隨著現在科技發展以及手機的普及，人手一機已成現代趨勢，同時也帶起了許多適地性服務。基於適地性服務的發起，引起了許多人投入定位相關研究，其中一項便是無線電波訊號定位。然而此項定位法卻容易受天氣因素影響，因此本論文透過機器學習的特性，結合天氣因素，將低無線定位法受到天氣造成的影響。
此篇論文提出了利用機器學習的特性，對天氣因素進行分群。並由這些天氣群集中所對應的無線電波資料，找出距離誤差最低的群集設為基底。之後利用類神經網路訓練訊號補償模型，將其他群集的訊號強度補償至基底，而後再利用路徑衰減模型估測出使用者和基地台之間的距離。最後和以前常用的方法進行比較，以驗證此篇論文的優點。

With the current development of science and technology and the popularization of mobile phones, the manpower and equipment have become a modern trend and brought many suitable services. Based on the launch of a service of locality, many people have been involved in positioning related research. One of them is the positioning of radio signals. However, this positioning method is easily influenced by the weather. Therefore, this paper uses the characteristics of machine learning and the weather to influenced the low-radio location method by the weather.

This essay proposes the use of machine learning features to group weather factors. And from these radio waves corresponding to the weather cluster data, and the cluster with the lowest distance error as the base. After that, the neural network is used to train the signal compensation model, and the signal intensities of the other clusters are compensated to the base. Then, the path attenuation model is used to estimate the distance between the user and the base station. Finally, it compares with the commonly used methods before to verify the advantages of this paper.

Contents . . . . . . . . . . . . . . . . . . . . . . . .vii
List of Tables . . . . . . . . . . . . . . . . . . . . . ix
List of Figures . . . . . . . . . . . . . . . . . . . . . x
Chapter 1. 緒論. . . . . . . . . . . . . . . . . . . . . 2
1.1 研究動機以及目的. . . . . . . . . . . . . . . . . . . 2
1.2 相關文獻. . . . . . . . . . . . . . . . . . . . . . . 3
1.3 論文架構. . . . . . . . . . . . . . . . . . . . . . . 3
Chapter 2. 理論基礎. . . . . . . . . . . . . . . . . . . . 4
2.1 K-平均聚類(K-means clustering) . . . . . . . . . . . . 4
2.2 Deep Denoising Autoencoder . . . . . . . . . . . . . 5
2.3 路徑對數衰減模型(Log-Distance Path Loss Model) . . . . 6
2.4 三角定位(Triangulation) . . . . . . . . . . . . . . . 7
2.5 決策樹(Dscision Tree) . . . . . . . . . . . . . . . . 9
Chapter 3. 系統架構與資料說明. . . . . . . . . . . . . . . 10
3.1 建構天氣資料分類器. . . . . . . . . . . . . . . . . . 11
3.2 建構訊號補償模型. . . . . . . . . . . . . . . . . . . 11
3.3 資料說明. . . . . . . . . . . . . . . . . . . . . . . 12
Chapter 4. 實驗環境及實驗設置. . . . . . . . . . . . . . . 15
4.1 無線電波訊號量測設置. . . . . . . . . . . . . . . . . 15
4.2 天氣資料量測設置. . . . . . . . . . . . . . . . . . . 16
4.3 量測環境設置. . . . . . . . . . . . . . . . . . . . . 20
Chapter 5. 實驗結果. . . . . . . . . . . . . . . . . . . 22
5.1 天氣資料分群數分析. . . . . . . . . . . . . . . . . . 22
5.2 天氣群集分類. . . . . . . . . . . . . . . . . . . . . 23
5.3 距離估測誤差. . . . . . . . . . . . . . . . . . . . . 23
Chapter 6. 結論與未來展望. . . . . . . . . . . . . . . . 30
Bibliography . . . . . . . . . . . . . . . . . . . . . . 31

[1] C.-Y. Chen, L.-P. Yin, Y.-J. Chen, and R.-C. Hwang, "A modied probability neural network indoor positioning technique," in International Conference on Information Security and Intelligence Control, pp. 317-320, 2012.

[2] K. Abrougui, A. Boukerche, and R. Pazzi, "Location-aided gateway advertise-ment and discovery protocol for VANets," IEEE Transactions on Vehicular Technology, vol. 59, no. 8, pp. 3843-3858, 2010.

[3] H. Saleet, O. Basir, R. Langar, and R. Boutaba, "Region-based location-service-management protocol for VANETs," IEEE Transactions on Vehicular Technol-ogy, vol. 59, no. 2, pp. 917-931, 2010.

[4] E. D. Kaplan and C. J. Hegarty Understanding GPS: principles and applica-tions, Artech house, 2005.

[5] S. A. Golden and S. S. Bateman, "Sensor measurements for Wi-Fi location with emphasis on time-of-arrival ranging," IEEE Transactions on Mobile Computing, vol. 6, no. 10, pp. 1185-1198, 2007.

[6] K. Lui, H. So, and W.-K. Ma, "Maximum a posteriori approach to time-of-arrival-based localization in non-line-of-sight environment," IEEE Transactions on Vehicular Technology, vol. 59, no. 3, pp. 1517-1523, 2010.

[7] E. Elnahrawy, J. Austen-Francisco, and R. Martin, "Adding angle of arrival modality to basic RSS location management techniques," Wireless Pervasive Computing, 2007.

[8] J. J. Caffery Jr, "A new approach to the geometry of toa location," Vehicular Technology Conference, vol. 4, pp. 1943-1949, 2000.

[9] K. Yang, J. An, X. Bu, and G. Sun, "Constrained total least-squares location algorithm using time-difference-of-arrival measurements," IEEE Transactions on Vehicular Technology, vol. 59, no. 3, pp. 1558-1562, 2010.

[10] A.Weiss, "On the accuracy of a cellular location system based on RSS measure-ments," IEEE Transactions on Vehicular Technology, vol. 52, no. 6, pp. 1508-1518, 2003.

[11] C. Feng, W. Au, S. Valaee, and Z. Tan, "Received-signal-strength-based indoor positioning using compressive sensing," IEEE Transactions on Mobile Computing, vol. 11, no. 12, pp. 1983-1993, 2012.

[12] J. Yang and Y. Chen, "Indoor localization using improved rss-based lateration methods," in GLOBECOM 2009 - 2009 IEEE Global Telecommunications Conference, pp. 1-6, Nov. 2009.

[13] M. Tamrakar, K. Bandyopadhyay, and A. De, "Comparison of rain attenuation prediction models with ku-band beacon measurement for satellite communication system," in 2010 International Conference on Signal Processing and Communications (SPCOM), pp. 1-5, July 2010.

[14] J. Goldhirsh, "A review on the application of nonattenuating frequency radars for estimating rain attenuation and space-diversity performance," IEEE Trans-
actions on Geoscience Electronics, vol. 17, pp. 218-239, Oct 1979.

[15] A. Hirata, R. Yamaguchi, H. Takahashi, T. Kosugi, K. Murata, N. Kukutsu,
and Y. Kado, "Effect of rain attenuation for a 10-gb/s 120-ghz-band millimeter-wave wireless link," IEEE Transactions on Microwave Theory and Techniques, vol. 57, pp. 3099-3105, Dec 2009.

[16] J. Nemarich, R. J. Wellman, and J. Lacombe, "Backscatter and attenuation by falling snow and rain at 96, 140, and 225 ghz," IEEE Transactions on Geoscience and Remote Sensing, vol. 26, pp. 319-329, May 1988.

[17] S. H. Fang and Y. H. S. Yang, "The impact of weather condition on radio-based distance estimation: A case study in gsm networks with mobile measurements," IEEE Transactions on Vehicular Technology, vol. 65, pp. 6444-6453, Aug 2016.

[18] M. O. Odedina and T. J. O. Afullo, "Rain attenuation prediction along terrestrial paths in south africa using existing attenuation models," in AFRICON 2007, pp. 1-7, Sept 2007.

[19] L. S. Kumar, Y. H. Lee, and J. T. Ong, "Slant-path rain attenuation at different elevation angles for tropical region," in 2009 7th International Conference on
Information, Communications and Signal Processing (ICICS), pp. 1-4, Dec 2009.

[20] L. D. Emiliani, J. Agudelo, E. Gutierrez, J. Restrepo, and C. Fradique-Mendez, "Development of rain-attenuation and rain-rate maps for satellite system de-
sign in the ku and ka bands in colombia," IEEE Antennas and Propagation Magazine, vol. 46, pp. 54-68, Dec 2004.

[21] D. Roddy satellite communications, fourth edition., 2006.

[22] L. Ippolito Radiowave propagation in satellite communications., Van Nostrand Reinhold, 1986.

[23] R. Olsen, D. Rogers, and D. Hodge, "The arbrelation in the calculation of rain attenuation," IEEE Transactions on Antennas and Propagation, vol. 26, pp. 318-329, March 1978.

[24] Y. Okumura, E. Ohmori, T. Kawano, and K. Fukuda, "Field strength and its variability in vhf and uhf land-mobile radio service," Rev. Elec. Commun. Lab, vol. 16, no. 9, pp. 825-73, 1968.

[25] J. Deng, Z. Zhang, F. Eyben, and B. Schuller, "Autoencoder-based unsupervised domain adaptation for speech emotion recognition," IEEE Signal Processing Letters, vol. 21, pp. 1068-1072, Sept 2014.

[26] C. Hong, J. Yu, J. Wan, D. Tao, and M. Wang, "Multimodal deep autoencoder for human pose recovery," IEEE Transactions on Image Processing, vol. 24, pp. 5659-5670, Dec 2015.

[27] V. Miranda, J. Krstulovic, H. Keko, C. Moreira, and J. Pereira, "Reconstructing missing data in state estimation with autoencoders," IEEE Transactions on Power Systems, vol. 27, pp. 604-611, May 2012.

[28] 維基百科, "語意分析," 2015.

[29] P. M. Santos, T. E. Abrudan, A. Aguiar, and J. Barros, "Impact of position errors on path loss model estimation for device-to-device channels," IEEE Transactions on Wireless Communications, vol. 13, pp. 2353-2361, May 2014.

[30] C. R. Anderson, H. I. Volos, and R. M. Buehrer, "Characterization of low-antenna ultrawideband propagation in a forest environment," IEEE Transactions on Vehicular Technology, vol. 62, pp. 2878-2895, Sept 2013.

[31] R. Sun and D. W. Matolak, "Characterization of the 5-ghz elevator shaft channel," IEEE Transactions on Wireless Communications, vol. 12, pp. 5138-5145, October 2013.

[32] C. Wang, L. Wang, X. Chi, S. Liu, W. Shi, and J. Deng, "The research of indoor positioning based on visible light communication," China Communications, vol. 12, pp. 85-92, August 2015.

[33] F. Barba, A. G. Martin, and A. Fernandez-Duran, "Wireless indoor positioning: Effective deployment of cells and auto-calibration," Bell Labs Technical Journal, vol. 18, pp. 213-235, Sept 2013.

[34] S. Taha and X. Shen, "A physical-layer location privacy-preserving scheme for mobile public hotspots in nemo-based vanets," IEEE Transactions on Intelligent Transportation Systems, vol. 14, pp. 1665-1680, Dec 2013.

[35] X. Chen, D. Schonfeld, and A. A. Khokhar, "Localization and trajectory estimation of mobile objects using minimum samples," IEEE Transactions on Vehicular Technology, vol. 58, pp. 4439-4446, Oct 2009.