基于线性判别分析和梯度提升决策树的WLAN室内定位算法
|
摘要
为了减小室内无线局域网(WLAN)环境中接收信号强度值复杂的时变特性对定位精度的影响,提出了一种基于线性判别分析和梯度提升决策树的室内定位算法。该算法利用线性判别分析(LDA)提取原始位置指纹的主要定位特征,去除冗余和噪声;接着,使用前向分布算法,将损失函数在当前模型的负梯度值作为误差的近似值,拟合一个分类回归树,并使用加法模型将生成的分类回归树线性组合,生成梯度提升决策树(GBDT)定位模型。实验结果表明,与其他室内定位算法相比,该算法的定位精度提升20%,并且减少了接入点使用个数。
In order to reduce the influence of the complex time-varying characteristic of received signal strength indication on positioning accuracy in indoor wireless local area network(WLAN) environment, a new indoor positioning algorithm based on linear discriminant analysis(LDA) and gradient boosting decision tree(GBDT) is proposed in this paper. The algorithm adopts LDA to extract the main positioning features of original location fingerprints and remove the redundant localization features and noise. Then, using the forward distribution algorithm, the negative gradient value of the loss function in current model is taken as the approximation of the error to fit a classification and regression tree. The additive model is used to linearly combine the resulting classification and regression trees and generate a GBDT positioning model. The experiment results show that compared with other indoor positioning algorithms, the positioning accuracy of the proposed algorithm is improved by more than 20%, and the algorithm also reduces the number of the required access points.
In order to reduce the influence of the complex time-varying characteristic of received signal strength indication on positioning accuracy in indoor wireless local area network(WLAN) environment, a new indoor positioning algorithm based on linear discriminant analysis(LDA) and gradient boosting decision tree(GBDT) is proposed in this paper. The algorithm adopts LDA to extract the main positioning features of original location fingerprints and remove the redundant localization features and noise. Then, using the forward distribution algorithm, the negative gradient value of the loss function in current model is taken as the approximation of the error to fit a classification and regression tree. The additive model is used to linearly combine the resulting classification and regression trees and generate a GBDT positioning model. The experiment results show that compared with other indoor positioning algorithms, the positioning accuracy of the proposed algorithm is improved by more than 20%, and the algorithm also reduces the number of the required access points.
引文
[1] TIAN X H, LI W X. Optimization of fingerprints reporting strategy for WLAN indoor localization [J]. IEEE Transactions on Mobile Computing, 2018, 17(2): 390- 403.
[2] HE S, CHAN S H G. Wi-Fi fingerprint-based indoor positioning: Recent advances and comparisons[J]. IEEE Communications Surveys & Tutorials, 2016, 18(1): 466- 490.
[3] CHEN K Y, WANG C. Slide: Towards fast and accurate mobile fingerprinting for Wi-Fi indoor positioning syste-ms[J]. IEEE Sensors Journal, 2018, 18(3):1213-1223.
[4] BAHL P, PADMANABHAN V N. RADAR: An in-building RF-based user location and tracking system[C]. Infocom 9th Joint Conference of the IEEE Computer & Communications Societies, 2000:775- 784.
[5] CHEN Y, YANG Q, YIN J, et al. Power-efficient access-point selection for indoor location estimation[J]. IEEE Transactions on Knowledge & Data Engineering, 2006, 18(7):877- 888.
[6] FANG S H, LIN T. Principal component localization in indoor WLAN environments[J]. IEEE Transactions on Mobile Computing, 2011, 11(1):100-110.
[7] ZHANG G, ZHAN X, DAN L. Research and improvement on indoor localization based on RSSI fingerprint database and K-nearest neighbor points[C].IEEE International Conference on Communications, Circuits and Systems, 2013:68-71.
[8] 谢代军, 胡捍英, 孔范增. 基于分布重叠和特征加权的无线局域网室内定位算法[J]. 计算机科学, 2013, 40(11):38- 42.XIE D J, HU H Y, KONG F Z. Indoor positioning algorithm for WLAN based on distribution and feature weighting[J]. Computer Science, 2013, 40(11):38- 42.
[9] BORENOVIC M, NESKOVIC A. ANN based models for positioning in indoor WLAN environments[C]. Telecommunications Forum. IEEE, 2012:305-312.
[10] LIU L P, JIANG Y, ZHOU Z H. Least square incremental linear discriminant analysis[C]. IEEE International Conference on Data Mining, 2009:298-306.
[11] ZHANG X, CHU D, TAN R C E. Sparse uncorrelated linear discriminant analysis for undersampled proble-ms[J]. IEEE Transactions on Neural Networks & Learning Systems, 2016, 27(7):1469-1485.
[12] FRIEDMAN J. Greedy function approximation: a gradient boosting machine[J]. Annals of Statistics, 2001, 29(5):1189-1232.
[13] SOLEIMANI R, DEHAGHANI A H S. A new decision tree based algorithm for prediction of hydrogen sulfide solubility in various ionic liquids[J]. Journal of Molecular Liquids, 2017(242):703-713.
[14] MA X L,DING C. Prioritizing influential factors for freeway incident clearance time prediction using the Gradient Boosting Decision Trees Method[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(9):2303- 2310.
[15] XIA Y F, LIU C Z. A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring[J]. Expert Systems with Applications, 2017(78): 225- 241.
[16] 雷海锐,高秀峰,刘辉. 基于机器学习的混合式特征选择算法[J].电子测量技术, 2018, 41(16):42- 46.LEI H R, GAO X F, LIU H. Mixed feature selection method based on machine learning [J]. Electronic Measurement Technology, 2018,41(16):42- 46.
[17] KING T, HAENSELMANN T, EFFELSBERG W. On-demand fingerprint selection for 802.11-based positioning systems[J]. Transplantation, 2008, 82(1):1- 8.
[18] 赵光权,刘小勇,姜泽东,等. 基于深度学习的轴承健康因子无监督构建方法[J].仪器仪表学报, 2018,39(6):82- 88.ZHAO G Q, LIU X Y, JIANG Z D, et al. Unsupervised health indicator of bearing based on deep learning[J]. Chinese Journal of Scientific Instrument, 2018,39(6):82- 88.
[19] 李明阳,陈万忠,张涛. 基于DD-DWT和Log-Logistic参数回归的癫痫脑电自动识别方法[J].仪器仪表学报,2017,38(6):1368-1377.LI M Y, CHEN W ZH, ZHANG T. Automatic epilepsy EEG recognition method based on DD-DWT and Log-Logistic parameter regression[J]. Chinese Journal of Scientific Instrument,2017, 38(6):1368-1377.
[20] 周卫庆,司风琪,徐治皋,等. 基于KPCA残差方向梯度的故障检测方法及应用[J]. 仪器仪表学报, 2017,38(10):2518- 2524.ZHOU W Q, SI F Q, XU ZH G, et al. Fault detection method based on KPCA residual direction gradient and its application[J]. Chinese Journal of Scientific Instrument, 2017, 38(10): 2518- 2524.
[21] 董浩,李明星,张淑清,等.基于核主成分分析和极限学习机的短期电力负荷预测[J]. 电子测量与仪器学报,2018,32(1):188-193.DONG H, LI M X, ZHANG SH Q, et al. Short-term power load forecasting based on kernel principal component analysis and extreme learning machine[J]. Journal of Electronic Measurement and Instrumentation, 2018, 32(1): 188-193.
[22] 石柯,陈洪生,张仁同. 一种基于支持向量回归的802.11无线室内定位方法[J].软件学报,2014,25(11):2636- 2651.SHI K, CHEN H SH, ZHANG R T. Indoor location method based on support vector regression in 802.11 wireless environments[J]. Journal of Software, 2014, 25(11):2636- 2651.
[23] 孙扩,李文海,王怡萍. 基于SVM专家系统的模拟电路PCB故障诊断研究[J].国外电子测量技术,2018,37(9):22- 26.SUN K, LI W H, WANG Y P. Research on PCB fault diagnosis of analog circuit based on SVM expert syst-em[J]. Foreign Electronic Measurement Technology, 2018,37(9):22- 26.
[2] HE S, CHAN S H G. Wi-Fi fingerprint-based indoor positioning: Recent advances and comparisons[J]. IEEE Communications Surveys & Tutorials, 2016, 18(1): 466- 490.
[3] CHEN K Y, WANG C. Slide: Towards fast and accurate mobile fingerprinting for Wi-Fi indoor positioning syste-ms[J]. IEEE Sensors Journal, 2018, 18(3):1213-1223.
[4] BAHL P, PADMANABHAN V N. RADAR: An in-building RF-based user location and tracking system[C]. Infocom 9th Joint Conference of the IEEE Computer & Communications Societies, 2000:775- 784.
[5] CHEN Y, YANG Q, YIN J, et al. Power-efficient access-point selection for indoor location estimation[J]. IEEE Transactions on Knowledge & Data Engineering, 2006, 18(7):877- 888.
[6] FANG S H, LIN T. Principal component localization in indoor WLAN environments[J]. IEEE Transactions on Mobile Computing, 2011, 11(1):100-110.
[7] ZHANG G, ZHAN X, DAN L. Research and improvement on indoor localization based on RSSI fingerprint database and K-nearest neighbor points[C].IEEE International Conference on Communications, Circuits and Systems, 2013:68-71.
[8] 谢代军, 胡捍英, 孔范增. 基于分布重叠和特征加权的无线局域网室内定位算法[J]. 计算机科学, 2013, 40(11):38- 42.XIE D J, HU H Y, KONG F Z. Indoor positioning algorithm for WLAN based on distribution and feature weighting[J]. Computer Science, 2013, 40(11):38- 42.
[9] BORENOVIC M, NESKOVIC A. ANN based models for positioning in indoor WLAN environments[C]. Telecommunications Forum. IEEE, 2012:305-312.
[10] LIU L P, JIANG Y, ZHOU Z H. Least square incremental linear discriminant analysis[C]. IEEE International Conference on Data Mining, 2009:298-306.
[11] ZHANG X, CHU D, TAN R C E. Sparse uncorrelated linear discriminant analysis for undersampled proble-ms[J]. IEEE Transactions on Neural Networks & Learning Systems, 2016, 27(7):1469-1485.
[12] FRIEDMAN J. Greedy function approximation: a gradient boosting machine[J]. Annals of Statistics, 2001, 29(5):1189-1232.
[13] SOLEIMANI R, DEHAGHANI A H S. A new decision tree based algorithm for prediction of hydrogen sulfide solubility in various ionic liquids[J]. Journal of Molecular Liquids, 2017(242):703-713.
[14] MA X L,DING C. Prioritizing influential factors for freeway incident clearance time prediction using the Gradient Boosting Decision Trees Method[J]. IEEE Transactions on Intelligent Transportation Systems, 2017, 18(9):2303- 2310.
[15] XIA Y F, LIU C Z. A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring[J]. Expert Systems with Applications, 2017(78): 225- 241.
[16] 雷海锐,高秀峰,刘辉. 基于机器学习的混合式特征选择算法[J].电子测量技术, 2018, 41(16):42- 46.LEI H R, GAO X F, LIU H. Mixed feature selection method based on machine learning [J]. Electronic Measurement Technology, 2018,41(16):42- 46.
[17] KING T, HAENSELMANN T, EFFELSBERG W. On-demand fingerprint selection for 802.11-based positioning systems[J]. Transplantation, 2008, 82(1):1- 8.
[18] 赵光权,刘小勇,姜泽东,等. 基于深度学习的轴承健康因子无监督构建方法[J].仪器仪表学报, 2018,39(6):82- 88.ZHAO G Q, LIU X Y, JIANG Z D, et al. Unsupervised health indicator of bearing based on deep learning[J]. Chinese Journal of Scientific Instrument, 2018,39(6):82- 88.
[19] 李明阳,陈万忠,张涛. 基于DD-DWT和Log-Logistic参数回归的癫痫脑电自动识别方法[J].仪器仪表学报,2017,38(6):1368-1377.LI M Y, CHEN W ZH, ZHANG T. Automatic epilepsy EEG recognition method based on DD-DWT and Log-Logistic parameter regression[J]. Chinese Journal of Scientific Instrument,2017, 38(6):1368-1377.
[20] 周卫庆,司风琪,徐治皋,等. 基于KPCA残差方向梯度的故障检测方法及应用[J]. 仪器仪表学报, 2017,38(10):2518- 2524.ZHOU W Q, SI F Q, XU ZH G, et al. Fault detection method based on KPCA residual direction gradient and its application[J]. Chinese Journal of Scientific Instrument, 2017, 38(10): 2518- 2524.
[21] 董浩,李明星,张淑清,等.基于核主成分分析和极限学习机的短期电力负荷预测[J]. 电子测量与仪器学报,2018,32(1):188-193.DONG H, LI M X, ZHANG SH Q, et al. Short-term power load forecasting based on kernel principal component analysis and extreme learning machine[J]. Journal of Electronic Measurement and Instrumentation, 2018, 32(1): 188-193.
[22] 石柯,陈洪生,张仁同. 一种基于支持向量回归的802.11无线室内定位方法[J].软件学报,2014,25(11):2636- 2651.SHI K, CHEN H SH, ZHANG R T. Indoor location method based on support vector regression in 802.11 wireless environments[J]. Journal of Software, 2014, 25(11):2636- 2651.
[23] 孙扩,李文海,王怡萍. 基于SVM专家系统的模拟电路PCB故障诊断研究[J].国外电子测量技术,2018,37(9):22- 26.SUN K, LI W H, WANG Y P. Research on PCB fault diagnosis of analog circuit based on SVM expert syst-em[J]. Foreign Electronic Measurement Technology, 2018,37(9):22- 26.