近年來，用於室內定位和導航的超寬頻(UWB)系統在學術界和工業界已有許多研究成果。然而，當信號在嚴重的非直視性(NLoS)條件下傳播時，UWB定位準確度會大幅降低。在本文中，我們使用深度學習模型，包括長短期記憶(LSTM)網路和深度神經網路(DNN)來分析UWB訊號的五個不同特徵。五個特徵分別為：接收訊號強度(RSSI)、到達時間(ToA)、到達時間差(TDoA)、從通道脈衝響應(CIR)提取的第一路徑脈衝振幅(FP)以及FP與脈衝峰值振幅的比值(Mc)。我們將這五個特徵組合到六個不同的數據集中，用於我們的深度學習模型之中。基於具有組合特徵的深度學習模型的效能，我們提出了加權室內定位(WIP)演算法。實驗結果表明，我們的模型比基準模型具有更好的準確性。

In recent years, the Ultra-wideband (UWB) system has been investigated for indoor localization and navigation by academia and industry. However, the UWB localization accuracy deteriorates when the signal propagates under severe non-line-of-sight (NLoS) conditions. We use deep learning model, including the long short-term memory (LSTM) network and the deep neural network (DNN), to analyze five different UWB signal features. The five features are received signal strength indication (RSSI), time of arrival (ToA), time difference of arrival (TDoA), first path (FP) amplitude from channel impulse response (CIR), and metric Mc (the ratio of the first path amplitude to peak amplitude). Then, we combine the five features into six different datasets for our deep learning model. Based on the performance of the deep learning model with the combined features, we propose a weighted indoor position (WIP) algorithm. The experiment results show that our model has better accuracy than baseline works.

Abstract
Contents--------------------i
List of Figures-------------ii
List of Tables--------------iii
Chapter 1-------------------1
Chapter 2-------------------4
Chapter 3-------------------8
Chapter 4-------------------20
Chapter 5-------------------27
Chapter 6-------------------36
References------------------37

[1] F. Zafari, A. Gkelias, and K. K. Leung, "A survey of indoor localizations systems and technologies," IEEE Communications Surveys & Tutorials, vol. 21, no. 3, pp. 2568-2599, 3rd Quart., Apr. 2019.
[2] V. Djaja-Josko and J. Kolakowski, "UWB positioning system for elderly persons monitoring," 2015 23rd Telecommunications Forum Telfor (TELFOR), pp. 169-172, 2015.
[3] E. Cardellach, F. Fabra, O. Nogués-Correig, S. Oliveras, S. Ribó, and A. Rius, "GNSS-R ground-based and airborne campaigns for ocean, land, ice, and snow techniques: Application to the GOLD-RTR data sets," Radio Science, vol. 46, no. 6, p. RS0C04, Dec. 2011.
[4] R. Mautz, "Overview of current indoor positioning systems," Geodezija ir Kartografija, vol. 35, no. 1, pp. 18-22, Dec. 2009.
[5] W. Li, T. Zhang, Q. Zhang, "Experimental researches on an UWB NLoS identification method based on machine learning," 2013 15th IEEE International Conference on Communication Technology, pp. 473-477, Nov. 2013
[6] M. Youssef and A. Agrawala, "The horus WLAN location determination system,'' Proceedings of the 3rd international conference on Mobile systems, applications, and services, pp. 205-218, Jun. 2005.
[7] J. Lovón-Melgarejo, M. Castillo-Cara, O. Huarcaya-Canal, L. Orozco-Barbosa and I. García-Varea, "Comparative study of supervised learning and metaheuristic algorithms for the development of Bluetooth-based indoor localization mechanisms," IEEE Access, vol. 7, pp. 26123-26135, Feb. 2019.
[8] W. Xue, Q. Li, X. Hua, K. Yu, W. Qiu, and B. Zhou, "A new algorithm for indoor RSSI radio map reconstruction," IEEE Access, vol. 6, pp. 76118-76125, 2018
[9] X. Wang, L. Gao, and S. Mao, "CSI phase fingerprinting for indoor localization with a deep learning approach,'' IEEE Internet Things Journal, vol. 3, no. 6, pp. 1113-1123, Dec. 2016.
[10] Z. Yin, X. Jiang, Z. Yang, N. Zhao, and Y. Chen, "WUB-IP: A high-precision UWB positioning scheme for indoor multiuser applications," IEEE systems Journal, vol. 13, no. 1, pp. 279-288, Mar. 2019.
[11] M. Kok, J. D. Hol and T. B. Schön, "Indoor Positioning Using Ultrawideband and Inertial Measurements," IEEE Transactions on Vehicular Technology, vol. 64, no. 4, pp. 1293-1303, Apr 2015.
[12] I. Sharp and K. Yu, "Indoor TOA error measurement, modeling, and analysis," IEEE Transactions on Instrumentation Measurement, vol. 63, no. 9, pp. 2129-2144, Sept. 2014.
[13] S. Wu, S. Zhang, and D. Huang, "A TOA-based localization algorithm with simultaneous NLoS mitigation and synchronization error elimination," IEEE Sensors Letters, vol. 3, no. 3, Mar. 2019.
[14] A. Makki, A. Siddig, M. Saad, J. R. Cavallaro, and C. J. Bleakley, "Indoor localization using 802.11 time differences of arrival," IEEE Transactions on Instrumentation Measurement, vol. 65, no. 3, pp. 614-623, Mar. 2016.
[15] P. Du, S. Zhang, C. Chen, A. Alphones, and W. Zhong, "Demonstration of a low-complexity indoor visible light positioning system using an enhanced TDOA scheme," IEEE Photonics Journal, vol. 10, no. 4, Aug. 2018.
[16] G. Wang, S. Cai, Y. Li and N. Ansari, "A Bias-Reduced Nonlinear WLS Method for TDOA/FDOA-Based Source Localization," IEEE Transactions on Vehicular Technology, vol. 65, no. 10, pp. 8603-8615, Oct. 2016.
[17] S. W. Chen, C. K. Seow, and S. Y. Tan, "Virtual reference device-based NLoS localization in multipath environment," IEEE Antennas and Wireless Propagation Letters, vol. 13, pp. 1409-1412, 2014.
[18] S. Leugner, M. Pelka, and H. Hellbrück, "Comparison of wired and wireless synchronization with clock drift compensation suited for U-TDoA localization," 2016 13th Workshop on Positioning, Navigation and Communications (WPNC), pp. 1-4, Oct. 2016.
[19] C. Wang, J. Luo, and Y. Zheng, "Optimal target tracking based on dynamic fingerprint in indoor wireless network," IEEE Access, vol. 6, pp. 77226-77239, 2018.
[20] X. Wang, X. Wang, and S. Mao, "ResLoc: Deep residual sharing learning for indoor localization with CSI tensors," 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC). pp. 1-6, Oct. 2017.
[21] X. Wang, L. Gao, S. Mao, and S. Pandey, "CSI-based fingerprinting for indoor localization: A deep learning approach," IEEE Transactions on Vehicular Technology, vol. 66, no. 1, pp. 763-776, Feb. 2017.
[22] Decawave, "DW1000 Metrics for Estimation of Non-Line Of Sight Operating Conditions." [Online]. Available:
https://www.decawave.com/wp-content/uploads/2018/10/APS006_Part-3-DW1000-Diagnostics-for-NLoS-Channels_v1.1.pdf
[23] Y. Xue, W. Su, H. Wang, D. Yang, and J. Ma, "A model on indoor localization system based on the time difference without synchronization," IEEE Access, vol. 6, pp. 34179-34189, 2018.
[24] I. Dotlic, A. Connell, and M. McLaughlin, "Ranging Methods Utilizing Carrier Frequency Offset Estimation," 2018 15th Workshop on Positioning, Navigation and Communications (WPNC), pp. 1–6, Oct 2018.
[25] A. S. M. Sala, R. G. Quiros, E. E. Lopez, "Using neural networks and Active RFID for indoor location services," European Workshop on Smart Objects: Systems, Technologies and Applications, June. 2011
[26] J. Luo and H. Gao, "Deep belief networks for fingerprinting indoor localization using ultrawideband technology," International Journal of Distributed Sensor Networks, vol. 2016, no. 18, pp. 18:18–18:18, 2016
[27] C. Liu , C. Wang, and J. Luo, "Large-Scale Deep Learning Framework on FPGA for Fingerprint-Based Indoor Localization," IEEE Access, vol. 8, pp. 65609-65617, Apr. 2020.
[28] C. M. Own, J. W. Hou, W. Y. Tao, "Signal Fuse Learning Method With Dual Bands Wi-Fi Signal Measurements in Indoor Positioning," IEEE Access, vol. 7, pp. 131805-131817, Sep. 2019.
[29] Z. Iqbal, D. Luo, P. Henry, S. Kazemifar, T. Rozario, Y. Yan, K. Westover, W. Lu, D. Nguyen, T. Long, J. Wang, H. Choy, and S. Jiang, "Accurate real time localization tracking in a clinical environment using bluetooth low energy and deep learning," PLoS ONE, arXiv/1711.08149, 2017
[30] X. Cui, H. Zhang, and T. Gulliver, "Threshold selection for ultrawideband toa estimation based on neural networks," Journal of Networks, vol. 7, no. 9, pp. 1311–1318, 2012
[31] Y. Jin, W. Soh, and W. Wong, "Indoor localization with channel impulse response based fingerprint and nonparametric regression," IEEE Transactions on Wireless Communications, vol. 9, no. 3, pp. 1120–1127, 2010
[32] X. Wang, L. Gao, and S. Mao, "Biloc: Bi-modal deep learning for indoor localization with commodity 5ghz Wi-Fi," IEEE Access, vol. 5, pp. 4209– 4220, 2017.
[33] Y. Xue, W. Su, H. C Wang, D. Yang, Y. Jiang, "DeepTAL: Deep Learning for TDOA-Based Asynchronous Localization Security With Measurement Error and Missing Data," IEEE Access, vol. 7, pp. 122492-122502, Aug. 2019.
[34] J. Vieira, E. Leitinger, M. Sarajlic, X. Li, and F. Tufvesson, "Deep convolutional neural networks for massive MIMO fingerprint-based positioning," 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC), pp. 1–6, Oct. 2017.
[35] A. Niitsoo, T. Edelhaußer, and C. Mutschler, "Convolutional neural networks for position estimation in TDoA-based locating systems," 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN), pp. 1–8, 2018.
[36] M. Z. Comiter, M. B. Crouse, and K. H. T., "A structured deep neural network for data driven localization in high frequency wireless networks," 2017 International Journal of Computer Networks & Communications (IJCNC) vol. 9, pp. 21–39, May 2017.
[37] Y. Y. Chen, S. P. Huang. T. W. Wu, W. T. Tsai, C. Y. Liou, S. G. Mao, "UWB System for Indoor Positioning and Tracking with Arbitrary Target Orientation, Optimal Anchor Location, and Adaptive NLoS Mitigation," IEEE Transactions on Vehicular Technology, Feb. 2020.