Transfer Learning for Automatic Modulation Recognition Using a Few Modulated Signal Samples
Wensheng Lin, Dongbin Hou, Junsheng Huang, Lixin Li, Zhu Han
Abstract
This letter proposes a transfer learning model for automatic modulation recognition (AMR) with only a few modulated signal samples. The transfer model is trained with the audio signal UrbanSound8K as the source domain, and then fine-tuned with a few modulated signal samples as the target domain. For improving the classification performance, the signal-to-noise ratio (SNR) is utilized as a feature to facilitate the classification of signals. Simulation results indicate that the transfer model has a significant superiority in terms of classification accuracy.
Topics & Concepts
SIGNAL (programming language)Transfer of learningComputer scienceModulation (music)Pattern recognition (psychology)Artificial intelligenceFeature (linguistics)Speech recognitionSignal-to-noise ratio (imaging)Domain (mathematical analysis)Noise (video)Feature extractionTime domainFrequency domainFrequency modulationRadio frequencyAcousticsTelecommunicationsComputer visionMathematicsPhysicsImage (mathematics)LinguisticsPhilosophyProgramming languageMathematical analysisWireless Signal Modulation ClassificationAnimal Vocal Communication and Behavior