Compact automatic modulation recognition using over-the-air signals and FOS features

The recent deployment of automatic modulation recognition (AMR) for cognitive radio (CR) systems has significantly enhanced spectrum sensing capabilities. utilization real-time over-the-air digital frequency (RF) data the development a model based on classification (AMC) is presented in this study as step incorporating opportunistic onto NomadicBTS architecture. Some techniques were studied second-generation (2G) through fourth-generation (4G) technology. raw RF signal dataset was digitized and curated, while non-complex first-order statistical (FOS) features used with algorithms Scaled conjugate gradient (SCG) Levenberg-Marquardt (LM) to find best learning algorithm generated AMR model. results show that developed very high likelihood correctly classifying signals, distinct patterns each FOS. are compared reveal least mean square error (MSE) 0.0131 maximum accuracy 93.5 percent when trained seventy (70) neurons hidden layer using LM method. model's will allow most precise identification holes bands under consideration.