Share Email Print
cover

Proceedings Paper

Self-organizing map and its application in the analysis of ambient noise characteristics
Author(s): Chunxia Meng; Guijuan Li; Shuwei Che; Jin Bai
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The Self-organizing map (SOM) is an unsupervised neural network based on competitive learning, and can solve the problem that the center of clustering is unknown. SOM’s theory and the implementation of algorithm are studied in this paper. Simulating example is given to approve the feasibility of SOM in characteristic assessment for multivariate sample. The Ambient sea noise measurement is made in August 2014 on some sea of China. The total source level was forecasted using “ROSS formula” and the sailing information. The statistical variability of broadband ambient noise at frequencies between 20Hz and 31.5 kHz is obtained using SOM. The comparison between measured sound pressure and forecasting pressure is given, and the preliminary analysis of the relationship between ambient noise level and vessels is carried out. The results provide the technical reference to understand the temporal and spatial statistical variability of ambient noise, and are an efficient tool in assessing the potential effect of shipping noise on marine mammals in the special sea area.

Paper Details

Date Published: 23 January 2017
PDF: 5 pages
Proc. SPIE 10322, Seventh International Conference on Electronics and Information Engineering, 103220Z (23 January 2017); doi: 10.1117/12.2265728
Show Author Affiliations
Chunxia Meng, Science and Technology on Underwater Test and Control Lab. (China)
Guijuan Li, Science and Technology on Underwater Test and Control Lab. (China)
Shuwei Che, Science and Technology on Underwater Test and Control Lab. (China)
Jin Bai, Science and Technology on Underwater Test and Control Lab. (China)


Published in SPIE Proceedings Vol. 10322:
Seventh International Conference on Electronics and Information Engineering
Xiyuan Chen, Editor(s)

© SPIE. Terms of Use
Back to Top