Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/9272
標題: 應用分散式內核貝氏濾波實現室內定位之研究
Indoor Positioning With Distributed Kernel-Based Bayesian Filtering
作者: 蕭閔元
Hsiao, Ming-Yuen
關鍵字: 無線感測網路
Wireless Sensor Network
室內定位系統
支持向量迴歸
內核粒子濾波
Indoor Positioning System
Support Vector Regression
Kernel-Based Particle Filtering
出版社: 電機工程學系所
引用: [1] M. Sugano, T. Kawazoe, Y. Ohta, and M. Murata, “Indoor localization system using RSSI measurement of wireless sensor network based on ZigBee standard.”In Proc. IASTED Int. Conf.WSN, Jul. 2006, pp. 1-6. [2] B. S. Choi, et al., ”A hierarchical algorithm for indoor mobile robot localization using RFID sensor fusion”, IEEE Trans. Ind. Electron., vol. 58, no. 6, pp. 2226-2235, 2011. [3] H. Chen , Q. Shi , R. Tan , H. V. Poor and K. Sezaki, ”Mobile element assisted cooperative localization for wireless sensor networks with obstacles”, IEEE Trans. Wireless Commun.,vol. 9, no. 3, pp. 956-963, 2010. [4] H. Guo , K. S. Low and H. A. Nguyen, “Optimizing the localization of a wireless sensor network in real time based on a low-cost microcontroller”, IEEE Trans. Ind. Electron., vol. 58,no. 3, pp. 741-749, 2011. [5] A. Dhital et al., “Bayesian filtering for indoor localization and tracking in wireless sensor networks,” EURASIP Journal on Wireless Communications and Networking, 2012, 2012:21. [6] Jie Wang, et al., “Toward Robust Indoor Localization Based on Bayesian Filter Using Chirp-Spread-Spectrum Ranging,” IEEE Transactions on Industrial Electronics, vol. 59, no. 3, pp. 1622-1629, March 2012. [7] J. Hightower and G. Borriello, “Particle Filters for Location Estimation in Ubiquitous Computing: A Case Study,” in Proc.of the Sixth International Conference on Ubiquitous Computing, pp. 88-106, Sep. 2004. [8] Gordon, N.; Salmond, D.; Smith, A. F. M. Novel approach to nonlinear/non-Gaussian Bayesian state estimation IEEE Proc. of Radar and Signal Processing 1993, 140, 107-113. [9] Yi-Chin Kuo, “An Integrated Mobile Sensor Platform for Collaborative Indoor Self-Positioning Applications. ” [10] N. Cristianini, J. Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, Cambridge University Press, Cambridge, 2002. [11] Kazuhiro Hotta, “Adaptive weighting of local classifiers by particle filters for robust tracking,” Pattern Recognition, vol. 42,no.5, pp. 619-628, May 2009. [12] B. Yin, et al., ”A novel particle filter method for mobile robot localization,” in Proc. of International Conference on Measuring Technology and Mechatronics Automation, pp. 269-272, 2010. [13] A. Yao, et al., “A compact association of particle filtering and kernel based object tracking,” Pattern Recognition, Volume 45Issue 7, pp. 2584-2597, July 2012. [14] Chang, Cheng and Sahai, Anant, “Cramer-Rao-type bounds for localization,” EURASIP Journal on Applied Signal Processing, Vol. 2006, Article ID 94287, pp. 1-13, 2006. [15] Yubin Zhao, Yuan Yang, and Marcel Kyas, “Dynamic Searching Particle Filtering Scheme for Indoor Localization in Wireless Sensor Network,” in Proc. of the 9th Workshop on Positioning Navigation and Communication (WPNC), pp. 65-70, 2012. [16] J. Luo, et al., “Non-interactive location surveying for sensor networks with mobility-differentiated ToA,” in Proc. IEEE INFOCOM, Barcelona, Spain, Apr. 2006, pp. 1-12. [17] MySQL, http://www.mysql.com. [18] Savvides, A.; Han, C.C.; Srivastava, M.B. Dynamic fine-grained localization in ad-hoc networks of sensors. In Proceedings of ACM SIGMOBILE, Rome, Italy, July 16-21, 2001; pp. 166-179. [19] V. Vapnik, The Nature of Statistical Learning Theory, Springer-Verlag, New York, 1995. [20] Kernel basis functions. http://people.revoledu.com/kardi/tutorial/Regression/KernelRegression/Kernel.htm [21] Gram Matrix, http://mathworld.wolfram.com/GramMatrix.html. [22] Mercer''s theorem, http://en.wikipedia.org/wiki/Mercer''s_theorem. [23] Sabri Boughorbel, Jean-Philippe Tarel, Nozha Boujema, "Conditionally Positive Definite Kernels For SVM Based Image Recognition". [24] Kernel Functions for Machine Learning Applications. http://crsouza.blogspot.tw/2010/03/kernel-functions-for-machine-learning.html [25] J. Polastre R. Szewczyk K. Whitehouse-A. Woo D. Gay J. Hill-M. Welsh E. Brewer P. Levis, S. Madden and D. Culler. ”tinyos: An operating system for wireless sensor networks.”. In Ambient Intelligence Springer-Verlag,2004. [26] Hanback Electronics. http://www.hanback.cn/. [27] Kim S.H Yun S.U, Youk Y.S. ”study on applicability of self-organizing maps to sensor network.”. In Proc. of International Symposium on Advanced Intelligent Systems, 2007. [28] D. Culler. ”the nesc language: a holistic approach to network embedded systems.”. In Proc. of the ACM SIGPLAN 2003 Conf. on Programming Language Design and Implementation (PLDI), June 2003. [29] H. Lim S. Han and J. Lee. ”an efficient localization scheme for a differential driving mobile robot based on rfid system.”. IEEE Trans. Ind. Electron, vol. 54, no. 6:pp. 3362–3369, 2007. [30] Yanping Cong Bo Yin, ZhiqiangWei and Tao Xu. ”a novel particle filter method for mobile robot localization”. in Proc. of 2010 International Conference on Measuring Technology and Mechatronics Automation, pages 269–272, 2010.
摘要: 在無線感測網路中,我們套用許多定位演算法在室內定位系統上。然而發現許多演算法的計算複雜度太高,不適合應用在感測器。舉例而言,粒子濾波演算法的先天的限制,造就粒子濾波器只能以少量的取樣點進行定位。伴隨而來的結果則是高定位誤差。因此,需擬定新定位計劃以提高定位準確度。本論文利用支持向量迴歸的觀念抑制估測錯誤,同時增強定位系統的可靠性,而創出內核粒子濾波演算法,此演算法主要遵循三個步驟:(1)初始支持向量迴歸估測、(2)內核重新加權,和(3)估測精緻化。實驗結果顯示此論文主要可利用少量取樣點即可達到優良的室內定位準確度,以及三顆參考點的KBPF演算之效能可匹配四顆參考點的KLF演算法定位效益。
In the wireless sensor network, several localization algorithms have been proposed for indoor positioning systems. However, the computational complexity of these schemes is high, which may not be suitable to be implemented in sensor nodes. For example, the limited sensor capabilities lead to performing the particle filtering with a very small set of samples, which results in high positioning errors. Hence, a novel sampling scheme may be required to improve estimation accuracy for the particle filter method. In this thesis, the concept of support vector regression (SVR) is conducted to suppress the estimation error, which enhances the reliability of the positioning system. Accordingly, we propose a Kernel-Based Particle Filtering (KBPF) algorithm, which consists of the following three steps: (1) Initial SVR Estimation; (2) Kernel-based Re-weighting; and (3) Estimation Refinement. The experimental results show that the proposed scheme can achieve good indoor positioning accuracy with a small number of samples and the performance of the proposed KBPF system using three beacons is comparable with that of the KLF system using four beacons.
URI: http://hdl.handle.net/11455/9272
其他識別: U0005-1908201315595200
文章連結: http://www.airitilibrary.com/Publication/alDetailedMesh1?DocID=U0005-1908201315595200
Appears in Collections:電機工程學系所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.