Classification of linear and nonlinear modulations using Bayesian methods

• Main Author: Puengnim, Anchalee
• Format: Others
• Published: 2008
• Online Access: http://oatao.univ-toulouse.fr/7730/1/puengnim.pdf

This thesis studies classification of digital linear and nonlinear modulations using Bayesian methods. Modulation recognition consists of identifying, at the receiver, the type of modulation signals used by the transmitter. It is important in many communication scenarios, for example, to secure transmissions by detecting unauthorized users, or to determine which transmitter interferes the others. The received signal is generally affected by a number of impairments. We propose several classification methods that can mitigate the effects related to imperfections in transmission channels. More specifically, we study three techniques to estimate the posterior probabilities of the received signals conditionally to each modulation. The first technique estimates the unknown parameters associated with various imperfections using a Bayesian approach coupled with Markov Chain Monte Carlo (MCMC) methods. A second technique uses the Baum Welch (BW) algorithm to estimate recursively the posterior probabilities and determine the most likely modulation type from a catalogue. The last method studied in this thesis corrects synchronization errors (phase and frequency offsets) with a phase-locked loop (PLL). The classification algorithms considered in this thesis can recognize a number of linear modulations such as Quadrature Amplitude Modulation (QAM), Phase Shift Keying (PSK), and nonlinear modulations such as Gaussian Minimum Shift Keying (GMSK)