METHODS FOR IMPLEMENTING NEURAL NETWORK HYDROACOUSTICS ALGORITHMS BASED ON HETEROGENEOUS HARDWARE PLATFORM GRIFON

Author:

Alekseev G. G.1,Alekseeva E. A.1,Galagan P. V.1,Sorokin A. P.1,Sorokin S. А.1

Affiliation:

1. M. A. Kartsev  Computing  System  Research  and  Development  Institute  (NIIVK,  JSC)

Abstract

Recently, there has been an increase of interest in creating new neural network hydroacoustics algorithms, for example, test sites  in the Arctic are being created to evaluate the effectiveness of target detection and to ensure the safety of the Canadian North.  The open architecture allows you to adapt hardware to new threats or economic interests. Not only the equipment of radiation and  reception of hydroacoustic systems is improved, but also their processing. The article discusses the ways of improvement and the  principles of building specialized computers based on the GRIFON hardware platform, providing control and signal processing  in mobile and stationary sonar systems. We consider an example of creating a complex that demonstrates the capabilities of  the equipment and the prospects for creating calculators with high parameters and minimal mass‑dimensional characteristics.  Described in detail the structure and principles of the mathematical software of specialized computer. Comparative characteristics  of the proposed algorithms that can be used to optimize signal processing paths and the volume of digital equipment are given.

Publisher

CRI Electronics

Subject

General Medicine

Reference11 articles.

1. Chen S. China’s plan to use artificial intelligence to boost the thinking skills of nuclear submarine commanders. Available at: http://www.scmp.com/news/china/society/article/2131127/chinas-plan-use-artificial-intelligence-boost-thinking-skills (accessed 20.01.19).

2. Keipon J. Spatio-temporal spectral analysis with high resolution. TIIER, 1969, vol. 57, no. 8, pp. 69–79. (In Russian).

3. Borgiotti G. V., Kaplan L. J. Superresolution of uncorrelated interference sources by using adaptive array technique. IEEE Trans. Antennas Propagation, 1979, AP-27, pp. 842–845.

4. Lagunas M. A., Gasull A. An improved maximum likelihood method for power spectral density estimation. IEEE Trans. Acoustic, Speech and Signal Processing, 1984, ASSP-32, pp. 170–173.

5. Schmidt R. Multiple emitter location and signal parameter estimation. IEEE Trans. Antennas Propagation, 1986, AP-34, pp. 276–280.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3