Channel Prediction
We can use channel_prediction.py to predict what the underlying distribution of the channel is (either Rayleigh or Rician). To do this run the following command:
Where Ric1.dat is the input file and the generated image is stored as output.jpg
For this we first compute the histogram of the data by using Numpy library and then smooth this using a moving average filter and plot this. Then using the SciPy library, we first do a parameter estimation for both Rayleigh and Rician distributions. Using these estimated parameters we plot the analytical expressions of both Rayleigh and Rician distribution in the same image as before. We thus can visually judge which distribution fits the data more by looking at output.jpg.
However, since we want a more accurate measure, we do a error analysis and compute the Mean Absolute Error (MAE) and Mean Squared Error (MSE) between the histogram and the two distributions and these errors are shown in the console for us to see how close it is to the distributions. Finally based on the MAE, the prediction is made (the lower MAE class is the predicted channel).
Last updated