摘要
浅海水声环境非常复杂,包含了各种各样的大量噪声干扰。根据水声检测器监测到的信号会被这些隐藏的异常信号干扰进而影响传输,同时也给有效信号的获取造成困难。盲分离技术可以模仿人的认知能力,通过不断迭代有效选择所关注的信号,被认为是解决该问题的有效途径。本文采用一种慢特性分析方法来解决浅海环境下非线性盲源分离问题,仿真实验的结果也进一步验证了本文方法的有效性,加快了收敛时间,提高效率。
The shallow sea acoustic environment is astoundingly complex,consisting of numerous noises. The signals detected by the hydrophones are disturbed by these inherent anomalies of the propagating medium and be a challenge to extract useful information from the mixtures of received signals. Blind Source Separation( BSS),which attempts to mimic the human cognitive capability of selectively extracting an interesting process amidst several similar competing processes,can be considered as a useful solution to the problem. In this paper,the effectiveness of Slow Feature Analysis( SFA) algorithm for solving the problem of nonlinear BSS is investigated. The experiment result shows the availability of this method with faster convergence speed and improved efficiency.
出处
《舰船科学技术》
北大核心
2016年第5X期73-75,共3页
Ship Science and Technology
基金
重庆市教育委员会科学技术研究项目(KJ132206)
关键词
盲源分离
浅海
非线性
blind source separation
shallow sea
nonlinear