Deep-Learning-based-Spectrum-Sensing

Use MATLAB to simulate the signal and extract features. Use PyTorch to build and train deep network to do spectrum sensing.

The files in MATLAB are used to simulate signal and extract features. Use cs_feature.m to receive QPSK signals in AWGN channels and extract cyclostationary features of different signal, and save the .mat data for training.

The files in Python are use to train deep networks. Build a dataset "dataset" containing two typs of signals, use SignalDataloader.py to load the data and use train.py to train a deep linear network, and calculate the probability of detection and the probability of falsealarm.