Skip to content

This project was undertaken as part of my Bachelors degree. My chosen subject area integrates the disciplines of both electronics engineering and computer science by using artificial intelligence to remove noise and distortion from telecommunications systems. This project is developed entirely in MATLAB.

License

Notifications You must be signed in to change notification settings

ryan-n-may/AI-Channel-Equalisation

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

AI-Channel-Equalisation

Using AI to equalise distortion and white noise in a multipath communications channel.

The Channel Model:

The channel model is a SISO system with QAM modulation in an OFDM system of 32 subcarriers.

channel

The Estimator:

The estimator model uses a 2 layered bi-lstm model connected via a fully-connected layer. This model estimates the time-domain time-varied channel response given the recieved signal data and the known transmission data.

estimator

The LSTM cell:

The LSTM cell is theoretically modelled as follows:

lstm

The Denoiser:

The purpose of the denoiser is to use a series of CNN layers, average pooling layers, and ReLU layers to remove of AWGN from the recieved signal. The recieved signal is over-sampled. The noise classification layer identifies noise in the received signal, and the denoiser layer removes noise from the recieved signal if noise is detected.

denoiser

The complete model:

The complete model combines estimation with noise removal.

completemodel

Performance:

Rayleigh channel simulation

channel simulation

Denoiser performance

Performance against AWGN & AWGN influenced channel estimation.

denoiser performance

The following is a visualisation of denoiser performance:

denoiser visualisation

Estimation performance against MMSE and LS

Performance in regard to MSE:

estimation performance

Performance in regard to SER:

estimation performance

Estimation accuracy at 5 dB:

50dB Accuracy

Estimation accuracy at 50 dB:

5 dB Accuracy

About

This project was undertaken as part of my Bachelors degree. My chosen subject area integrates the disciplines of both electronics engineering and computer science by using artificial intelligence to remove noise and distortion from telecommunications systems. This project is developed entirely in MATLAB.

Topics

Resources

License

Stars

Watchers

Forks