Deep-learning-for-Modulation-Recognition-on-RML2016.10a_dict-dataset

This project contains implementation of a deep learning model using a convolutional neural network (CNN) and Long short-term memory (LSTM) on radio modulation data. The project contains plot of 11 different modulations based on power spectrum and time domain in I/Q plane, for SNR=16. The variance of data is also plotted. The maximum accuracy obtained by the model is 0.66 in higher SNR. You can also see the confusion matrix of predicted against true labels, classification accuracy against signal to noise ratio is also plotted.