Target Detection in Unbalanced Doppler Radar Data Using Convolutional Neural Network

The protection of critically important military and civil settlements resumes its importance today as in the past. For this purpose, systems with various sensors are being developed. Extracting information from the data provided by the sensors is also important for the most efficient use of the hardware. Radar systems are frequently used for reconnaissance, surveillance and detection purposes. There are rule-based and machine learning-based methods for the classification of objects detected by radar. In machine learning-based approaches, the characteristics of the target object are learned by the model over time without the need for expert opinion. For this reason, these methods are more advantageous than rulebased methods. In this study, target classification was made on unstable Doppler Radar data in order to distinguish UAVs from other objects. In experimental studies, the highest performance was obtained in the data set balanced using SMOTE, and %99,99 accuracy was achieved with the proposed CNN model.