On cluster validity indices with its application to interleaved radar pulse separation through fuzzy-based representation

详细信息    查看全文

• 作者：A. H. Mazinan
• 关键词：Interleaved radar ; Pulse separation ; Fuzzy ; based representation ; Cluster validation indices
• 刊名：Evolving Systems
• 出版年：2016
• 出版时间：December 2016
• 年：2016
• 卷：7
• 期：4
• 页码：243-254
• 全文大小：844 KB
• 刊物类别：Engineering
• 刊物主题：Artificial Intelligence and Robotics
  Complexity
  Statistical Physics, Dynamical Systems and Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1868-6486
• 卷排序：7

文摘

The present research describes an approach to radar pulse separation through a set of state-of-the-art cluster validity indices in association with fuzzy-based representation. Detection of a number of radars during the separation process is an important applicable issue, which needs to be investigated more in both real and academic environments. It is obvious that the fuzzy-based clustering approach may be known as one of the intelligent solutions regarding the interleaved radar pulse separation. In a word, the study considers the optimal number of clusters on the basis of the cluster validity indices that are useful to determine the radars. To consider the performance of the proposed approach, the whole of cluster validity indices are simulated though a series of experiments in some applicable scenarios in the area of interleaved radar pulse separation. The outcomes indicate that W-index is known as a suitable candidate to guarantee the better performance with high accuracy, while the fuzzy c-means technique is realized. In fact, a purposeful integration of the fuzzy c-means in association with W-index aims us to separate the interleaved radar pulse trains, efficiently. Subsequently, the effectiveness of the approach performance is verified by demonstrating its accuracy to be resulted as 96.71 %, while 10 % of additional pulse and 2 % of noise are included.