基于流形插值數(shù)據(jù)庫構建的WLAN室內(nèi)定位算法

周牧; 唐云霞; 田增山; 衛(wèi)亞聰

doi:10.11999/JEIT161269

基于流形插值數(shù)據(jù)庫構建的WLAN室內(nèi)定位算法

doi: 10.11999/JEIT161269 cstr: 32379.14.JEIT161269

2.
(重慶郵電大學移動通信技術重慶市重點實驗室重慶 400065) ②(天津師范大學天津市無線移動通信與無線電能傳輸重點實驗室天津 300387)

基金項目:

國家自然科學基金(61301126)，長江學者和創(chuàng)新團隊發(fā)展計劃(IRT1299)，重慶市科委重點實驗室專項經(jīng)費，重慶郵電大學青年科學研究項目(A2013-31)

計量
- 文章訪問數(shù): 1579
- HTML全文瀏覽量: 231
- PDF下載量: 395
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-11-24
- 修回日期: 2017-03-20
- 刊出日期: 2017-08-19

WLAN Indoor Localization Algorithm Based on Manifold Interpolation Database Construction

2.
(Chongqing Key Laboratory of Mobile Communication Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China)

Funds:

The National Natural Science Foundation of China (61301126), The Program for Changjiang Scholars and Innovative Research Team in University (IRT1299), The Special Fund of Chongqing Key Laboratory (CSTC), Young Scientific Research Program of CUPT (A2013-31)

摘要

摘要: 針對傳統(tǒng)無線局域網(wǎng)(WLAN)室內(nèi)定位系統(tǒng)中因參考點密集分布及逐點信號采集所帶來的位置指紋數(shù)據(jù)庫構建工作量繁重的問題，該文提出一種基于混合半監(jiān)督流形學習和3次樣條插值的數(shù)據(jù)庫構建方法。該方法利用少量標記數(shù)據(jù)和大量未標記數(shù)據(jù)求解定位目標函數(shù)的最優(yōu)解，同時根據(jù)高維信號強度空間與低維物理位置空間的映射關系，實現(xiàn)對未標記數(shù)據(jù)的位置標定。大量實驗結果表明，該方法能夠在保證較高定位精度的同時，顯著降低位置指紋數(shù)據(jù)庫的構建開銷。
- 無線局域網(wǎng) /
- 位置指紋 /
- 半監(jiān)督學習 /
- 流形對齊 /
- 3次樣條插值
Abstract: To deal with the high cost involved in the location fingerprint database construction due to the dense Reference Points (RPs) distribution and point-by-point Received Signal Strength (RSS) collection in the conventional Wireless Local Area Network (WLAN) indoor localization systems, a new database construction approach based on the integrated semi-supervised manifold learning and cubic spline interpolation is proposed. The proposed approach utilizes a small amount of labeled data and a massive amount of unlabeled data to find the optimal solution to localization target function, and meanwhile relies on the mapping relations between the high-dimensional signal strength space and low-dimensional physical location space to calibrate the unlabeled data with location coordinates. The extensive experiments demonstrate that the proposed approach is able to guarantee the high localization accuracy, as well as significantly reduce the cost involved in location fingerprint database construction.
- Wireless Local Area Network (WLAN) /
- Location fingerprint /
- Semi-supervised learning /
- Manifold alignment /
- Cubic spline interpolation

HTML全文

參考文獻(26)

KASHIF A, TAYYAB J, HOSSAM S H, et al. Non-audible acoustic communication and its application in indoor location-based services[C]. IEEE Wireless Communications and Networking Conference, Doha, Qatar, 2016: 1-6.

周牧, 蒲巧林, 田增山. 室內(nèi)WLAN定位中位置指紋優(yōu)化的接入點部署方法[J]. 通信學報, 2015, 36(Z1): 30-41. doi: 10.11959/j.issn.1000-436x.2015279.

ZHOU Mu, PU Qiaolin, and TIAN Zengshan. Location fingerprint optimization based access point deployment in indoor WLAN localization[J]. Journal on Communications, 2015, 36(Z1): 30-41. doi: 10.11959/j.issn.1000-436x.2015279.

陳兵, 楊小玲. 一種基于概率密度的WLAN接入點定位的算法[J]. 電子與信息學報, 2015, 37(4): 855-862. doi: 10.11999/ JEIT140661.

CHEN Bing and YANG Xiaoling. A WLAN access point localization algorithm based on probability density[J]. Journal of Electronics Information Technology, 2015, 37(4): 855-862. doi: 10.11999/JEIT140661.

HE Jie, LI Shen, PAHLAVAN Kaveh, et al. A realtime testbed for performance evaluation of indoor TOA location system[C]. IEEE International Conference on Communications, Ottawa, Canada, 2012: 482-486.

TAPONECCO L, AMICO A D, and MENGALI U. Joint TOA and AOA estimation for UWB localization applications [J]. IEEE Transactions on Wireless Communications, 2011, 10(7): 2207-2217. doi: 10.1109/TWC.2011.042211.100966.

ZHANG Liye, MA Lin, and XU Yubin. A semi-supervised indoor localization method based on l1-graph algorithm[J]. Journal of Harbin Institute of Technology (New Series), 2015, 22(4): 55-61.

OUYANG R, WONG A, LEA C, et al. Indoor location estimation with reduced calibration exploiting unlabeled data via hybrid generative/discriminative learning[J]. IEEE Transactions on Mobile Computing, 2011, 11(11): 1613-1626. doi: 10.1109/TMC.2011.193.

PAN J J, PAN S J, YIN J, et al. Tracking mobile users in wireless networks via semi-supervised colocalization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(3): 587-600. doi: 10.1109/TPAMI.2011.165.

勵晶晶, 郭文. 兩類錯誤條件下的樣本容量選擇[J]. 統(tǒng)計與決策, 2010, (15): 14-18.

LI Jingjing and GUO Wen. Select the sample size under two types of error conditions[J]. Statistics and Decision, 2010, (15): 14-18.

賈俊平. 統(tǒng)計學[M]. 北京. 中國人民大學出版社. 2011: 220-224.

JIA Junping. Statistics[M]. Beijing, China Renmin University Press, 2011: 220-224.

彭小輝, 晏政, 李艷軍, 等. 一種基于解析冗余關系的半定性故障隔離方法在航天器推進系統(tǒng)中的應用[J]. 國防科技大學學報. 2012, 34(6): 104-110. doi: 10.3969/j.issn.1001-2486. 2012.06.018.

PENG Xiaohui, YAN Zheng, LI Yanjun, et al. A semi- qualitative fault isolation method based on analytical redundancy relations for spacecraft propulsion system[J]. Journal of National University of Defense Technology, 2012, 34(6): 104-110. doi: 10.3969/j.issn.1001-2486.2012.06.018.

陳家琪, 嚴梓乘. 一種Newton插值的RFID室內(nèi)定位改進算法[J]. 計算機系統(tǒng)應用, 2012, (1): 45-48. doi: 10.3969/j.issn. 1003-3254.2012.01.010.

CHEN Jiaqi and YAN Zicheng. Improvement algorithm of Newton interpolation for RFID indoor positioning[J]. Computer Systems Applications, 2012, (1): 45-48. doi: 10. 3969/j.issn.1003-3254.2012.01.010.

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.

SHI Lei, ZHANG Lefei, ZHAO Lingli, et al. Adaptive Laplacian eigenmap-based dimension reduction for ocean target discrimination[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(7): 902-906. doi: 10.1109/LGRS. 2016.2553046.

ZHANG Yanming, HUANG Kaizhu, HOU Xinwen, et al. Learning locality preserving graph from data[J]. IEEE Transactions on Cybernetics, 2014, 44(11): 2088-2098. doi: 10.1109/TCYB.2014.2300489.

曾孝平, 劉刈, 劉國金. 基于圖譜理論和隨機游走核的圖像去噪[J]. 通信學報. 2010, 31(7): 116-121. doi: 10.3969/j.issn. 1000-436X.2010.07.017.

ZENG Xiaoping, LIU Yi, and LIU Guojin. Image denoising based on spectral graph theory and random walk kernel[J]. Journal on Communications, 2010, 31(7): 116-121. doi: 10.3969/j.issn.1000-436X. 2010. 07.017.

金珠. 改進的支持向量機分類算法及其在煤礦人因事故安全評價中的應用[D]. [博士論文], 中國礦業(yè)大學, 2011, 81-89.

JIN Zhu. Improved support vector machine classification algorithm and application for human factors of coal mine accidents safety evaluation[D]. [Ph.D. dissertation], China University of Mining, 2011, 81-89.

RENAN S, PASCAL D C, RICHARD P, et al. Human step detection from a piezoelectric polymer floor sensor using normalization algorithms[C]. IEEE Sensors 2014, Valencia, Spain, 2014: 1169-1172.

施引文獻

資源附件(0)

訪問統(tǒng)計