Journal
ECOLOGICAL INFORMATICS
Volume 51, Issue -, Pages 103-111Publisher
ELSEVIER
DOI: 10.1016/j.ecoinf.2019.02.010
Keywords
Soundscape ecology; Multi-labeling; K-nearest neighbor; Visualization of acoustic data; Audio features
Categories
Funding
- NSF Advancing Informal STEM Learning [1323615]
- Purdue University Graduate School's Bilsland Dissertation Fellowship
- NSF
- National Natural Science Foundation of P.R. China [61401203]
- State Scholarship Fund of China [201606840023]
- USER Research Institute
- Purdue University's Executive Office of the Vice President for Research and Engagement
- Department of Forestry and Natural Resources Wright Fund
- USDA NIFA Hatch/McIntire Stennis [1016730]
- Sloan Foundation
- Purdue University Graduate School
- Division Of Research On Learning
- Direct For Education and Human Resources [1323615] Funding Source: National Science Foundation
Ask authors/readers for more resources
Scientists are using acoustic monitoring to assess the impact of altered soundscapes on wildlife communities and human systems. In the soundscape ecology field, monitoring and analyses approaches rely on the interdisciplinary intersection of ecology, acoustics, and computer science. Combining theory and practice of each field in the context of Knowledge Discovery in Databases (KDD), soundscape ecologists provide innovative monitoring solutions for ecologically-driven research questions. We propose a soundscape content analysis framework for improved knowledge outcome with assistance of the new multi-label (ML) concept. Here, we investigated the effectiveness of a ML k-nearest neighbor algorithm (ML-kNN) for labeling concurrent soundscape components within a single recording. We manually labeled 1200 field recordings for the presence of soundscape components and extracted ecological acoustic features, audio profile features, and Gaussian-mixture model features for each recording. Then, we tested the ML-kNN algorithm accuracy with well-established metrics adapted to ML learning. We found that seventeen unique acoustic features could predict a set of biophonic, geophonic, and anthrophonic labels for a single field recording with average precision of 0.767. However, certain labels were predicted incorrectly depending on the time of day and co-occurrence of that label with another label, suggesting further refinement is needed to improve the accuracy of predicted labels. Overall, this ML classification approach could enable researchers to label field recordings more quickly and generate an alert system for monitoring changes in a specific sound class. Ultimately, the adaptation of the ML algorithm may provide soundscape ecologists with new metadata labels that are searchable in large databases of soundscape field recordings.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available