Anthropogenic noise and habitat structure shaping dominant frequency of bird sounds along urban gradients

iScience, Journal Year: 2024, Volume and Issue: 27(2), P. 109056 - 109056

Published: Jan. 30, 2024

The shifts of bird song frequencies in urbanized areas provide a unique system to understand avian acoustic responses urbanization. Using passive monitoring and automatic sound recognition technology, we explored the frequency variations six common urban species their associations with habitat structures. Our results demonstrated that were significantly higher than those peri-urban rural areas. Anthropogenic noise structure identified as crucial factors shaping space for birds. We found noise, urbanization, open understory spaces are contributing increase dominant sounds. However, variables such vegetation density tree height can potentially slow down this upward trend. These findings offer essential insights into behavioral response birds variety forest habitats, implications ecosystem management restoration.

Language: Английский

---

A novel approach for bird sound classification with cross correlation by denoising with complementary ensemble empirical mode decomposition using B-spline and LSTM features

Applied Acoustics, Journal Year: 2025, Volume and Issue: 233, P. 110601 - 110601

Published: Feb. 19, 2025

Language: Английский

---

DBS-NET: A Dual-Branch Network Integrating Supervised and Contrastive Self-Supervised Learning for Birdsong Classification

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(10), P. 5418 - 5418

Published: May 12, 2025

Birdsong classification plays a crucial role in monitoring species distribution, population structure, and environmental changes. Existing methods typically use supervised learning to extract specific features for classification, but this may limit the generalization ability of model lead errors. Unsupervised feature extraction are an emerging approach that offers enhanced adaptability, particularly handling unlabeled diverse birdsong data. However, their drawback bring additional time cost downstream tasks, which impact overall efficiency. To address these challenges, we propose DBS-NET, Dual-Branch Network Model classification. DBS-NET consists two branches: branch (Res-iDAFF) unsupervised (based on contrastive approach). We introduce iterative dual-attention fusion (iDAFF) module backbone enhance contextual extraction, linear residual classifier is exploited further improve accuracy. Additionally, class imbalance dataset, weighted loss function introduced adjust cross-entropy with optimized weights. training efficiency, networks both branches share portion weights, reducing computational overhead. In experiments self-built 30-class dataset Birdsdata proposed method achieved accuracies 97.54% 97.09%, respectively, outperforming other methods.

Language: Английский

---

MDF-Net: A multi-view dual-attention fusion network for efficient bird sound classification

Applied Acoustics, Journal Year: 2024, Volume and Issue: 225, P. 110138 - 110138

Published: July 14, 2024

Language: Английский

---