在本論文之中，我們討論了二種計算有效率的疊代方法。目前我們考慮使用在半靜態的通道下使用EM演算法來進行結合資料偵測和通道估測。在這裡，我們考慮了通道是否已知或未知和雜訊的變異數是否已知或未知的問題。在通道和雜訊的變異數都是未知的情況下，我們可以使用架構於SAGE演算法的方法來解決問題。在通道未知和雜訊的變異數已知的情況下，我們可以使用架構於EM演算法的另一個方法來解決問題。在完美通道資訊已知情況下，ML方法的模擬和這二個疊代的方法來做比較。而模擬結果可以發現這二個方法在通道資訊已知的條件下分別接近各自的ML方法。並且我們討論這二個疊代方法，哪一個方法的信號錯誤率效能比較佳。

In this thesis, we discuss two computationally efficient iterative methods from literature. We consider the problem of joint channel estimation and data detection under quasi-static channels now. Here, we consider the problems that channels and noise variance are known or unknown and known or unknown. When channels and noise variance are unknown, we use the method based on space-alternating generalized expectation-maximization (SAGE) algorithms. When channels are unknown and noise variances are known, we use the other method based on expectation-maximization (EM) algorithms. Bit error rate (BER) performance of the Maximum Likelihood (ML) method with perfect channel state information (CSI) is simulated and compared with BER performance of the two iterative methods. The results show that the two methods exhibit near ML performance with a few iterations and we want to know which is better.

CHAPTER 1 INTRODUCTION 1
1.1 THE EXPECTAION-MAXIMIZING ALGORITHM 3
1.2 THEHEORY OF THE EM ALGORITHM 6
1.3 THE MISSING IFORMATION 9
1.4 EM THEORY OF EXPONENTIAL FAMILIES 10
1.5 ALLLICATION OF EM ALGORITHM 11
1.6 THE MMSE ESTIMATOR 14
CHAPTER 2 SYSTEM MODEL 18
2.1 THE DSTRIBUTED DETECTION SYSTEM MODEL 18
2.2 DSTRIBUTED DETECTION IN SENSOR NETWORK 20
CHAPTER 3 THE PREVIOUS DDM SCHEME 23
3.1 DISTRIBUTED DETECTION FOR MARCODIVERSITY IN CELLULAR COMMUNICAION SYSTEMS 23
CHAPTER 4 THE DDM SCHEME 26
4.1 JOINT CHANNEL ESTIMATION AND DATA DETECTION 26
4.2 THE METHOD 2 31
CHAPTER 5 PEFORMANCE ANALYES AND SIMULATION RESULT 35
5.1 The BER PERFORMANCE OF THE METHOD 1 35
5.2 The BER PERFORMANCE OF THE METHOD 2 37
5.3 COMPARED THE METHOD 1 AND THE METHOD 2 38
5.4 The BER PERFORMANCE OF THE METHOD 1 AND THE METHOD 2 39
5.5 THE BER PERFORMANCE OF THE DDM SCHEME 42
5.6 COMPARED THE SCHEME WITH THE METHOD 1 AND THE METHOD 1 43
5.7 MSE OF THE CHANNEL ESTIMATORS THAT ARE OF THE METHOD 1 AND THE METHOD 2 45
5.8 MSE OF THE CHANNEL ESTIMATORS THAT ARE OF THE METHOD 1 AND THE METHOD 2 47

CHAPTER 6 THE CONSLUSION AND FURTURE WORK 49
6.1 CONSLUSION 49
6.2 FURTURE WORK 49

[1]. A. P. Dempster, N. M. Laird and D. B. Rubin, “Maximum Likelihood from Incomplete Data via the EM Algorithm,” J. Roy. Statist. Soc., vol.39, pp. 1-38, 1977.
[2]. L. A. Shepp and T. Vardi, “Maximum Likelihood Reconstruction for Emission Tomograph,” IEEE Trans. Med. Imaging, Vol. MI-1, pp. 113-122, 1982.
[3]. C. N. Georghiades and D. L. Snyder, “The Expectation-Maximization Algorithm for Symbol Unsynchornized Sequence Detection,” IEEE Trans. Commun., Vol. 36, No.1, pp. 54-61, 1991.
[4]. Feder and E. Weinstein, “Parameter Estimation of Superimposed Signals Using the EM Algorithm,” IEEE Trans. Acoust., Speech, Signal Process., vol. 36, No. 4, pp.477-489, 1988.
[5]. G. K. Kaleh and R. Vallet, “Joint parameter estimation and symbol detection for linear or on non-linear unknown channels,” IEEE Trans. Commun. vol. 42, pp. 2406-2413, Jul. 1994.
[6]. C. N. Georghiades and J. C. Han, “Sequence estimation in the presence of random parameters via the EM algorithm,” IEEE Trans. Commun., vol. 45, pp. 300–308, Mar 1997.
[7]. A. Kocian and B. H. Fleury, “EM-Based joint data detection and channel estimation of DS-CDMA signals,” IEEE Trans. Commun., vol. 51, pp. 1709–1120, Oct 2003.
[8]. T. A. Fesler and A. O. Hero, “Space-alternating generalized expectation- maximization algorithm,” IEEE Trans. Signal Processing, vol. 42, pp. 2664–2677, Oct 1994.
[9]. V. K. Garg, Wireless Network Evolution: 2G to 3G, Prentice Hall, 2001.
[10]. Roderick J. A. Little and Donald B. Rubin, Statistical Analysis with Missing Data, New York: John Wiley & Sons, 2002.
[11]. Rao, C. R., Linear Statistical Inference and Its applications, New York: Wiley.
[12]. Demster, A. P., Hall, B., Hall, R., and Rubin, D. B., Maximum likelihood estimation from incomplete data via the EM Algorithm, J. Roy. Statist. Soc. B39, 1-38, 1977.
[13]. Wu, C. F. J, On the convergence properties of the EM algorithm, Ann. Statist. 11, 95-103, 1983.
[14]. Steven M. Kay, Fundamentals of Statistical Signal Processing: Estimation Theory, 1997.
[15]. P.K. Varshney, Distributed Detection and Data Fusion, Springer-Verlag New-York, 1997.
[16]. R.S. Blum, “Distributed detection for diversity reception of fading signals in noise,” IEEE Transaction on Information Theory, vol. 45, no. 1, pp. 158–164, January 1999.
[17]. T. A. Fesler and A. O. Hero, “Space-alternating generalized expectation- maximization algorithm,” IEEE Trans. Signal Processing, vol. 42, pp. 2664–2677, Oct 1994.
[18]. The–Hanh Pham、 A. Nallanathan and Y.-C Liang, “Joint Channel Estimation and Data Detection for MIMO Systems: A SAGE-Based Approach,” Milltary Communications Conference, 2006. Milcom 2006. Oct. 2006 pp. 1 - 7