相关实验视频

Updated: May 11, 2025

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

Automatic Image Processing to Determine the Community Size Structure of Riverine Macroinvertebrates

Published on: January 13, 2023

深海的声音:输入表示,模型选择和数据集大小如何影响水下声音分类性能

Abdullah Olcay¹, Paul R White¹, Jonathan M Bull²

¹Institute of Sound and Vibration Research, University of Southampton, Southampton, SO17 1BJ, United Kingdom.

The Journal of the Acoustical Society of America

|April 18, 2025

概括

选择正确的输入表示可以显著改善使用卷积神经网络 (CNN) 的水下声音分类. 一个定制的浅CNN与Mel光谱 (MS-PCEN) 提供了卓越的性能,特别是在有限的数据.

科学领域:

海洋生物声学海洋生物声学
机器学习用于环境监测.
信号处理信号处理

背景情况:

水下音景分析对于海洋环境监测至关重要.
卷积神经网络 (CNN) 在自动水下声音源分类方面表现有前途.
优化CNN设计选择是提高分类准确性和通用性的关键.

研究的目的:

调查输入表示和网络架构对CNN性能对水下声音分类的影响.
评估训练数据大小如何影响这些设计选择的重要性.
评估CNN模型在不同离岸地点的通用性.

主要方法:

利用来自苏格兰西部三个离岸地点的被动声学数据.
用于四种声音类别的层次分类:海豚音调,海豚点击,船只和环境噪音.
比较了三个输入信号表示和四个CNN架构,包括预训练模型.

主要成果:

一个定制的浅CNN与Mel频谱规范化,每通道能量规范化 (MS-PCEN) 输入表示,超过了ResNet等复杂架构,特别是训练数据有限 (12.5%的精度提高).
发现输入表示对于强大的站点对站点通用化至关重要,MS-PCEN表现最好.
随着培训数据集大小的增加,输入表示选择的意义下降了.

结论:

适当的输入表示比复杂的网络架构更为关键,用于使用CNN进行有效的水下声音分类,特别是在较小的数据集中.
MS-PCEN成为一个非常有效的输入表示,用于在不同地点进行强大的水下声学分类.
未来的研究应该专注于优化输入表示,以提高CNN在海洋声学监测中的性能和通用性.

更多相关视频

Flying Insect Detection and Classification with Inexpensive Sensors

Flying Insect Detection and Classification with Inexpensive Sensors

Published on: October 15, 2014

A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry

A Field Primer for Monitoring Benthic Ecosystems Using Structure-From-Motion Photogrammetry

Published on: April 15, 2021

相关概念视频

Classification of Signals

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...

Survival Tree

Survival Tree

Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...

Perception of Sound Waves

Perception of Sound Waves

The human ear is not equally sensitive to all frequencies in the audible range. It may perceive sound waves with the same pressure but different frequencies as having different loudness. Moreover, the perception of sound waves depends on the health of an individual's ears, which decays with age. The health of one's ears may also be affected by regular exposure to loud noises.
The pitch of a sound depends on the frequency and the pressure amplitude of the source. Two sounds of the same...

Force Classification

Force Classification

Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...

Sound Intensity Level

Sound Intensity Level

Humans perceive sound by hearing. The human ear helps sound waves reach the brain, which then interprets the waves and creates the perception of hearing. The loudness of the environment in which a person is located determines whether they can distinguish between different sound sources.
The human ear can perceive an extensive range of sound intensity, necessitating the use of the logarithmic scale to define a physical quantity—the intensity level. It is a ratio of two intensities and...

Typical Model Studies

Typical Model Studies

Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.