چكيده به لاتين
Small Drones (such as quadcopters, etc.) are becoming an important and growing part of our society. Small drones are used for Traffic monitoring , Geographical surveys, Sending postal items, Imaging, meteorological assessment, Spraying agricultural pesticides, Crisis management, Control of oil and gas and electricity transmission lines, Monitoring of forests and natural resources,Infrastructure inspection, Protection and security affairs, etc. Despite all these advantages, if the issue of drones safety is not taken seriously, they can easily be used for malicious purposes. Their presence in some areas, such as airports, crowded places, protected areas, power plants, nuclear facilities and even prisons, can cause great damage to these facilities. In such cases, an efficient detection system to detect and alert the presence of drones is very necessary. Small drones are usually too small for radar and this method takes a lot of time and has a lot of errors. Other traditional methods, such as sound and heat, also have a lot of errors.Therefore, there is a need for a powerful method to solve this problem, and the use of Radio Frequency (RF) signals is one of the most accurate methods to solve this problem. In this Dissertation, we investigate the methods of Drone Detection and identification Systems using one of the most widely used machine learning algorithms (support vector machine). These models have been made by entering the data obtained from the spectrum of the RF radio frequency signal of three types of common Drones into the Support Vector Machine Algorithm. Finally, by using the analysis outputs of this algorithm, the presence or absence, the type of Drones and the operational mode(On and connected to a flight controller, hovering, flying without video recording, and flying with video recording) have been separated and identified with high accuracy.