Spectrum Classification Application

Introduction

The goal of this project is to create an application that will run on a receiver node and processes signals. It will take the received signal as an input, analyze the components and details of the signal, and classify the signal based on the analysis. This will require machine learning techniques to perform the classification.

The program will receive signals, determine what modulation scheme was used to modulate the signal, and then demodulate the signal with the found scheme. This can also be expanded to creating a modem that will also choose the best modulation scheme to modulate a signal depending on the SNR of the given range of wireless frequencies.

Background

​Brief Summary of Project

To recognize the modulation scheme of the modulated signal received, we will train a classifier by using training data that encompasses many signals modulated with varying modulation schemes. Then, we will test the classifier using signals created from GNU Radio to confirm that it works properly. In practice, it will be running on an ORBIT node and receiving at a given frequency, try to determine if the given signals are just noise, and will demodulate any determined signals.

Tools Used

Classifier - TensorFlow - Gives us a neural network library for smarter machine learning algorithms Signal Training Data - ​RadioML Dataset Testing Data - GNURadio - Comes with SDR Toolkit to send, receive, and plot signals

Presentations

​Week One

​Week Two

​Week Three

​Week Four

The Team

Avanish Mishra Brendan Bruce