基于SVR-Kriging插值的矿井工人二维指纹定位数据库构建算法

王红军; 周宇; 王伦文

doi:10.11999/JEIT170058

基于SVR-Kriging插值的矿井工人二维指纹定位数据库构建算法

doi: 10.11999/JEIT170058

基金项目:

国家自然科学基金(61273302)

计量
- 文章访问数: 1349
- HTML全文浏览量: 124
- PDF下载量: 212
- 被引次数: 0
出版历程
- 收稿日期: 2017-01-16
- 修回日期: 2017-04-12
- 刊出日期: 2017-11-19

Establishment Algorithm of Two Dimensional Fingerprint Database for Mine Workers Based on SVR-Kriging Interpolation

Funds:

The National Natural Science Foundation of China (61273302)

摘要

摘要: 为突破矿井工人指纹定位中1维模型在定位精度上的局限性，该文提出一种矿井工人2维指纹定位数据库构建算法，并通过SVR-Kriging插值法解决因2维模型带来的数据采集工作量大的问题。首先，通过高斯滤波对采集的采样点位置指纹信息进行预处理，并利用支持向量回归由采样点数据拟合变异函数。然后采用Kriging插值法补全2维网格划分中的未采样区域的位置指纹信息。最后综合采样点与插值点的位置指纹信息建立矿井工人指纹信息数据库，为后续矿井工人指纹定位奠定基础。仿真结果表明，该文算法在减少数据采集工作量的同时保证了算法的可行性与有效性，且在进行位置指纹定位时能够保证较高的精度。
- 矿井工人定位 /
- 高斯滤波 /
- 变异函数 /
- 支持向量回归 /
- Kriging插值
Abstract: In order to overcome the limitation of one-dimensional model in accuracy of mine workers fingerprint location, a two-dimensional fingerprint location database algorithm for mine workers is proposed. The problem of the large data acquisition workload brought by the two-dimensional model is also solved by SVR-Kriging interpolation. Firstly, Gaussian filtering is used to preprocess the fingerprint information of the collected sampling point and the variation function is fitted by the Support Vector Regression (SVR). Then, the Kriging interpolation is used to complete the position fingerprint information of the un-sampled area in the two-dimensional meshing. Finally, the fingerprint location database of the mine workers is established by integrating the location fingerprint information of the sampling points and the interpolation points, laying the foundation for the follow-up mine workers fingerprint location. The simulation results show that the proposed algorithm can reduce the workload of data acquisition while ensuring the feasibility and the effectiveness of the algorithm and can guarantee high accuracy when positioning is performed through the location fingerprint.
- Mine positioning /
- Gauss filter /
- Variogram /
- Support Vector Regression (SVR) /
- Kriging interpolation

HTML全文

参考文献(27)

胡青松, 张申, 吴立新, 等. 矿井动目标定位: 挑战、现状与趋势[J]. 煤炭学报, 2016, 41(5): 1059-1068. doi: 10.13225/ j.cnki.jccs.2015.1267.

HU Qingsong, ZHANG Shen, WU Lixin, et al. Localization techniques of mobile objects in coal mines: Challenges, solutions and trends[J]. Journal of China Coal Society, 2016, 41(5): 1059-1068. doi: 10.13225/j.cnki.jccs.2015.1267.

WANG Jie, GAO Qinghua, YU Yan, et al. Toward robust indoor localization based on Bayesian filter using chrip-spread-spectrum ranging[J]. IEEE Transactions on Industrial Electronics, 2012, 59(3): 1622-1629. doi: 10.1109/TIE.2011.2165462.

WANG Jie, GAO Qinghua, PAN Miao, et al. Toward accurate device-free wireless localization with a saddle surface model[J]. IEEE Transactions on Vehicular Technology, 2016, 65(8): 6665-6677. doi: 10.1109/TVT.2015.2476495.

ERRINGTON A F C, DAKU B L F, and PRUGGER A F. Initial position estimation using RFID tags: A least-squares approach[J]. IEEE Transactions on Instrumentation and Measurement, 2010, 59(11): 2863-2869. doi: 10.1109/TIM. 2010.2046366.

YU Gu and REN Fuji. Energy-efficient indoor localization of smart hand-held devices using Bluetooth[J]. IEEE Access, 2015, 3: 1450-1461. doi: 10.1109/ACCESS.2015.2441694.

WEI Jiaxi, CHEN Yan, and SUN Shuo. An improved TDOA algorithm applied person localization system in coal mine[C]. 2011 Third International Conference on Measuring Technology and Mechatronics Automation, Shanghai, 2011, 1: 428-431. doi: 10.1109/ICMTMA.2011.108.

郝丽娜, 张秀均, 郁万里, 等. 基于RSS手指模的煤矿井下WLAN定位方法[J]. 传感器与微系统, 2012, 31(9): 46-49. doi: 10.13873/j.1000-97872012.09.020.

HAO Lina, ZHANG Xiujun, YU Wanli, et al. Underground coal mine WLAN localization algorithm based on RSS fingerprinting[J]. Transducer and Microsystem Technologies, 2012, 31(9): 46-49. doi: 10.13873/j.1000-97872012.09.020.

GUO Jiateng, JIANG Jizhou, WU Lixin, et al. 3D modeling for mine roadway from laser scanning point cloud[C]. 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Beijing, 2016: 4452-4455. doi: 10.1109/IGARSS.2016.7730160.

王桃. 基于位置指纹的煤矿井下定位算法研究[D]. [硕士论文], 中国矿业大学, 2015: 29-39.

WANG Tao. Research of positioning algorithm in coal mine based on location fingerprint[D]. [Master dissertation], China University of Mining Technology, 2015: 29-39.

JIANG Qideng, MA Yongtao, LIU Kaihua, et al. A probabilistic radio map construction scheme for crowdsourcing-based fingerprinting localization[J]. IEEE Sensors Journal, 2016, 16(10): 3764-3774. doi: 10.1109/JSEN. 2016.2535250.

彭玉旭, 杨艳红. 一种基于RSSI的贝叶斯室内定位算法[J]. 计算机工程, 2012, 38(10): 237-240. doi: 10.3969/j.issn. 1000-3428.2012.10.073.

PENG Yuxu and YANG Yanhong. Bayesian indoor location algorithm based on RSSI[J]. Computer Engineering, 2012, 38(10): 237-240. doi: 10.3969/j.issn.1000-3428.2012.10.073.

XIAO Song, ROTARU M, and SYKULSKI J K. Adaptive weighted expected improvement with rewards approach in kriging assisted electromagnetic design[J]. IEEE Transactions on Magnetics, 2013, 49(5): 2057-2060. doi: 10.1109/TMGA.2013.2240662.

ZIMOS E, TOUMPAKARIS D, MUNTEANU A, et al. Multiterminal source coding with copula regression for wireless sensor networks gathering diverse data[J]. IEEE Sensors Journal, 2017, 17(1): 139-150. doi: 10.1109/JSEN. 2016.2585042.

WU Qiang and ZHOU Dingxuan. SVM soft margin classifiers: Linear programming versus quadratic programming[J]. Neural Computation, 2005, 17(5): 1160-1187. doi: 10.1162/ 0899766053491896.

TAKAHASHI N, GUO J, and NISHI T. Global convergence of SMO algorithm for support vector regression[J]. IEEE Transactions on Neural Networks, 2008, 19(6): 971-982. doi: 10.1109/TNN.2007.915116.

SHAMSHIRBAND S, PETKOVIC D, JAVIDNIA H, et al. Sensor data fusion by support vector regression methodologyA comparative study[J]. IEEE Sensors Journal, 2015, 15(2): 850-854. doi: 10.1109/JSEN.2014. 2356501.

李明山, 王正明, 张仪. 基于均匀试验设计的支持向量回归参数选择方法[J]. 系统仿真学报, 2008, 20(8): 2195-2199. doi: 10.16182/j.cnki.joss.2008.08.067.

LI Mingshan, WANG Zhengming, and ZHANG Yi. New method for selecting parameters of support vector machine regression based on uniform design[J]. Journal of System Simulation, 2008, 20(8): 2195-2199. doi: 10.16182/j.cnki. joss.2008.08.067.

何飞, 方金云. 基于自适应的并行空间插值算法及仿真实现[J]. 系统仿真学报, 2014, 26(4): 761-768. doi: 10.16182/j.cnki. joss.2014.04.030.

HE Fei and FANG Jinyun. Algorithm for spatial interpolation based on self-adaptive parallel programming[J]. Journal of System Simulation, 2014, 26(4): 761-768. doi: 10.16182/j.cnki.joss.2014.04.030.

陈丽, 陈静, 高清涛, 等. 基于支持向量机与反K近邻的分类算法研究[J]. 计算机工程与应用, 2010, 46(24): 135-137.

CHEN Li, CHEN Jing, GAO Qingtao, et al. Classification algorithm research based on support vector machine and reverse K-nearest neighbor[J]. Computer Engineering and Applications, 2010, 46(24): 135-137.

NI L M, LIU Y, LAN Y C, et al. LANDMARC: Indoor location sensing using active RFID[J]. Wireless Networks, 2004, 10(6): 701-710. doi: 10.1023/B:WINE.0000044029. 06344.DD.

施引文献

资源附件(0)

访问统计