A Novel Method for Sea-Land Clutter Separation Using Regularized Randomized and Kernel Ridge Neural Networks



Zhang, Le, Thiyagalingam, Jeyan ORCID: 0000-0002-2167-1343, Xue, Anke and Xu, Shuwen
(2020) A Novel Method for Sea-Land Clutter Separation Using Regularized Randomized and Kernel Ridge Neural Networks. SENSORS, 20 (22). E6491-.

Access the full-text of this item by clicking on the Open Access link.
[img] Text
A Novel Method for Sea-Land Clutter Separation Using Regularized Randomized and Kernel Ridge Neural Networks.pdf - Published version

Download (639kB) | Preview

Abstract

Classification of clutter, especially in the context of shore based radars, plays a crucial role in several applications. However, the task of distinguishing and classifying the sea clutter from land clutter has been historically performed using clutter models and/or coastal maps. In this paper, we propose two machine learning, particularly neural network, based approaches for sea-land clutter separation, namely the regularized randomized neural network (RRNN) and the kernel ridge regression neural network (KRR). We use a number of features, such as energy variation, discrete signal amplitude change frequency, autocorrelation performance, and other statistical characteristics of the respective clutter distributions, to improve the performance of the classification. Our evaluation based on a unique mixed dataset, which is comprised of partially synthetic clutter data for land and real clutter data from sea, offers improved classification accuracy. More specifically, the RRNN and KRR methods offer 98.50% and 98.75% accuracy, outperforming the conventional support vector machine and extreme learning based solutions.

Item Type: Article
Uncontrolled Keywords: radar clutter classification, ECAV based feature extraction, KRR and RRNN, efficient and generalizing
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 16 Aug 2021 14:28
Last Modified: 18 Jan 2023 21:33
DOI: 10.3390/s20226491
Open Access URL: https://www.mdpi.com/1424-8220/20/22/6491
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3133702