Clustering of acoustic fish features tracked by broadband split-beam echo sounder

• Published in: The Journal of the Acoustical Society of America 2013-05, Vol.133 (5_Supplement), p.3538-3538
• Main Authors: Ito, Masanori, Matsuo, Ikuo, Imaizumi, Tomohito, Akamatsu, Tomonari, Wang, Yong, Nishimori, Yasushi
• Format: Article
• Language: English
• ISSN: 0001-4966; 1520-8524
• DOI: 10.1121/1.4806394

Monitoring fish species and amount with acoustical instruments is a challenging problem to survey fish resources in the ocean. Broadband split-beam echo sounder was useful to observe individual fish behavior in schools. Echoes from fish schools were measured from an anchored vessel for several hours. Echo signals were gathered into one block within a certain depth and a period of time and analyzed to track individual fish in the schools. Target strength was calculated from the individual fish echo and associated with tilt angle which could be estimated by using the tracking result. Feature in each block was statistically calculated by averaging target strengths according to the tilt angles. The blocks of the signals were clustered by K-means method with the features and divided into some clusters. The distribution of the clusters in time and depth was investigated. It appeared that the distributions of the clusters were dependent on both time and depth. Clustering of the features would be effective to monitor diversity of fish in the ocean. [Research supported by JST, CREST.]