Automatic modulation classification using techniques from image classification

Automatic Modulation Classification (AMC) is a rapidly evolving technology, which can be employed in software defined radio structures, especially 5G and 6G technology. Machine Learning (ML) provide novel efficient technology for modulation classification, systems working low signal to noise ratio (SNR). In this article, two dynamic not reliant on received phase lock frequency are presented, with both employing ML classify the types different SNR. The first model developed from previous existing literatures, utilises constellation images (CI) image classification Here, detected way without lock. second model, new method named Graphic Representation of Features (GRF) proposed, represents statistical features as spider graph ML. concepts tested verified using simulations RF data lab (SDR). results models compared. With GRF techniques an overall accuracy 59% observed 0 dB SNR 86% at 10 SNR, compared random guess 25%.