Combining Principal Component Analysis Methods and Self-Organized and Vector Learning Neural Networks for Radar Data

The primary task of systems with real-time signal processing is to identify radars in the operating environment and to classify them based on prior system learning and to perform high-speed, real-time operations, especially where the received signal is an immediate threat such as missiles and requires war systems. Electronics should respond as soon as possible as an alarm. The purpose of this study is to use the results of this research to classify the information extracted by radar interception systems, which is achieved after the input signal selection stage and the correct selection of classification algorithms, and the other is accelerated by the learning vector quantization method. In this paper, we have presented a numerical method called a learning vector quantization, a method for data retrieval. In this method, the neural network algorithms are first organized to generate the required coding, and in the next step the digital vector learning algorithms will be created to retrieve the data. In this article, we will also consider each database benchmark. The implications of the usual implementation of universal command and control practices and their use of conventional restraint methods are a clear indication.

Keywords:

LVQ , SOM , PCA , radar