The Littoral Acoustic Demonstration Center—Gulf Ecological Monitoring and Modeling (LADC-GEMM) consortium has collected passive acoustic monitoring data in the northern Gulf of Mexico since 2001. Recordings were made in 2007… Click to show full abstract
The Littoral Acoustic Demonstration Center—Gulf Ecological Monitoring and Modeling (LADC-GEMM) consortium has collected passive acoustic monitoring data in the northern Gulf of Mexico since 2001. Recordings were made in 2007 near the Deepwater Horizon oil spill, which have provided a baseline for an extensive study of regional marine mammal populations in response to the disaster. Beaked whales are of particular interest as they remain one of the least understood groups of marine mammals, and relatively few abundance estimates exist. Efficient classification and clustering algorithms are demanded for mining the long-term passive acoustic data. Three algorithms using k-means, self-organizing maps, and spectral clustering are tested with various features of detected echolocation transients. Several methods are observed to effectively isolate recorded echolocation clicks of regional beaked whale species. The waveform fractal dimension is introduced as a feature for marine biosonar classification and shown to...
               
Click one of the above tabs to view related content.