基于深度学习的Wi-Fi与iBeacon融合的室内定位方法
|
摘要
针对传统室内定位指纹法存在定位精度低、容易受到环境影响的问题,提出了一种基于深度学习的Wi-Fi与iBeacon融合的室内定位方法。离线阶段在参考点处采集各个AP和iBeacon的信号强度,使用这些信号强度数据对堆叠自动编码机进行训练并从大量带有噪声的信号强度样本中提取特征,构建位置指纹数据库;在线定位阶段,使用堆叠自动编码机获得待测点信号强度特征并与位置指纹数据库中信号强度特征进行匹配,通过近邻算法估计待测点位置。实验结果表明,基于堆叠自动编码机的室内定位算法具有更高的定位精度。
Aiming at the problem that the traditional indoor fingerprint localization algorithm has low positioning accuracy and is easily affected by the environment, an indoor localization algorithm based on deep learning using Wi-Fi and i Beacon is proposed. Signal strength of each AP and iBeacon is collected at each reference point in offline phase, and is used to train the stacked auto-encoder which is used to extract features from a large number of signal strength samples with noise.These features are used to construct the fingerprint database. The features of the point to be measured can be obtained by the stacked auto-encoder in online phase. Then these features are matched in fingerprint database. The position of the point to be measured is estimated by the nearest neighbor algorithm. Experimental results show that the proposed indoor localization algorithm has higher localization accuracy.
Aiming at the problem that the traditional indoor fingerprint localization algorithm has low positioning accuracy and is easily affected by the environment, an indoor localization algorithm based on deep learning using Wi-Fi and i Beacon is proposed. Signal strength of each AP and iBeacon is collected at each reference point in offline phase, and is used to train the stacked auto-encoder which is used to extract features from a large number of signal strength samples with noise.These features are used to construct the fingerprint database. The features of the point to be measured can be obtained by the stacked auto-encoder in online phase. Then these features are matched in fingerprint database. The position of the point to be measured is estimated by the nearest neighbor algorithm. Experimental results show that the proposed indoor localization algorithm has higher localization accuracy.
引文
[1]张世哲.基于惯性传感器和WiFi的室内定位系统的设计与实现[D].北京:北京邮电大学,2012
[2] Peters S W,Heath R W.Interference alignment via alternating minimization[C]//Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing,Taipei,Taiwan,China,2009.
[3] Newman N.Apple iBeacon technology briefing[J].Journal of Direct Data&Digital Marketing Practice,2014,15(3):222-225.
[4] Ciurana M,Cugno S.Indoor tracking in WLAN location with TOA measurements[C]//Proceedings of the 4th ACM International Workshop on Mobility Management and Wireless Access,2006.
[5] Cheng L,Wu C D,Zhang Y Z.Indoor robot localization based on wireless sensor networks[J].IEEE Transactions on Consumer Electronics,2011,57(3):1099-1104.
[6] Kang W,Han Y.SmartPDR:Smartphone-based pedestrian dead reckoning for indoor localization[J].IEEE Sensors Journal,2015,15(5):2906-2916.
[7] Youssef M,Agrawala A.The Horus location determination system[J].Wireless Networks,2008,14(3):357-374.
[8] 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.
[9] Laitinen E,Lohan E S.On the choice of access point selection criterion and other position estimation characteristics for WLAN-based indoor positioning[J].Sensors,2016,16(5):737.
[10] Wu C L,Fu L C,Lian F L.WLAN location determination in e-home via support vector classification[C]//Proceedings of IEEE International Conference on Networking,Sensing and Control,Taipei,Taiwan,China,2004.
[11] Saleem F,Wyne S.Wlan-based indoor localization using neural networks[J].Journal of Electrical Engineering,2016,67(4):299-306.
[12]朱顺涛,卢先领.基于半监督极限学习机的增量式定位算法[J].传感技术学报,2017,30(10):1554-1559.
[13] Bahl P,Padmanabhan V N.RADAR:An in-building RFbased user location and tracking system[C]//Proceedings of Nineteenth Annual Joint Conference on the IEEE Computer and Communications,2000.
[14] Feng C,Au W S A,Valaee S,et al.Received-signalstrength-based indoor positioning using compressive sensing[J].IEEE Transactions on Mobile Computing,2012,11(12):1983-1993.
[15] Nikitaki S,Tsakalides P.Localization in wireless networks via spatial sparsity[C]//Proceedings of Signals,Systems and Computers,Pacific Grove,CA,USA,2010.
[16] Deng L.Three classes of deep learning architectures and their applications:a tutorial survey[EB/OL].(2013)[2018-08-15].]https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/Transactions-APSIPA.pdf.
[17] Majumder N,Poria S,Gelbukh A,et al.Deep learningbased document modeling for personality detection from text[J].IEEE Intelligent Systems,2017,32(2):74-79.
[18] Shen D,Wu G,Suk H I.Deep learning in medical image analysis[J].Annual Review of Biomedical Engineering,2017,19:221-248.
[19] Liou C Y,Huang J C,Yang W C.Modeling word perception using the Elman network[J].Neurocomputing,2008,71(16/18):3150-3157.
[20] Liou C Y,Cheng W C,Liou J W,et al.Autoencoder for words[J].Neurocomputing,2014,139:84-96.
[2] Peters S W,Heath R W.Interference alignment via alternating minimization[C]//Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing,Taipei,Taiwan,China,2009.
[3] Newman N.Apple iBeacon technology briefing[J].Journal of Direct Data&Digital Marketing Practice,2014,15(3):222-225.
[4] Ciurana M,Cugno S.Indoor tracking in WLAN location with TOA measurements[C]//Proceedings of the 4th ACM International Workshop on Mobility Management and Wireless Access,2006.
[5] Cheng L,Wu C D,Zhang Y Z.Indoor robot localization based on wireless sensor networks[J].IEEE Transactions on Consumer Electronics,2011,57(3):1099-1104.
[6] Kang W,Han Y.SmartPDR:Smartphone-based pedestrian dead reckoning for indoor localization[J].IEEE Sensors Journal,2015,15(5):2906-2916.
[7] Youssef M,Agrawala A.The Horus location determination system[J].Wireless Networks,2008,14(3):357-374.
[8] 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.
[9] Laitinen E,Lohan E S.On the choice of access point selection criterion and other position estimation characteristics for WLAN-based indoor positioning[J].Sensors,2016,16(5):737.
[10] Wu C L,Fu L C,Lian F L.WLAN location determination in e-home via support vector classification[C]//Proceedings of IEEE International Conference on Networking,Sensing and Control,Taipei,Taiwan,China,2004.
[11] Saleem F,Wyne S.Wlan-based indoor localization using neural networks[J].Journal of Electrical Engineering,2016,67(4):299-306.
[12]朱顺涛,卢先领.基于半监督极限学习机的增量式定位算法[J].传感技术学报,2017,30(10):1554-1559.
[13] Bahl P,Padmanabhan V N.RADAR:An in-building RFbased user location and tracking system[C]//Proceedings of Nineteenth Annual Joint Conference on the IEEE Computer and Communications,2000.
[14] Feng C,Au W S A,Valaee S,et al.Received-signalstrength-based indoor positioning using compressive sensing[J].IEEE Transactions on Mobile Computing,2012,11(12):1983-1993.
[15] Nikitaki S,Tsakalides P.Localization in wireless networks via spatial sparsity[C]//Proceedings of Signals,Systems and Computers,Pacific Grove,CA,USA,2010.
[16] Deng L.Three classes of deep learning architectures and their applications:a tutorial survey[EB/OL].(2013)[2018-08-15].]https://www.microsoft.com/en-us/research/wp-content/uploads/2016/02/Transactions-APSIPA.pdf.
[17] Majumder N,Poria S,Gelbukh A,et al.Deep learningbased document modeling for personality detection from text[J].IEEE Intelligent Systems,2017,32(2):74-79.
[18] Shen D,Wu G,Suk H I.Deep learning in medical image analysis[J].Annual Review of Biomedical Engineering,2017,19:221-248.
[19] Liou C Y,Huang J C,Yang W C.Modeling word perception using the Elman network[J].Neurocomputing,2008,71(16/18):3150-3157.
[20] Liou C Y,Cheng W C,Liou J W,et al.Autoencoder for words[J].Neurocomputing,2014,139:84-96.