Blind Modulation Recognition in Wireless MC-CDMA Systems Using a Support Vector Machine Classifier

Abstract

<p align="justify"> <span style="font-family:verdana;">Automatic Digital Modulation Recognition (ADMR) is becoming an interesting problem with various civil and military applications. In this paper, an</span><span> </span><span style="font-family:verdana;">ADMR</span><span> </span><span style="font-family:verdana;">algorithm in Multi-Carrier Code Division Multiple Access (MC-CDMA) systems using Discrete Transforms (DTs) and Mel-Frequency</span><span> </span><span style="font-family:verdana;">Cepstral Coefficients (MFCCs)</span><span> </span><span style="font-family:verdana;">is proposed.</span><span> </span><span style="font-family:verdana;">This</span><span> </span><span style="font-family:verdana;">algorithm uses</span><span> </span><span style="font-family:verdana;">various DT techniques such as the Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Discrete Sine Transform (DST) with MFCCs to extract features from the modulated signal and a</span><span> </span><span style="font-family:verdana;">Support Vector Machine</span><span> </span><span style="font-family:verdana;">(SVM) to classify the modulation orders. The</span><span> </span><span style="font-family:verdana;">proposed algorithm avoids over fitting and local optimal problems that appear in Artificial Neural Networks (ANNs). Simulation results shows the classifier is capable of recognizing the modulation scheme with high accuracy up to 90%</span><span> </span><span style="font-family:verdana;">-</span><span> </span><span style="font-family:verdana;">100% using DWT, DCT and DST for some modulation schemes</span><span> </span><span style="font-family:verdana;">over a wide Signal-to-Noise Ratio (SNR) range in the presence of Additive White Gaussian Noise (AWGN) and Rayleigh fading channel, particularly at a low Signal-to-Noise ratios (SNRs).</span> </p

Sparse Matrix Based Low-Complexity, Recursive, and Radix-2 Algorithms for Discrete Sine Transforms

“…Similarly, the duality theorem proposed in [21], [22] now allows for the avoidance of calculating the inverse DST (IDST) in applications where similar signals are commonly encountered. Recently, the DST has expanded to applications including underwater signal transmission [23], [24], analysis and noise estimation of speech [25], finite impulse response (FIR) frequency filtering [26], and feature extraction of modulated signals in orthogonal frequency division multiplexing (OFDM) systems [27]. Similarly, the noise filtering capabilities have led to a new DST-based approach to measuring the volatility of stock prices [28], [29].…”

“…the weight matrix is congregated in(26) as opposed to scattered weight matrices in (14), (b). the weight matrix W Q S I in (2) was factored into the product of permutation and odd/even weight matrices in(27), (c). the matrix G S I in (29) has been simplified and factored into the product of sparse and diagonal matrices as opposed to the matrix G S I in (7), (d).…”