In the first part of this series, we introduced the general concepts needed for understanding the Hidden Markov Models Classifiers. Namely: Bayesian Logic, The concept of Bayesian Classifiers and Bayesian networks. All these notions are now grouped to form a new type of classifier which can accurately model and classify time-series data such as the RADAR data.

In this article we will explore a very special class of classifiers, the Hidden Markov Model Classifiers (HMMs). They are mainly a statistical and probabilistic model but they have found their entry in the world of Machine Learning since they can be trained and classify data.

The recent crash of Ukrainian Airlines Flight 752, downed by a surface-to-air (SAM) Iranian missile after a tragic human error from a military RADAR operator underlines dramatically the need for ADS-B, combined with automatic computer-based recognition of RADAR targets.

In this article we shall perform the anatomy of a simple but efficient convolutional network (CNN), the LeNet-1 neural network.

RADAR data classification mainly relies on convolutional neural networks. In this article, we shall detail and explain the main operations performed by Convolution networks in order to classify RADAR data.

A relevant technique to classify RADAR object is to use a colored 2D map representing range, speed or frequency against time and color the map with power intensity. Here we represent examples of such typical RADAR data.

Fast reaction and decision-making of the RADAR operator is a key factor in ATC. There is a need to develop techniques for the automatic extraction and fine-granulated classification of RADAR objects, allowing for faster and better decision making and more effective processes.

RADAR is short for RAdio Detection And Ranging. The principle of RADAR systems is not very difficult to understand. It is simply because most solid objects reflect radio waves, e.g., electromagnetic radiation with wavelengths superior to infrared. A RADAR therefore sends radio waves through an emitter and captures the “response”, e.g the reflecting signal through a receiver.

Deep Learning Algorithms produce better-than-human results in image recognition, generating a close to zero fault rate [1]. This article shows how this works in radar technology and explains, how Artificial Intelligence can be taught in University Education and NextGen ATC qualification.