摘要
在基于无线指纹室内定位技术中,信号的时空干扰引入了定位误差。为了解决这一问题,文中提出基于深度信号特征的室内定位方案,利用深度置信网络从接收信号强度中提取特征参数作为特征指纹。该方法能有效地缓解信号的波动性干扰,感知当前复杂的室内环境。为评估所提方法的性能,文中选择在两个具有典型性室内场景中进行实验。实验结果表明,该方法在定位精度和定位系统稳定性上都有了显著的提高。
Wi-Fi fingerprint-based localization has been applied into various indoor scenarios. However,the wireless fingerprints introduces estimation errors. Anovel feature-based deep learning localization scheme is proposed,which extracts the characteristic parameters as featured fingerprints from quantitative Received Signal Strength( RSS) with Deep Belief Network( DBN) framework. The featured fingerprints effectively alleviate the interference of RSS variability. In order to evaluate the performance of the proposed method,two representative indoor scenarios were chosen to experiment. The experimental results show that the method achieves substantial improvement in localization accuracy and realizes better real-time performance compared with two existing schemes.
引文
[1]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.
[2]Davidson P,Piche R.A survey of selected indoor positioning methods for smartphones[J].IEEE Communications Surveys&Tutorials,2017,19(2):1347-1370.
[3]Bahl P,Padmanabhan V N.RADAR:An in-building RF-based user location and tracking system[C].INFOCOM 2000.Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies.Proceedings.IEEE,2000,2:775-784.
[4]Zhao X,Xiao Z,Markham A,et al.Does BTLE measure up against Wi-Fi?A comparison of indoor location performance[C].European Wireless 2014;20th European Wireless Conference;Proceedings of VDE,2014:1-6.
[5]Chen Y,Lymberopoulos D,Liu J,et al.FM-based indoor localization[C].Proceedings of the 10th international conference on Mobile systems,applications,and services.ACM,2012:169-182.
[6]Chung J,Donahoe M,Schmandt C,et al.Indoor location sensing using geo-magnetism[C].Proceedings of the 9th international conference on Mobile systems,applications,and services.ACM,2011:141-154.
[7]Gentile C,Alsindi N,Raulefs R,et al.Geolocation techniques:principles and applications[M].Springer Science&Business Media,2012.
[8]Xie Y,Wang Y,Nallanathan A,et al.An Improved K-NearestNeighbor Indoor Localization Method Based on Spearman Distance[J].IEEE Signal Process.Lett.,2016,23(3):351-355.
[9]Zhou R,Lu S,Chen J,et al.An Optimized Space Partitioning Technique to Support Two-Layer Wi-Fi Fingerprinting[C].Wireless Communications and Networking Conference(WCNC),2017IEEE,2017:1-6.
[10]Zhang W,Liu K,Zhang W,et al.Deep neural networks for wireless localization in indoor and outdoor environments[J].Neurocomputing,2016,194:279-287.
[11]Youssef M,Agrawala A.The Horus WLAN location determination system[C].Proceedings of the 3rd international conference on Mobile systems,applications,and services.ACM,2005:205-218.
[12]Felix G,Siller M,Alvarez E N.A fingerprinting indoor localization algorithm based deep learning[C].Ubiquitous and Future Networks(ICUFN),2016 Eighth International Conference on.IEEE,2016:1006-1011.
[13]O'Connor P,Neil D,Liu S C,et al.Real-time classification and sensor fusion with a spiking deep belief network[J].Frontiers in neuroscience,2013,7:178.
[14]Dahl G,Mohamed A,Hinton G E.Phone recognition with the mean-covariance restricted Boltzmann machine[C].Advances in neural information processing systems,2010:469-477.
[15]Leonard J A,Kramer M A.Radial basis function networks for classifying process faults[J].IEEE Control Systems Magazine,1991,11(3):31-38.