Name
Abstract | ||
|---|---|---|
Automated Modulation Classification (AMC) has been applied in various emerging areas such as cognitive radio (CR). In our paper, we propose a deep learning-based AMC method that employs Spectral Correlation Function (SCF). In our proposed method, one deep learning technology, Deep Belief Network (DBN), is applied for pattern recognition and classification. By using noise-resilient SCF signatures and DBN that is effective in learning complex patterns, we achieve high accuracy in modulation detection and classification even in the presence of environment noise. Our simulation results illustrate the efficiency of our proposed method in classifying 4FSK, 16QAM, BPSK, QPSK, and OFDM modulation techniques in various environments. |
Year | DOI | Venue |
|---|---|---|
2016 | 10.1109/ICCS.2016.7833571 | 2016 IEEE International Conference on Communication Systems (ICCS) |
Keywords | Field | DocType |
Modulation classification,Cognitive radio,Spectral correlation,Deep belief network | Quadrature amplitude modulation,Computer science,Deep belief network,Modulation,Speech recognition,Artificial intelligence,Deep learning,Orthogonal frequency-division multiplexing,Phase-shift keying,Cognitive radio | Conference |
ISBN | Citations | PageRank |
978-1-5090-3424-6 | 1 | 0.35 |
References | Authors | |
7 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Gihan J. Mendis | 1 | 43 | 3.35 |
| Jin Wei | 2 | 47 | 6.42 |
| Arjuna Madanayake | 3 | 242 | 53.31 |