本研究之目標有二，目標一：試圖提出一套改善目前室內定位精準度之演算法。本研究利用卡爾曼濾波器（Kalman Filter，KF）的過濾能力來降低訊號干擾，再結合支持向量機（Support Vector Machine，SVM）之方法，用於改善使用類神經網路（Artificial Neural Network）預測不良之結果。本研究稱此方法為KF-SVM。目標二：試圖提出一套適用於多樓層定位設計之方法。多樓層定位有可能發送端佈置不當或數量過多導致不同樓層間訊號互相影響。本研究提出小範圍定位並結合轉換區域之概念以確定樓層。利用小範圍定位可以降低過多訊號導致定位不良，再以轉換區域解決樓層間相互干擾之問題。本研究採iBeacon作為實驗設備，並比較KF-SVM方法與類神經演算法之差異，透過三組實驗驗證KF-SVM演算精準度可高達85%以上，並且最大誤差至多2個區域（區域大小為1.2 平方公尺，區域間隔0.8平方公尺）。此外，本研究也驗證多樓層定位演算法之可行性。多樓層定位實作以KF-SVM為基礎並結合SVM的ONE-CLASS分類器，由於該分類器複雜度較低，從實驗結果顯示該分類器預測精準度可達90%以上。

This research has two objectives. The first objective is to propose an algorithm to improve the accuracy of indoor positioning. We reduce the signal by Kalman Filter. We also improve the correct prediction rate by Support Vector Machine. We named it as KF-SVM method. The second objective is to propose a method for Multi-Floor positioning. In Multi-Floor positioning, signals may affect each other from improper deployment or too many transmitting terminals. Hence a wrong floor may be positioned, especially when a user moves from one floor to another. We propose a concept of 'small area positioning ' with a changing area. We use small area positioning to overcome the challenge of too many transmitting terminals. With in a changing area, the problem of the interferences between different floors can be reduced. Hence, a good prediction could be achieved.
The experiments were based on Bluetooth Low Energy (BLE) devices. We compare the result of KF-SVM and Artificial Neural Network (ANN) algorithm. The accuracy is higher than 85% and the error area is at most two areas. Besides, in the evaluation of Multi-Floor positioning, the floor changing can be detected with the classifier in KF-SVM.

[1] C. J. C. Burges, "A Tutorial on Support Vector Machines for Pattern Recognition", Knowledge Discovery and Data Mining, vol.2, no.2, pp.121 -167, 1998
[2] C.-C. Chang and C.-J. Lin, LIBSVM: A Library for Support Vector Machines, 2001 [online] Available: http://www.csie.ntu.edu.tw/~cjlin/libsvm

[3] V. Chirakkal, M. Park and D. S. Han, "Indoor Navigation Using WiFi for Smartphones: An Improved Kalman Filter Based Approach," Proceedings of 2015 IEEE International Conference on Consumer Electronics(ICCE), 2015, pp.90-91
[4] Z. Farid, R. Nordin, and M. Ismail, "Recent Advances in Wireless Indoor Localization Techniques and System," Journal of Computer Networks and Communications, vol. 2013, p. 12, 2013, Article ID 185138, [online]
Available:http://dx.doi.org/10.1155/2013/185138.
[5] H. T. Friis, "Simple Transmission Formula, " Proceedings of IRE,vol. 34, 1946, pp.254 -256
[6] B. Li , A. G. Dempster , C. Rizos and J. Barnes , "Hybrid Method for Localization Using WLAN, "Proceedings of the International Conference on Spatial Intelligence, Innovation and Praxis,2006, pp.297–303
[7] C. H. Huang, L. H. Lee, C. C. Ho, L. L. Wu, and Z. H. Lai, "Real-Time RFID Indoor Positioning System Based on Kalman-Filter Drift Removal and Heron-Bilateration Location Estimation," IEEE Transactions on Instrumentation and Measurement, vol. 64, pp.728-739, 2014.
[8] H. Liu , H. Darabi , P. Banerjee and J. Liu, "Survey of Wireless Indoor Positioning Techniques and Systems", IEEE Transactions on Systems, Man, and Cybernetics, vol. 37, no. 6, pp. 1067-1080, Nov. 2007
[9] C.-W. Hsu , C.-C. Chang and C.-J. Lin , "A Practical Guide to Support Vector Classification, " [online] Available:
http://www.csie.ntu.edu.tw/~cjlin/papers/guide/guide.pdf.
[10] S. Kikuchi, S. Matsuyama, A. Sano, and H. Tsuji, "Subspace-Based Indoor Mobile Positioning Using Support Vector Regressor," Proceedings of 2006 IEEE 64th Vehicular Technology Conference, 2006, pp. 1-5.
[11] D. Qian and W. Dargie, "Evaluation of the Reliability of RSSI for Indoor Localization," Proceedings of 2012 International Conference on Wireless Communications in Unusual and Confined Areas (ICWCUCA), 2012, pp. 1-6.
[12] N. A. Razak, N. H. M. Arshad, R. Adnan, M. F. Misnan, N. M. Thamrin, and S. F. Mahmud, "A Study of Kalman's Filter in Embedded Controller for Real-Time Quadrocopter Roll and Pitch Measurement," Proceedings of 2012 IEEE International Conference on Control System, Computing and Engineering (ICCSCE),2012, pp. 590-595.
[13] D. Rajaveerappa and Fituri H. Belgassem, "A Two Ray Propagation Model for Finding Mobile Location over Plain Microcellular Environment," Proceedings of 2010 IEEE International Conference on Computer and Communication Technology (ICCCT-2010), Sept. 2010, pp. 408-414.
[14] R. Peng and M. L. Sichitiu, "Angle of Arrival Localization for Wireless Sensor Networks, "Third Annual IEEE Communications Society Conference on Sensor and Ad Hoc Communications and Networks, (Reston, VA), Sep. 2006, pp. 374-382.
[15] F. Subhan, H. Hasbullah, and K. Ashraf, "Kalman Filter-Based Hybrid Indoor Position Estimation Technique in Bluetooth networks," International Journal of Navigation and Observation, vol. 2013, p. 13, 2013, Article ID 570964,
[Online] Available: http://dx.doi.org/10.1155/2013/570964.
[16] V. Cherkassky and F. Mulier,Learning from Data: Concepts, Theory and Methods,2nd Edition ,Wiley-IEEE Press, United States of America.
[17] G. Welch and G. Bishop,"An Introduction to the Kalman Filter," Technical Report, University of North Carolina at Chapel Hill, 1995.
[18] W. Yapeng, Y. Xu, Z. Yutian, L. Yue, and L. Cuthbert, "Bluetooth Positioning Using RSSI and Triangulation Methods," Proceedings of 2013 IEEE Consumer Communications and Networking Conference (CCNC),2013, pp. 837-842.
[19] R.-C. Chen and Y.-H. Lin, "Using ZeeBee Sensor Network with Artifical Neural Network for Indoor Location," Proceedings of 2012 Eighth International Conference on Natural Computation (ICNC), 2012, pp. 290-294.
[20] H.-Q. Zhang, X.-W. Shi, L.-G. Cao, and G.-H. Deng, "A New Indoor Location Technology Using Back Propagation Neural Network and Improved Centroid Algorithm," 2012 31st Chinese on Control Conference (CCC), 2012, pp. 5460-5463.
[21] Neuroph , Java Neural Network Framework, 2009 [Online] Available：
http://neuroph.sourceforge.net/

[22] 王進德，類神經網路與模糊控制理論入門與應用，全華圖書2013年
[23] 林冠吉，基於訊號強度特徵值之手持裝置室內定位系統，碩士論文，通訊工程研究所，中正大學，2009年
[24] 曾光正，智慧型室內定位演算法之研究，碩士論文，電腦與通訊研究所，樹德科技大學，2010年
[25] 鄭傑撰，類神經網路室內定位方法之研究，碩士論文，電機工程學系研究所，義守大學，2011年
[26] 葉怡成，類神經網路模式應用與實作，儒林圖書，2009年