Indoor fingerprint localization method based on FDE-IRF
-
摘要: 针对传统指纹库存在建立工作量大以及随机森林匹配误差大等问题，提出了一种基于指纹库自动扩充的改进随机森林指纹定位方法(FDE-IRF)以提升指纹库构建的效率和指纹匹配的精度. 该方法对传统全采样构建指纹库方法和随机森林回归定位方法进行改进，稀疏采样多时间段的指纹数据和Kriging插值方法组合补全未采样指纹点，提升建库效率，得到强代表性的指纹库. 同时，利用决策树加权策略改进传统随机森林平均投票的方式，根据袋外数据评估决策树的预测误差，分配相应的权重，提高该算法的回归准确率. 实验结果表明：该方法的平均定位误差为1.26 m，其误差值比同类方法至少降低14.3%，验证了算法的准确性和有效性.Abstract: Aiming at the problems of heary work during establishment of traditional fingerprint database and the large matching error of the traditional random forest, an improved random forest localization method was proposed based on automatic fingerprint database expansion (FDE-IRF) to enhance the efficiency of fingerprint database construction and the accuracy of fingerprint matching. This method improved the traditional all sampling method to construct fingerprint database and the traditional random forest regression positioning method. The combination of sparse sampling fingerprint data of multiple time periods and Kriging interpolation method to complete unsampled fingerprint points improves the efficiency of database construction and gets a strong representative fingerprint database. At the same time, the decision tree weighting strategy is used to improve the average voting method in the traditional random forest, and the data out of bag is used to evaluate the prediction error of the decision tree and assign the corresponding weight, which improves the regression accuracy of the algorithm. The experimental results shows that the average positioning error of the proposed method is 1.26 m, which is at least 14.3% lower than that of similar methods, and verifies the accuracy and effectiveness of the proposed method.
-
表 1 指纹库数据
位置坐标 指纹数据 $ ({x}_{1},{y}_{1})$ $ ({\rm{RSS}}_{1,1}^{1},{\rm{RSS}}_{1,2}^{1},\cdots ,{\rm{RSS}}_{1,n}^{1})$ $\vdots $ $ ({\rm{RSS}}_{m,1}^{1},{\rm{RSS}}_{m,2}^{1},\cdots ,{\rm{RSS}}_{m,n}^{1})$ $ ({x}_{2},{y}_{2})$ $ ({\rm{RSS}}_{1,1}^{2},{\rm{RSS}}_{1,2}^{2},\cdots ,{\rm{RSS}}_{1,n}^{2})$ $\vdots $ $ ({\rm{RSS}}_{m,1}^{2},{\rm{RSS}}_{m,2}^{2},\cdots ,{\rm{RSS}}_{m,n}^{2})$ $\vdots $ $\vdots $ $ ({x}_{s},{y}_{s})$ $ ({\rm{RSS}}_{1,1}^{s},{\rm{RSS}}_{1,2}^{s},\cdots ,{\rm{RSS}}_{1,n}^{s})$ $\vdots $ $ ({\rm{RSS}}_{m,1}^{s},{\rm{RSS}}_{m,2}^{s},\cdots ,{\rm{RSS}}_{m,n}^{s})$ 注：$m$表示第$m$条指纹；$ ({x}_{s},{y}_{s})$表示第$s$个位置处的坐标； ${\rm{RSS}}_{m,n}^s$表示第$s$个位置处第$m$条指纹的第$n$个AP的RSS值. 
下载: 导出CSV
-
[1] GU Y Y, LO A, NIEMEGEERS I. A survey of indoor positioning systems for wireless personal networks[J]. IEEE communications surveys and tutorials, 2009, 11(1): 13-32. DOI: 10.1109/SURV.2009.090103 [2] PENG X S, CHEN R Z, YU K G, et al. A new Wi-Fi dynamic selection of nearest neighbor localization algorithm based on RSS characteristic value extraction by hybrid filtering[J]. Measurement science and technology, 2021, 32(3): 034003. DOI: 10.1088/1361-6501/abc510 [3] WOO S K, JEONG S S, MOK E, et al. Application of Wi-Fi-based indoor positioning system for labor tracking at construction sites: a case study in Guangzhou MTR[J]. Automation in construction, 2011, 20(1): 3-13. DOI: 10.1016/j.autcon.2010.07.009 [4] DING X X, WANG B B, WANG Z J. Dynamic threshold location algorithm based on fingerprinting method[J]. ETRI journal, 2018, 40(4): 531-536. DOI: 10.4218/etrij.2017-0155 [5] TIAN X H, SHEN R F, LIU D W, et al. Performance analysis of RSS fingerprinting based indoor localization[J]. IEEE transactions on mobile computing, 2016, 16(10): 2847-2861. DOI: 10.1109/TMC.2016.2645221 [6] 曹子腾, 郭阳, 赵正旭, 等. 室内定位技术研究综述[J]. 计算机技术与发展, 2020, 30(6): 202-206. DOI: 10.3969/j.issn.1673-629X.2020.06.039 [7] HE S N, CHAN S H G. Wi-Fi fingerprint-based indoor positioning: recent advances and comparisons[J]. IEEE communications surveys and tutorials, 2016, 18(1): 466-490. DOI: 10.1109/COMST.2015.2464084 [8] YASSIN A, NASSER Y, AWAD M, et al. Recent advances in indoor localization: a survey on theoretical approaches and applications[J]. IEEE communications surveys and tutorials, 2017, 19(2): 1327-1346. DOI: 10.1109/COMST.2016.2632427 [9] DENG Z L, YU Y P, YUAN X, et al. Situation and development tendency of indoor positioning[J]. China communications, 2013, 10(3): 42-55. DOI: 10.1109/CC.2013.6488829 [10] ZHAO H L, HUANG B Q, JIA B. Applying kriging interpolation for Wi-Fi fingerprinting based indoor positioning systems[C]//IEEE Wireless Communications and Networking Conference, 2016. DOI: 10.1109/WCNC.2016.7565018 [11] 王轩, 陈国良, 曹晓祥, 等. 自适应K值及指纹库扩充的WLAN室内定位方法[J]. 测绘科学, 2020, 45(7): 26-32. [12] RAHMAN M A A, KARIM M K A, BUNDAK C E A. Weighted local access point based on fine matching k-nearest neighbor algorithm for indoor positioning system[C]// International Annual Conference (AEIT), 2019. DOI: 10.23919/AEIT.2019.8893365 [13] CHEN R, YE F. An overview of indoor positioning technology based on Wi-Fi channel state information[J]. Geomatics and information science of Wuhan University, 2018, 43(12): 2064-2070. DOI: 10.13203/j.whugis20180176 [14] CHEN R Z, CHU T X, LIU K Q, et al. Inferring human activity in mobile devices by computing multiple contexts[J]. Sensors, 2015, 15(9): 21219-21238. DOI: 10.3390/s150921219 [15] LEE S M, KIM J, MOON N. Random forest and Wi-Fi fingerprint-based indoor location recognition system using smart watch[J]. Human-centric computing and information sciences, 2019, 9(1): 6. DOI: 10.1186/s13673-019-0168-7 [16] 王日升, 谢红薇, 安建成. 基于分类精度和相关性的随机森林算法改进[J]. 科学技术与工程, 2017, 17(20): 67-72. DOI: 10.3969/j.issn.1671-1815.2017.20.012 [17] 张家伟, 郭林明, 杨晓梅. 针对不平衡数据的过采样和随机森林改进算法[J]. 计算机工程与应用, 2020, 56(11): 39-45. DOI: 10.3778/j.issn.1002-8331.1908-0338 [18] SWANGMUANG N, KRISHNAMURTHY P. Location fingerprint analyses toward efficient indoor positioning[C]//The 6th Annual IEEE International Conference on Pervasive Computing and Communications (PerCom), 2008. DOI: 10.1109/PERCOM.2008.33. [19] YOUSSEF M A, AGRAWALA A, SHANKAR A U. WLAN location determination via clustering and probability distributions[C]//The 1st IEEE International Conference on Pervasive Computing and Communications, 2003. DOI: 10.1109/PERCOM.2003.1192736 [20] BREIMAN L. Random forests[J]. Machine learning, 2001, 45(1): 5-32. DOI: 10.1023/A:1010933404324 -
点击查看大图
图(12) / 表(3)
计量
- 文章访问数: 420
- HTML全文浏览量: 147
- PDF下载量: 52
- 被引次数: 0
