A comparison of different machine learning algorithms for automatic classification of sonar targets
A comparison of different machine learning algorithms for automatic classification of sonar targets
复制标题
声纳目标自动分类的不同机器学习算法的比较
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
T. S. Sastad
中科院分区：
文献类型：
--
作者：
H. Berg;K. Hjelmervik;D. H. S. Stender;T. S. Sastad
现代反潜声纳在波束宽度窄、频率带宽宽的情况下，经常出现虚警，特别是在沿岸的环境中。这增加了声纳操作员的工作量，也降低了自动系统（如自主水下航行器）的有用性，因为它们有限的通信能力阻碍了它们分享大量的联系。在本文中，四个传统的机器学习算法进行了测试声纳数据与大量的假警报与合成潜艇回波。结果表明，一些算法可以优于简单的信噪比（SNR）阈值的显着量，但性能是高度依赖于为每个算法选择的参数值。因此，研究这些参数，以确定其相对意义。
A well-known problem with modern anti-submarine warfare sonars with narrow beamwidths and wide frequency bandwidths, is the frequent occurence of false alarms, particularly in littoral environments. This increases the workload of sonar operators and also reduces the usefulness of automatic systems such as autonomous underwater vehicles, since their limited communication abilities hinder them from sharing large amounts of contacts. In this paper, four traditional machine learning algorithms are tested on sonar data with a high amount of false alarms together with synthetic submarine echoes. It is shown that some of the algorithms can outperform simple signal to noise ratio (SNR) thresholding by a significant amount, but that the performance is highly dependent on the parameter values chosen for each algorithm. These parameters are therefore investigated in order to determine their relative significance.