Automatic Modulation Recognition in OFDM Systems using Cepstral Analysis and a Fuzzy Logic Interface Rasha M. Al-Makhlasawy, Mustafa M. Abd Elnaby,Heba A.El-Khobby Electronics and Electrical Communications dept. Faculty of Engineering, Tanta University Tanta, Egypt. E-mails: eng_rasha_mostafa@yahoo.com, mnaby@yahoo.com, h_khobby@yahoo.com F. E. Abd El-Samie Electronics and Electrical Communications dept. Faculty of Electronic Engineering, Menoufia University, Menouf, 32952,Egypt. E-mail: fathi_sayed@yahoo.com Abstract— Modulation type is one of the most important characteristics used in signal waveform identification for wireless communications. In this paper, a cepstral algorithm for Automatic Digital Modulation Recognition (ADMR) is proposed with adaptive modulation in Orthogonal Frequency Division Multiplexing (OFDM) systems. The proposed algorithm is verified using classifiers for the modulated signals. This algorithm uses Mel Frequency Cepstral Coefficients (MFCCs) to extract the features of the modulated signal and a multi-layer feed-forward neural network to classify the modulation type and its order. The proposed classifier is capable of recognizing the modulation scheme with high accuracy over a wide Signal-to- Noise Ratio (SNR) range in the presence of Additive White Gaussian Noise (AWGN). As the demand of high-quality service in next-generation wireless communication systems increases, a high performance of data transmission requires an increase in spectral efficiency and an improvement in error performance of wireless communication systems. One of the promising approaches to 4G is Adaptive OFDM (AOFDM). In AOFDM, an adaptive transmission scheme is employed according to the channel fading conditions to improve the performance. The performance of adaptive modulation systems depends on the decision-making logic. Adaptive modulation systems using hardware decision-making circuits are inefficient to decide or change the modulation scheme according to the given conditions. Using a fuzzy logic in the decision-making interface makes the system more efficient. Keywords- ADMR, MFCCs, Fuzzy logic. I. INTRODUCTION Automatic identification of the digital modulation technique is an essential step in the interception process. It has wide military applications including electronic warfare, surveillance, and threat analysis [1]. Automatic recognition plays an important role in other civilian applications due to its capability of placing several receivers in one universal receiver. These systems contain two main processes; feature extraction and classification. Feature extraction extracts a small amount of data from the signal. There are various techniques for extracting signal features such as the MFCCs technique. The MFCCs are not robust enough in noisy environments. This problem is solved by extracting MFCCs from transform domains rather than the time domain [2]. Transforms such as the Discrete Cosine Transform (DCT) and the Discrete Sine Transform (DST) enjoy a sophisticated energy compaction property, which can be efficiently utilized for feature extraction. Another popular transform; the Discrete Wavelet Transform (DWT), decomposes the signal into subbands leading to distinguishing features for each subband [3]. In this paper, we study the MFCCs to extract the classification features in the adaptive modulation case. Our proposed classifier is a multi-layer feed-forward neural network trained using the resilient back-propagation learning algorithm. This classifier has the capability of recognizing the M-ary Amplitude Shift Keying (M-ASK), M-ary Frequency Shift Keying (M-FSK), Minimum Shift Keying (MSK), M-ary Phase Shift Keying (M-PSK), and M-ary Quadratic Amplitude Modulation (M-QAM) signals and the order of the identified modulation. The performance of the proposed algorithm is examined based on False Recognition Probability (FRP). The AWGN channel is considered when developing the mathematical model and through most of the results. OFDM is a special form of multi-carrier transmission techniques in which a single high-rate data stream is divided into multiple low-rate data streams. These data streams are then modulated using sub-carriers, which are orthogonal to each other. In this way, the symbol rate on each sub-channel is greatly reduced, and hence the effect of Inter-Symbol Interference (ISI) due to channel dispersion in time caused by multipath delay spread is reduced. Therefore it is possible to improve performance of OFDM transmission by controlling such parameters of each sub-carrier optimally according to the channel characteristics and the additive noise [4], [5]. The 8th International Conference on INFOrmatics and Systems (INFOS2012) – 14-16 May Cloud and Mobile Computing Track Faculty of Computers and Information - Cairo University CC-56