于接收信號(hào)強(qiáng)度非齊性分布特征的半監(jiān)督學(xué)習(xí)室內(nèi)定位指紋庫構(gòu)建

doi: 10.11999/JEIT180599

中國(guó)石油大學(xué)(華東)計(jì)算機(jī)與通信工程學(xué)院青島 ??266580

基金項(xiàng)目: 國(guó)家自然科學(xué)基金(61972417, 61601519, 61872385)，中央高校基本科研業(yè)務(wù)費(fèi)專項(xiàng)資金(18CX02134A, 18CX02137A, 18CX02133A,19CX05003A-4)

詳細(xì)信息

作者簡(jiǎn)介:
李世寶：男，1978年生，副教授，研究方向?yàn)橐苿?dòng)計(jì)算、無線傳感器網(wǎng)絡(luò)、干擾對(duì)齊等

王升志：男，1994年生，碩士生，研究方向?yàn)闊o線定位技術(shù)

劉建航：男，1978年生，副教授、博士，研究方向?yàn)闊o線局域網(wǎng)、車聯(lián)網(wǎng)

黃庭培：女，1980年生，講師、博士，研究方向?yàn)闊o線傳感器網(wǎng)絡(luò)

張?chǎng)危耗校?993年生，碩士生，研究方向?yàn)闊o線定位技術(shù)

通訊作者:
李世寶　lishibao@upc.edu.cn

中圖分類號(hào): TN929.5
計(jì)量
- 文章訪問數(shù): 3340
- HTML全文瀏覽量: 924
- PDF下載量: 89
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2018-06-20
- 修回日期: 2019-02-28
- 網(wǎng)絡(luò)出版日期: 2019-03-30
- 刊出日期: 2019-10-01

Semi-supervised Indoor Fingerprint Database Construction Method Based on the Nonhomogeneous Distribution Characteristic of Received Signal Strength

College of Computer and Communication Engineering, China University of Petroleum (East China), Qingdao 266580, China

Funds: The National Natural Science Foundation of China (61972417, 61601519, 61872385), The Fundamental Research Funds for the Central Universities (18CX02134A, 18CX02137A, 18CX02133A, 19CX05003A-4)

摘要

摘要: 室內(nèi)定位中半監(jiān)督學(xué)習(xí)的指紋庫構(gòu)建方法能夠降低人力開銷，但忽略了高維接收信號(hào)強(qiáng)度(RSS)數(shù)據(jù)不均勻的非齊分布特點(diǎn)，影響定位精度，針對(duì)此問題該文提出一種基于RSS非齊性分布特征的半監(jiān)督流形對(duì)齊指紋庫構(gòu)建方法。該算法運(yùn)用局部RSS尺度參數(shù)以及共享近鄰相似性構(gòu)造權(quán)重矩陣，得到精確反映RSS數(shù)據(jù)流形結(jié)構(gòu)的權(quán)重圖，利用該權(quán)重圖通過求解流形對(duì)齊的目標(biāo)函數(shù)最優(yōu)解，實(shí)現(xiàn)運(yùn)用少量標(biāo)記數(shù)據(jù)對(duì)大量未標(biāo)記數(shù)據(jù)的位置標(biāo)定。實(shí)驗(yàn)結(jié)果表明，該算法可以顯著降低離線階段數(shù)據(jù)采集的工作量，同時(shí)可以取得較高的定位精度。
- 無線局域網(wǎng) /
- 室內(nèi)指紋定位 /
- 半監(jiān)督流形對(duì)齊 /
- 非齊性分布 /
- 指紋庫構(gòu)建
Abstract: The radio map construction is time consuming and labor intensive, and the conventional semi-supervised based methods usually ignore the influence of the uneven distribution of high-dimensional Received Signal Strength (RSS). In order to solve that problem, a semi-supervised radio map construction approach which is based on the nonhomogeneous distribution characteristic of RSS is proposed. The approach utilizes the RSS local scale and common neighbors similarities to calculate the weighted matrix. Thus, the weighted graph that reflects accurately the structure of RSS data manifold is presented. In addition, the weighted graph is used to find the optimal solution of the objective function to calibrate the locations of plenty of unlabeled data by a small number of labeled RSS. The extensive experiments demonstrate that the proposed method is capable of not only constructing an accurate radio map at a low manual cost, but also achieving a high localization accuracy.
- Wireless Local Area Network (WLAN) /
- Indoor fingerprinting localization /
- Semi-supervised manifold alignment /
- Nonhomogeneous distribution /
- Radio map construction

HTML全文

圖 1 RSS非齊性分布示意圖

下載: 全尺寸圖片幻燈片

圖 2 3個(gè)數(shù)據(jù)集RSS數(shù)據(jù)疏密分布

下載: 全尺寸圖片幻燈片

圖 3 TUT數(shù)據(jù)集各參考點(diǎn)RSS疏密程度

下載: 全尺寸圖片幻燈片

圖 4 3個(gè)房間的RSS數(shù)據(jù)在LDA下2維空間分布

下載: 全尺寸圖片幻燈片

圖 5 算法示意圖

下載: 全尺寸圖片幻燈片

圖 6 實(shí)驗(yàn)環(huán)境平面圖

下載: 全尺寸圖片幻燈片

圖 7 不同算法定位性能

下載: 全尺寸圖片幻燈片

圖 8 不同比例指紋數(shù)下的定位精度下降比率

下載: 全尺寸圖片幻燈片

圖 9 不同算法構(gòu)建指紋庫時(shí)間消耗

下載: 全尺寸圖片幻燈片

圖 10 AP個(gè)數(shù)對(duì)定位精度的影響

下載: 全尺寸圖片幻燈片

圖 11 共同近鄰相似性中鄰居數(shù)對(duì)定位性能影響

下載: 全尺寸圖片幻燈片

參考文獻(xiàn)(19)

MELAMED R. Indoor localization: Challenges and opportunities[C]. 2016 IEEE/ACM International Conference on Mobile Software Engineering and Systems, Austin, USA, 2016: 1–2.

徐玉濱, 鄧志安, 馬琳. 基于核直接判別分析和支持向量回歸的WLAN室內(nèi)定位算法[J]. 電子與信息學(xué)報(bào), 2011, 33(4): 896–901. doi: 10.3724/SP.J.1146.2010.00813

XU Yubin, DENG Zhian, and MA Lin. WLAN indoor positioning algorithm based on KDDA and SVR[J]. Journal of Electronics &Information Technology, 2011, 33(4): 896–901. doi: 10.3724/SP.J.1146.2010.00813

KHALAJMEHRABADI A, GATSIS N, and AKOPIAN D. Modern WLAN fingerprinting indoor positioning methods and deployment challenges[J]. IEEE Communications Surveys & Tutorials, 2017, 19(3): 1974–2002. doi: 10.1109/COMST.2017.2671454

JI Yiming, BIAZ S, PANDEY S, et al. ARIADNE: A dynamic indoor signal map construction and localization system[C]. The 4th International Conference on Mobile Systems, Applications and Services, Uppsala, Sweden, 2006: 151–164.

OUYANG R W, WONG K K S, LEA C T, et al. Indoor location estimation with reduced calibration exploiting unlabeled data via hybrid generative/discriminative learning[J]. IEEE Transactions on Mobile Computing, 2012, 11(11): 1613–1626. doi: 10.1109/TMC.2011.193

SOROUR S, LOSTANLEN Y, VALAEE S, et al. Joint indoor localization and radio map construction with limited deployment load[J]. IEEE Transactions on Mobile Computing, 2015, 14(5): 1031–1043. doi: 10.1109/TMC.2014.2343636

ZHOU Mu, TANG Yunxia, TIAN Zengshan, et al. Semi-supervised learning for indoor hybrid fingerprint database calibration with low effort[J]. IEEE Access, 2017, 5: 4388–4400. doi: 10.1109/ACCESS.2017.2678603

WANG Jin, TAN N, LUO Jun, et al. WOLoc: WiFi-only outdoor localization using crowdsensed hotspot labels[C]. IEEE Conference on Computer Communications, Atlanta, GA, USA, 2017: 1–9.

CHAPELLE O and ZIEN A. Semi-supervised classification by low density separation[C]. The Tenth International Workshop on Artificial Intelligence and Statistics, Bridgetown, Barbados, 2005: 57–64.

STEVENS J R, RESMINI R G, and MESSINGER D W. Spectral-density-based graph construction techniques for hyperspectral image analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2017, 55(10): 5966–5983. doi: 10.1109/TGRS.2017.2718547

ZHU Manli and MARTINEZ A M. Pruning noisy bases in discriminant analysis[J]. IEEE Transactions on Neural Networks, 2008, 19(1): 148–157. doi: 10.1109/TNN.2007.904040

RODRIGUEZ A and LAIO A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191): 1492–1496. doi: 10.1126/science.1242072

LOHAN E S, TORRES-SOSPEDRA J, LEPP?KOSKI H, et al. Wi-Fi crowdsourced fingerprinting dataset for indoor positioning[J]. Data, 2017, 2(4): 32. doi: 10.3390/data2040032

TORRES-SOSPEDRA J, MONTOLIU R, MARTíNEZ-USó A, et al. UJIIndoorLoc: A new multi-building and multi-floor database for WLAN fingerprint-based indoor localization problems[C]. 2014 International Conference on Indoor Positioning and Indoor Navigation, Busan, South Korea, 2014: 261–270.

ZELNIK-MANOR L and PERONA P. Self-tuning spectral clustering[C]. Advances in Neural Information Processing Systems, Vancouver, British Columbia, Canada, 2005: 1601–1608.

TORRES-SOSPEDRA J, MONTOLIU R, TRILLES S, et al. Comprehensive analysis of distance and similarity measures for Wi-Fi fingerprinting indoor positioning systems[J]. Expert Systems with Applications, 2015, 42(23): 9263–9278. doi: 10.1016/j.eswa.2015.08.013

BELKIN M and NIYOGI P. Laplacian eigenmaps for dimensionality reduction and data representation[J]. Neural Computation, 2003, 15(6): 1373–1396. doi: 10.1162/089976603321780317

HAM J, LEE D D and SAUL L K. Semisupervised alignment of manifolds[C]. The Tenth International Workshop on Artificial Intelligence and Statistics, Bridgetown, Barbados, 2005: 120–127.

BAHL P and PADMANABHAN V N. RADAR: An in-building RF-based user location and tracking system[C]. The Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies, Tel Aviv, Israel, 2000, 2: 775–784.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計(jì)