جستجوی مقالات مرتبط با کلیدواژه "clutter" در نشریات گروه "فناوری اطلاعات"

Clutter usually has negative influence on the detection performance of radars. So, the recognition of clutters is crucial to detect targets and the role of clutters in detection cannot be ignored. The design of radar detectors and clutter classifiers are really complicated issues. Therefore, in this paper aims to classify radar clutters. The novel proposed MLP-based classifier for separating radar clutters is introduced. This classifier is designed with different hidden layers and five training algorithms. These training algorithms consist of Levenberg-Marquardt, conjugate gradient, resilient backpropagation, BFGS and one step secant algorithms. Statistical distributions are established models which widely used in the performance calculations of radar clutters. Hence In this research, Rayleigh, Log normal, Weibull and K-distribution clutters are utilized as input data. Then Burg‟s reflection coefficients, skewness and kurtosis are three features which applied to extract the best characteristics of input data. In the next step, the proposed classifier is tested in different conditions and the results represent that the proposed MLP-based classifier is very successful and can distinguish clutters with high accuracy. Comparing the results of proposed technique and RBF-based classifier show that proposed method is more efficient. The results of simulations prove that the validity of MLP-based method.

Due to the complex physical properties of the detected targets using sonar systems, identification and classification of the actual targets is among the most difficult and complex issues of this field. Considering the characteristics of the detected targets and unique capabilities of the intelligent methods in classification of their dataset, these methods seem to be the proper choice for the task. In recent years, neural networks and support vector machines are widely used in this field. Linear methods cannot be applied on sonar datasets because of the existence of higher dimensions in input area, therefore, this paper aims to classify such datasets by a method called Online Multi Kernel Classification (OMKC). This method uses a pool of predetermined kernels in which the selected kernels through a defined algorithm are combined with predetermined weights which are also updated simultaneously using another algorithm. Since the sonar data is associated with higher dimensions and network complexity, this method has presented maximum classification accuracy of 97.05 percent. By reducing the size of input data using genetic algorithm (feature selection) and statistical moments (feature extraction), eliminating the existing redundancy is crucial; so that the classification accuracy of the algorithm is increased on average by 2% and execution time of the algorithm is declined by 0.1014 second at best.