卫星定位终端入栏检测算法的研究与实现

朱江淼; 张 菁; 黄艳; 金森林; 高春柳

doi:10.3969/j.issn.1000-1158.2019.06.28

PDF(837 KB)

计量学报 ›› 2019, Vol. 40 ›› Issue (6) : 1112-1116. DOI: 10.3969/j.issn.1000-1158.2019.06.28

无线电、时间频率计量

卫星定位终端入栏检测算法的研究与实现

朱江淼¹,张菁¹,黄艳²,金森林²,高春柳²

作者信息 +

Research and Implementation on Algorithm for Entry Fence Detection of Satellite Positioning Terminal

ZHU Jiang-miao¹,ZHANG Jing¹,HUANG Yan²,JIN Sen-lin²,GAO Chun-liu²

Author information +

文章历史 +

摘要

载有卫星定位的设备终端是否在设定范围内的检测方法,决定着电子围栏设计的成败。将分类思想用于此类检测,提出一种基于支持向量机的入栏检测算法。该算法依据卫星定位终端的定位数据特征选择合适的核函数;通过网格搜索法求取核函数及误差惩罚参数的值;视检测准确率高低不断调整确定最优阈值等几个环节来实现。用实测数据进行算法验证,入栏检测准确率可达80%～96%,远高于直接检测得到的43%～67% 的准确率,表明算法可靠有效,具有较高的实用价值。

Abstract

The algorithm for detecting whether an equipment terminal with satellite positioning is within the set range or not deserves attention, which is the decisive factor in the design of an electronic fence. An algorithm for entry fence detection based on support vector machine using classification method was proposed. The algorithm mainly consists of three parts: selecting an appropriate kernel function according to the location data of the satellite positioning terminal; calculating the values of kernel function and error penalty parameters through grid searching technique; adjusting threshold value until the detection accuracy is highest. The validity of the algorithm was demonstrated using experimental data from satellite positioning terminals. The detection accuracy rate is estimated to be 80%～96%, which is much higher than the accuracy of 43%～67% obtained by direct detection. The result embodied high practical value for the society.

导出引用

朱江淼,张菁,黄艳,金森林,高春柳. 卫星定位终端入栏检测算法的研究与实现[J]. 计量学报. 2019, 40(6): 1112-1116 https://doi.org/10.3969/j.issn.1000-1158.2019.06.28

ZHU Jiang-miao,ZHANG Jing,HUANG Yan,JIN Sen-lin,GAO Chun-liu. Research and Implementation on Algorithm for Entry Fence Detection of Satellite Positioning Terminal[J]. Acta Metrologica Sinica. 2019, 40(6): 1112-1116 https://doi.org/10.3969/j.issn.1000-1158.2019.06.28

中图分类号： TB939

参考文献

［1］Jordan M I, Mitchell T M. Machine learning: Trends, perspectives, and prospects.［J］. Science, 2015, 349(6245): 255-260.
［2］何清, 李宁, 罗文娟,等. 大数据下的机器学习算法综述［J］. 模式识别与人工智能, 2014, 27(4): 327-336.
He Q, Ling N, Luo W J, et al. Survey of machine learning algorithms under big data［J］. Pattern Recognition and Artificial Intelligence, 2014, 27(4): 327-336.
［3］Li X, Ge M, Dai X, et al. Accuracy and reliability of multi-GNSS real-time precise positioning: GPS, GLONASS, BeiDou, and Galileo［J］. Journal of Geodesy, 2015, 89(6):607-635.
［4］周健, 毛刚, 赵李健,等. BD2/GPS四频高精度接收机在远望号船姿测量中的应用［J］. 测绘科学技术学报, 2012, 29(3): 171-174.
Zhou J, Mao G, Zhao L J, et al. Application of BD2/GPS four frequency high precision receiver in ship attitude measurement of Yuan Wang［J］. Journal of Surveying and Mapping Science and Technology, 2012, 29(3): 171-174.
［5］张继海, 广伟, 袁海波, 等. 北斗测距信号评估与精密单点定位应用研究［J］. 仪器仪表学报, 2017, 38(11): 2707-2714.
Zhang J H, Guang W, Yuan H B, et al.Study on range signal evaluation and precise point positioning application of Beidou navigation satellite system (BDS)［J］. Chinese Journal of Scientific Instrument, 2017, 38 (11): 2707-2714.
［6］王昱洁, 王媛, 张勇. 基于KFCM-LMC-LSSVM算法的WLAN室内定位方法［J］. 计量学报, 2018, 39(4): 554-558.
Wang Y J, Wang Y, Zhang Y. Indoor Positioning Algorithm for WLAN Based on KFCM-LMC-LSSVM［J］.Acta Metrologica Sinica, 2018, 39(4): 554-558.
［7］姚英彪, 毛伟勇, 姚瑞丽, 等. 基于改进支持向量回归的室内定位算法［J］. 仪器仪表学报, 2017, 38(9): 2112-2119.
Yao Y B, Mao W Y, Yao R L, et al. Indoor positioning algorithm based on improved support vector regression［J］. Chinese Journal of Scientific Instrument, 2017, 38(9):2112-2119.
［8］吴哲君, 赵忠华, 唐雷. 基于SVM的行人步态实时分类方法［J］. 电子测量技术, 2015, 38(7): 41-44.
Wu Z J, Zhao Z H, Tang L. SVM based method for real time classification of pedestrian gait［J］. Electronic Measurement Technology, 2015, 38(7): 41-44.
［9］程淑红,高许,周斌. 基于多特征提取和SVM参数优化的车型识别［J］. 计量学报, 2018, 39(3): 348-352.
Cheng S H, Gao X, Zhou B. Vehicle Recognition Based on Multi-feature Extraction
and SVM Parameter Optimization［J］.Acta Metrologica Sinica, 2018, 39(3): 348-352.
［10］Han S J,Cao Q B,Han M. Parameter selection in SVM with RBF kernel function［C］// World Automation Congress 2012,IEEE, 2012:1-4.
［11］陈超波, 杨楠. RBF神经网络算法在动态称重中的应用［J］. 电子测量技术, 2016, 39(5): 187-190.
Chen C B, Yang N. Application of RBF neural network algorithm in dynamic weighing［J］. Electronic Measurement Technology, 2016, 39(5):187-190.
［12］孙国强, 樊新海, 石文雷. 基于MFCC和支持向量机的装甲车辆识别研究［J］. 国外电子测量技术, 2017, 36(10): 31-35.
Sun G Q, Fan X H, Shi W L. Research on armored vehicle classification based on MFCC and SVM［J］. Foreign Electronic Measurement Technology, 2017, 36(10): 31-35.
［13］方雷, 张华鑫, 姚申君. 一种基于面积修改简单多边形的算法［J］. 华东师范大学学报, 2011, (2): 77-88.
Fang L, Zhang H X, Yao S J. An algorithm based on area modification of simple polygon ［J］. Journal of East China Normal University, 2011, (2): 77-88.