Abstract | ||
---|---|---|
It is important for digital modulation identification based on neural network to determine a suitable size of a network. This paper proposes that the number of nodes in hidden layer which is the core for network optimizing can be confirmed by K-L transform. The validity and robustness are verified by simulation. The percentage of correct identification (PCI) is almost the same before and after the network optimizing. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/PDCAT.2005.171 | PDCAT |
Keywords | Field | DocType |
neural network,digital modulation identification,hidden layer,network optimizing,suitable size,k-l transform,correct identification,signal processing,covariance matrix,robustness,redundancy,neural networks,network topology | Signal processing,Computer science,Algorithm,Probabilistic neural network,Theoretical computer science,Modulation,Real-time computing,Robustness (computer science),Network topology,Time delay neural network,Artificial neural network,Network performance | Conference |
ISBN | Citations | PageRank |
0-7695-2405-2 | 1 | 0.37 |
References | Authors | |
2 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yonghong Kuo | 1 | 95 | 12.09 |
Jian Chen | 2 | 126 | 13.46 |
Xiaohua Tan | 3 | 4 | 1.71 |