在這篇論文中，我們討論多訊源無線感測網路的分散式結合估計問題。在多訊源無線感測網路中，包含有一個負責估計的資料收集中心，與多個負責觀測和量化的感測器，每個感測器將感測到不定個數訊源所組成的結合訊號；我們設計在資料收集中心的估計法，並調整感測器端的量化函數。假設每個感測器只能傳送一個符號給資料收集中心，且此傳送過程為理想通道，而討論此情況下位於資料收集中心的多訊源結合估測函數。我們先推導出在集中式無線感測網路中所適用的最大適然法則估計子，並使用最大期望演算法作出可行的結合估計演算；而後考慮在經過分散式感測節點之量化影響下，如何引用前述結果。由結果發現，當系統的感測訊噪比越大時，強制引用集中式感測的結合估測結果並不可行，且運算過於困難，依此對原始的最大期望演算法提出一種修正運算以對抗量化雜訊，在高訊噪比的情況下減少因量化而對估測產生的不良影響，使我們提出的方法較傳統的方式可以得到較低的均方差。

In this work, a joint distributed estimation problem for multiple source wireless sensor network is considered. A wireless sensor network involves numbers of sensors and a fusion center. We design the estimation algorithm in the fusion center, and minimize the quantization effect to improve the performance of estimator. Let each sensor observe some combined signal from different source, quantize these row data into a finite symbol set, and transmit a finite number of bits to the fusion center. We consider the observation noise distribution is Gaussian, and ideal backward communication channels. First, we design a feasible joint maximum-likelihood (ML) estimator for centralized sensor network to avoid searching estimation result in infinite space. Second, we apply this estimator to our decentralized environment. In conclusion, we modify our algorithm to reduce the bad effect of quantization. The proposed method has better performance, or we say less mean square error (MSE), than the conventional one.

[1] I. F. Akyidiz, W. Su., Y. Sankarasubramaniam, and E.
Cayirci, “A Survey on Sensor Network,” IEEE Comm.
Mag., vol 40, no. 8, pp. 102 – 114, Aug. 2002.
[2] Jos□ M. F. Moura, Jin Lu, and Marius Kleiner,
“Intelligent Sensor Fusion: A Graphical Model
Approach,” IEEE Inter. Conf. on Acoustic, Speech,
and Signal Process., vol 6, VI-733-6, Apr 2003.
[3] Jin-Jun Xiao, Shuguang Cui, Zhi-Quan Luo, and Andrea
J. Goldsmith, “Power Scheduling of Universal
Decentralized Estimation in Sensor Network,” IEEE
Trans. Signal Process., vol. 54, no. 2, May 2006.
[4] Z. Q. Luo and J. –J. Xiao, “Decentralized Estimation
in an Inhomogeneous Sensing Environment,” IEEE Trans.
Inf. Theory, vol. 51, no. 10, pp. 3564-3575, Oct.
2005.
[5] Tuncer C. Aysal and Kenneth E. Barner, “Blind
Decentralized Estimation for Bandwidth Constrained
Wireless Sensor Networks,” IEEE Trans. Wireless Comm.,
val. 7, no. 5, pp. 1466-1471, 2008
[6] Leung H., Chandana S., and Shuang Wei, “Distributed
Sensing Based on Intelligent Sensor Network,” IEEE
Circuits and Systems Magazine, 8(2), pp. 38-52, 2008.
[7] S. Chandana, H. Leung, and J. Levy, “Disaster
Management Model Based on Modified Fuzzy Cognitive
Maps,” Proc. IEEE Intl. Conf. Systems, Man and
Cybernetics, pp. 392-397, 2007.
[8] Frank R. Kschischang, Brendan J. Frey, and Hans-
Andrea Loeliger, “Factor Graphs and the Sum-Product
Algorithm,” IEEE Trans. Inf. Theory, vol. 47, no. 2,
pp. 498 – 519, Feb. 2001
[9] H.-A. Loeliger, “An Introduction to Factor Graphs,”
IEEE Signal Proc. Mag., vol. 21, pp. 28 – 41, Jan.
2004.
[10] Dempster A.P., Lard N.M., and Rubin D.B., “Maximum
Likelihood from Incomplete Data via the EM
Algorithm,” Journal of the Royal Statistical
Society, Series B, 39, 1-38
[11] Jeffrey A. Fessler and Alfred O. Hero, “Space-
Alternating Generalized Expectation-Maximization
Algorithm,” IEEE Trans. Signal Process., vol. 42,
no. 10, pp. 2664 - 2677, Oct 1994.
[12] R. G. Gallager. “Low-Density Parity Check Codes,”
No. 21 in Res. Mongraph Series. Cambrige, MA: MIT
Press, 1963.
[13] T. Richardson and R. Urbanke, “The Capacity of Low
Density Parity Check Codes Under Message-Passing
Decoding,” IEEE Trans Inf. Theory, vol. 47, pp.
599-618, Feb 2001.
[14] Mestdagh D., Spruyt P., and Biran B., “Effect of
amplitude clipping in DMT-ADSL transceivers,”
Electronics Letters, vol. 29, no. 15, 22nd July
1993.
[15] Henning Ehm, Sebastian Winter, and Robert Weigel
“Analytic Quantization Modeling of OFDM Signals
Using Normal Gaussian Distribution”, 2006 APMC
(Asia-Pacific Microwave Conference), pp. 847-850,
Dec. 2006.