Honors College Thesis
 

Improving the accuracy and efficiency of bird song analysis with machine learning based event detection

Public Deposited

Downloadable Content

Download PDF
https://ir.library.oregonstate.edu/concern/honors_college_theses/c821gt336

Descriptions

Attribute NameValues
Creator
Abstract
  • Ornithology is an exciting field with novel research emerging everyday. Researchers in bioacoustics often spend hours within the wilderness recording bird calls to analyze later in their lab. The burden of sifting through hours of audio recordings from the field continues to remain a time-consuming and manual task, despite the inherent value of such research. In this work, we investigate the ability of a mobile application to provide an accelerated method for ornithologists to upload acoustic field recordings for analysis. Driven by recent advancements in technology, there is a growing need for innovative solutions that can streamline this research process. Our proposed solution integrates machine learning algorithms with bioacoustic signal processing with the goal of accelerating the process of analyzing hours of field recordings. In this thesis, we focus on the integration of future machine learning algorithms into an event detection pipeline. This larger project involves three separate parts: (1) the user interface and back end architecture developed by a small team of students for the Oregon State CS 46x capstone series, (2) an event detection algorithm completed as a synergistic extension of the capstone, and (3) a machine learning system developed as part of a graduate thesis. Together, these projects integrate to enhance the accuracy and efficiency of bioacoustic event detection by leveraging machine intelligence with deep learning. Furthermore, we evaluate the performance of these approaches using real-world datasets and discuss our approach in the context of traditional event detection techniques. This research project contributes valuable insights into the feasibility and effectiveness of integrating machine learning algorithms into a cloud-based acoustic event detection pipeline and highlights the potential benefits of this integration for various applications to expedite time-consuming bioacoustic research processes.
  • Key Words: audio processing, bioacoustics, bird song, event detection, database
Resource Type
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Non-Academic Affiliation
Rights Statement
Publisher
Peer Reviewed
Language

Relationships

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details MathewAnju2023.pdf 2023-06-12 Public Download