Classification of modulation signals using statistical signal characterization and artificial neural networks |
| |
Affiliation: | 1. SISSA/INFN, Via Bonomea 265, 34136 Trieste, Italy;2. CFTP, Departamento de Física, Instituto Superior Técnico, Universidade de Lisboa, Avenida Rovisco Pais 1, 1049-001 Lisboa, Portugal;3. Kavli IPMU (WPI), University of Tokyo, 5-1-5 Kashiwanoha, 277-8583 Kashiwa, Japan;1. Czestochowa University of Technology, Institute of Mathematics, al. Armii Krajowej 21, 42-200 Czestochowa, Poland;2. Czestochowa University of Technology, Institute of Computer and Information Sciences, ul. Dabrowskiego 73, 42-200 Czestochowa, Poland;1. Technical University of Ko?ice, Letná 9, 04120 Ko?ice, Slovakia;2. Budapest University of Technology and Economics, Budapest, Hungary |
| |
Abstract: | Modulation recognition systems have to be able to correctly classify the incoming signal modulation scheme in the presence of noise. A new method for classification of analogue and digital modulated signals at low signal-to-noise ratio (SNR) is introduced in this paper. This method uses the statistical signal characterization (SSC) to extract parameters to classify the different modulation signals. The SSC technique produces a set of four numerical parameters for a specific modulated signal. Subsequent comparison of these parameters to those of other waveforms provides the basis for our classification system. The results of SSC technique are applied to an artificial neural network (ANN) to have a robust classification system in the presence of noise down to SNR of 3 dB. No a priori information is required by this technique about the set of input waveforms. The input to the classification system can be analogue or digital signals or a combination of both. The proposed technique shows a 100% efficiency of classification of analogue signals or digital signals at SNR of 7 dB. This classification efficiency reduces to 83% and 86% for analogue or digital signals at SNR of 3 dB. The SSC technique shows better classification results in comparison with other techniques with an important advantage over other methods, which is the simplicity of the neural network needed with this technique due to the small number of features used in the classification. |
| |
Keywords: | |
本文献已被 ScienceDirect 等数据库收录! |
|