1 Ali Asadi 1 and Behzad Mozaffari Tazehkand 2 University of Tabriz Faculty of Electrical and Computer Engineering University of Tabriz, Blvd. 29 Bahman, Tabriz, Iran 1 a_asadi89@ms.tabrizu.ac.ir, 2 mozaffary@tabrizu.ac.ir ABSTRACT In OFDM systems, it is necessary to estimate the channel to overcome the distortion caused by channel fading’s which can be induced by many phenomena such as: delay spread, multipath effect, mobility and Doppler shift. Most of the channel estimation techniques are proposed in frequency domain using the pilot symbols. One of them which has less complicated is well-known as Least-Squares (LS) method which is widely used in channel estimation but it is more sensitive to noise respected to the other reported techniques. In this paper, a new threshold based method using wavelet decomposition will be proposed which is based on an initial LS estimation technique. The reported simulation results show that the proposed method has better performance compared to the other methods such as Lee Method that has been published recently. KEYWORDS OFDM signal, Channel Estimation, Channel State (CS), Least Square (LS), Wavelet Transform, Cyclic Prefix, Channel Impulse Response 1 INTRODUCTION OFDM is a signaling technique that has been applied widely in wireless communication systems due to its ability to maintain effective transmission and highly efficient bandwidth utilization in the presence of various channel impairments which one of them is frequency- selective fading. In OFDM systems the available spectrum are divided into many orthogonal sub-channels, which are instantaneously used to data transmission. Also, in this technique the inter-symbol interference (ISI) which is induced due to frequency- selective channels can be reduced by adding the cyclic prefix (CP) [1]. In OFDM systems, channel estimation is necessary to obtain the channel state information (CSI), reducing the bit error rate and also to achieve a distortion less output data. There are various methods to channel estimation such as: with or without a need to parametric models, blind or pilot based methods, frequency and/or time domain analysis, adaptive or non adaptive techniques. Among these mentioned methods, channel estimation in OFDM systems is often done in frequency domain using pilot symbols or training data [2]. The least square and minimum mean-square error (MMSE) are conventional linear channel estimation techniques which are based on pilot arrangement. The LS method is less complicated and simple respect to other methods and consequently is used to channel estimation, but it has a serious drawback which is more sensitive to channel noise. MMSE estimator has better performance than LS method but suffers from a high computational complexity because it requires knowledge of the channel statistics and the signal-to-noise ratio (SNR) [3]. Some different methods have been developed to reduce the complexity and improve the performance of the MMSE estimation such as modified MMSE and singular value decomposition (SVD) [4-5]. 1n 2006 Noh et al. proposed a method to decomposing the covariance matrix to the A New Method to Channel Estimation in OFDM Systems Based on Wavelet Transform International Journal of Digital Information and Wireless Communications (IJDIWC) 3(1): 1-9 The Society of Digital Information and Wireless Communications, 2013 (ISSN: 2225-658X)