2020 · 21 citations · 13 references
ComputingComputer ScienceElectrical EngineeringDigital CommunicationFeature EngineeringMachine LearningClassificationDeep LearningModulationNeural NetworksPattern RecognitionSupervised LearningAccuracyInterferenceInterference ClassificationInterference MitigationModulation ClassificationPower Spectral DensityPower Spectral Density AnalysisSignal Classification
Recent successes in supervised learning for modulation classification suggest that interference classification could similarly benefit from such approaches. This study proposes a deep neural network–based method for classifying interference types. The method trains a feed‑forward network on six synthetic interference types, using the received signal’s power‑spectral density and cyclic spectrum as input features. Experiments show that using the PSD yields higher accuracy than the cyclic spectrum, that feed‑forward networks outperform classic methods, and that the classifier can support downstream mitigation and integrate with modulation classification to improve overall accuracy.
The recent success in implementing supervised learning to classify modulation types suggests that other problems akin to modulation classification would eventually benefit from that implementation. One of these problems is classifying the interference type added to a signal-of-interest, also known as interference classification. In this paper, we propose an interference-classification method using a deep neural network. We generate six distinct types of interfering signals then use both the power-spectral density (PSD) and the cyclic spectrum of the received signal as input features to the network. The computer experiments reveal that using the received signal PSD outperforms using its cyclic spectrum in terms of accuracy. In addition, the same experiments show that the feed-forward networks yield better accuracy than classic methods. The proposed classifier aids the subsequent stage in the receiver chain with choosing the appropriate mitigation algorithm and also can coexist with modulation-classification methods to further improve the classifier accuracy.
13
Chih-Chung Chang, Chih‐Jen Lin · ACM Transactions on Intelligent Systems and Technology · 2011 · 41.3K citations
Least Squares Support Vector Machine Classifiers
Johan A. K. Suykens, Joos Vandewalle · Neural Processing Letters · 1999 · 9.4K citations · Full text
Statistical Digital Signal Processing and Modeling
Marvin H. J. Gruber, M.H. Hayes · Technometrics · 1997 · 2.2K citations
An analytical constant modulus algorithm
A. Paulraj · IEEE Transactions on Signal Processing · 1996 · 523 citations · Full text