Soft-output signal detection for cetacean vocalizations using spectral entropy,k-means clustering and the continuous wavelet transform |
| |
| Affiliation: | 1. South China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Guangzhou 510300, China;2. College of Fisheries and Life Science, Dalian Ocean University, Dalian 116023, China;3. College of Life Sciences, Nanjing Normal University, Nanjing 210023, China;4. Key Laboratory for Sustainable Utilization of Open-sea Fishery, Ministry of Agriculture and Rural Affairs, Guangzhou 510300, China;1. MarViva Foundation, Rohrmoser, San Jose, Costa Rica;2. Middlebury Institute of International Studies, 460 Pierce Street, Monterey, CA 93940, USA;3. The Ocean Foundation, 1320 19th St. NW, Suite 500, Washington DC, 20036, USA;1. University of Alaska Fairbanks, College of Fisheries and Ocean Sciences, 17101 Point Lena Loop Road, Juneau, AK 99801, USA;2. University of Washington, School of Aquatic and Fishery Sciences, Box 355020, Washington 98105, USA;3. Departments of Psychology and Biology, University of Hawai’i at Hilo, 200 West Kawili Street, Hilo, HI 96720, USA;4. The Dolphin Institute, P.O. Box 6279, Hilo, HI 96720, USA;5. University of Alaska Southeast, 1332 Seward Avenue, Sitka, AK 99835, USA;6. National Marine Fisheries Service, Alaska Fisheries Science Center, Ted Stevens Marine Research Institute, 17109 Pt. Lena Loop Road, Juneau, AK 99801, USA;7. Hawai’i Marine Mammal Consortium, P.O. Box 6107, Kamuela, HI 96743, USA;8. Glacier Bay National Park & Preserve, P.O. Box 140, Gustavus, AK 99826, USA;1. University Institute of Engineering and Technology, Panjab University, Chandigarh, India;2. Computer Science and Engineering Department (DB Campus), Thapar Institute of Engineering and Technology, Patiala, India |
| |
| Abstract: | Underwater passive acoustic monitoring systems record many hours of audio data for marine research, making fast and reliable non-causal signal detection paramount. Such detectors assist in reducing the amount of labor required for signal annotations, which often contain large portions devoid of signals.Cetacean vocalization detection based on spectral entropy is investigated as a means of vocalization discovery. Previous techniques using spectral entropy mostly consider time–frequency enhancement of the entropy measure, and utilize the short time Fourier transform (STFT) as its time–frequency (TF) decomposition. Spectral entropy methods also requires the user to set a detection threshold manually, which call for knowledge of the produced entropy measures.This paper considers median filtering as a simple, effective way to provide temporal stabilization to the entropy measure, and considers the continuous wavelet transform (CWT) as an alternative TF decomposition. K-means clustering is used to determine the threshold required to accurately separate the signal/no-signal entropy measures, resulting in a one-dimensional, two-class classification problem. The class means are used to perform pseudo-probabilistic soft class assignment, which is a useful metric in algorithmic development. The effect of median filtering, signal-to-noise ratio and the chosen TF decomposition are investigated.The accuracy and specificity measures of the proposed detection technique are simulated using a pulsed frequency modulated sweep, corrupted by a sample of ocean noise. The results show that median filtering is particularly effective for low signal-to-noise ratios. Both the STFT and CWT prove to be effective TF analyses for signal detection purposes, each presenting with different advantages and drawbacks. The simulated results provide insight into configuring the proposed detector, which is compared to a conventional STFT-based spectral entropy detector using manually annotated humpback whale (Megaptera novaeangliae) songs recorded in False Bay, South Africa, July2021.The proposed method shows a significant improvement in detection accuracy and specificity, while also providing a more interpretable detection threshold setting via soft class assignment, providing a detector for use in development of adaptive algorithms. |
| |
| Keywords: | Cetacean vocalization Spectral entropy K-means Signal detection Soft classification Continuous wavelet transform |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
