Conference Paper
Digital modulation recognition using support vector machine classifier
Dept. of Electr. & Comput. Eng., George Washington Univ., DC, USA
Conference: Signals, Systems and Computers, 2004. Conference Record of the ThirtyEighth Asilomar Conference on, Volume: 2 Source: IEEE Xplore

Conference Paper: Quickness of the instantaneous frequency based classifier distinguishing BFSK from QAM and PSK modulations
[Show abstract] [Hide abstract]
ABSTRACT: In this paper we study the quickness of a classifier based on simple feature that we have previously proposed to distinguish frequency from amplitudephase digital modulations. The feature is based on the product of two consecutive signal values and on time averaging of the imaginary part of the product. First, the conditional probability density functions of the feature given the present modulation are determined. The central limit theorem for strictly stationary mdependent sequences is used to obtain Gaussian approximations. Then thresholds are determined based on the minimization of the total probability of misclassification. Following that effects of carrier offsets, of fast fading, and of the symbol period and time delay being noninteger multiples of sampling period on the performance are studied. In the course of doing that, the proposed classifier is compared to the maximum likelihood classifier and the wavelet based classifier using support vector machine.2013 Asilomar Conference on Signals, Systems and Computers; 11/2013  IEEE Signal Processing Letters 04/2015; 22(5). · 1.64 Impact Factor

Conference Paper: Automatic content classification of digital modulation signals without binary sequence recovery
[Show abstract] [Hide abstract]
ABSTRACT: In this paper, we present a new classification method which aims to distinguish the contents of digital modulation signals without knowing about binary sequences. The differences of these binary sequences can be detected from the features extracted from their modulation signals directly. With the help of appropriately designed classifier, we can get the classification results in high accurate rates, and avoid the complex processing steps related with recovery of these binary sequences at the same time. We also provide an example and the method to deal with it in details. In numerical simulations, the mean probabilities of correct classification for signals we point out are more than 94%. And even in noisy conditions, the method is also effective.2012 11th International Conference on Signal Processing (ICSP 2012); 10/2012
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.