Building Ensemble of Resnet for Dolphin Whistle Detection

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(14), P. 8029 - 8029

Published: July 10, 2023

Ecoacoustics is arguably the best method for monitoring marine environments, but analyzing and interpreting acoustic data has traditionally demanded substantial human supervision resources. These bottlenecks can be addressed by harnessing contemporary methods automated audio signal analysis. This paper focuses on problem of assessing dolphin whistles using state-of-the-art deep learning methods. Our system utilizes a fusion various resnet50 networks integrated with augmentation (DA) techniques applied not to training test set. We also present speeds classification results DA Through extensive experiments conducted publicly available benchmark, our findings demonstrate that ensemble yields significant performance enhancements across several commonly used metrics. For example, approach obtained an accuracy 0.949 compared 0.923, reported in literature. provide testing sets other researchers use comparison purposes, as well all MATLAB/PyTorch source code this study.

Language: Английский

---

Advanced Technologies for Cetacean Monitoring: A One-Health and Multidisciplinary Approach for Ocean Effective Surveillance

Journal of Marine Science and Engineering, Journal Year: 2023, Volume and Issue: 11(7), P. 1431 - 1431

Published: July 17, 2023

Within the MARCET European project and community framework, a Waveglider®™ SV2 vehicle was deployed, equipped with passive acoustic monitoring (PAM) device, in Special Area of Conservation (SAC) Gran Canaria (Canary Islands, Spain). The soundscape continuously recorded from 23 July 2018 until 30 primarily used for marine mammal sound detection. This study aims to compare these automatically embedded detections human expert detections. Furthermore, it provides an assessment performance automatic detector discusses use this type technology monitor wildlife, particularly cetaceans. are only possible due multidisciplinary integration veterinary sciences, ecological, zoological, biological knowledge mechanical, communication, electronics engineering. It represents excellent example new technologies, capacities, skills, cutting-edge where science education training should progressively be involved contribute surveillance control ocean health.

Language: Английский

---

Machine Learning-Based Sound Event Detection: A Case Study for Noise Identification in Classroom Environment

Lecture notes in networks and systems, Journal Year: 2024, Volume and Issue: unknown, P. 911 - 925

Published: Jan. 1, 2024

Language: Английский

---

Unveiling Cetacean Voices: Entropy-Powered Spectrogram Denoising for Deep Learning Applications

Lecture notes in computer science, Journal Year: 2024, Volume and Issue: unknown, P. 374 - 384

Published: Nov. 15, 2024

Language: Английский

---

Investigation of a Neural Network for Dolphin Whistle Detection Through Heatmaps

Published: Oct. 28, 2024

Language: Английский

---

Transfer Learning of Image Classification Networks in Application to Dolphin Whistle Detection

Published: June 5, 2023

Dolphin whistle detection is an important and multipurpose but time-consuming task. The ability to automate streamline this process can be invaluable for future research in marine studies other fields that aim utilise these signals. When dealing with underwater acoustics, a large obstacle overcome the abundance of noise interfering sounds, natural anthropogenic alike. In paper, we apply successful image classification networks two separate datasets containing dolphin whistles goal determining effective method conduct automated minimal interference from manual operator regardless environment. We further investigate impacts shrinking dataset size performing parameter freezing on at hand. Networks are assessed by their accuracy achieve performances comparable those existing works, best being 96.7%, thus proving effectiveness pre-trained models.

Language: Английский

---

Automatic Detection of Acoustic Signals of Beluga Whales and Bottlenose Dolphins

Moscow University Physics Bulletin, Journal Year: 2023, Volume and Issue: 78(S1), P. S217 - S225

Published: Dec. 1, 2023

Language: Английский

---