Self-organizing map and its application in the analysis of ambient noise characteristics

Chunxia Meng; Guijuan Li; Shuwei Che; Jin Bai

doi:10.1117/12.2265728

23 January 2017 Self-organizing map and its application in the analysis of ambient noise characteristics

Chunxia Meng, Guijuan Li, Shuwei Che, Jin Bai

Proceedings Volume 10322, Seventh International Conference on Electronics and Information Engineering; 103220Z (2017) https://doi.org/10.1117/12.2265728
Event: Seventh International Conference on Electronics and Information Engineering, 2016, Nanjing, China

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.

Citation Download Citation

Chunxia Meng, Guijuan Li, Shuwei Che, and Jin Bai "Self-organizing map and its application in the analysis of ambient noise characteristics ", Proc. SPIE 10322, Seventh International Conference on Electronics and Information Engineering, 103220Z (23 January 2017); https://doi.org/10.1117/12.2265728

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available