Name
Title | ||
|---|---|---|
Detection of extremely weak NQR signals using stochastic resonance and neural network theories. |
Abstract | ||
|---|---|---|
•The proposed SRNN method is a combination of stochastic resonance and neural network, which effectively detects extremely weak NQR signals.•The SRNN method can detect a variety of NQR signals which have similar NQR parameters, which shows SRNNs good commonality, as well as robustness to the possible time-variation of NQR signal properties in real life settings.•The SRNN method also has good performance in the presence of interference.•We anticipate that the proposed SRNN method can be applicable to other problems of detecting weak signals under a similar framework. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1016/j.sigpro.2017.06.027 | Signal Processing |
Field | DocType | Volume |
Signal processing,Background noise,Detection theory,Control theory,Electronic engineering,Artificial intelligence,Stochastic resonance,Artificial neural network,Pattern recognition,Waveform,Nuclear quadrupole resonance,Mathematics,Feed forward | Journal | 142 |
Issue | ISSN | Citations |
C | 0165-1684 | 2 |
PageRank | References | Authors |
0.44 | 6 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Weihang Shao | 1 | 6 | 1.70 |
| Jamie Barras | 2 | 6 | 1.70 |
| Panagiotis Kosmas | 3 | 66 | 15.02 |