一个高效的神经网络设计,包括用于对蝙蝠回声定位声音进行分类的自动编码器
Sercan Alipek1, Moritz Maelzer1, Yannick Paumen2
1Department of Physics, Goethe University of Frankfurt, 60438 Frankfurt am Main, Germany.
Animals : an open access journal from MDPI
|August 26, 2023
概括
这项研究引入了一个使用神经网络识别蝙蝠物种和属的自动化系统,从回声定位呼叫中识别出蝙蝠物种和属,改进了保护工作. 这种高效的模型准确地分类蝙蝠,即使有背景噪音,有助于环境监测.
科学领域:
- 生态生态学 生态生态学
- 生物声学是一种生物声学.
- 人工智能的人工智能
背景情况:
- 蝙蝠是重要的生物指标,因为它们对息地变化的敏感性.
- 手动分析长期被动声学监测数据是耗时的.
- 自动化蝙蝠活动监测对于保护至关重要,特别是在风能影响方面.
研究的目的:
- 开发一种基于神经网络的方法,用于自动化蝙蝠回声定位脉冲检测,属和物种分类.
- 为了评估模型在各种噪音类型的真实环境下的性能.
- 评估模型在不同采样高度和位置的有效性.
主要方法:
- 使用监督神经网络模型进行蝙蝠呼叫分类.
- 使用无监督学习管道与自动编码器和UMAP用于数据压缩和特征提取.
- 在两年内从两个地点收集和分析了四个不同高度 (10米,35米,65米,95米) 的声学数据.
主要成果:
- 该模型获得了高的F1分数,在未知的测试组上,物种分类为92.3%至99.7%,属分类为94.6%至99.4%.
- 该系统在设计方面表现出了效率和简单性,能够解释复杂的回声定位音景.
- 无监督管道为数据属性提供了洞察力,并有助于模型解释.
结论:
- 开发的神经网络方法为自动蝙蝠声学监测提供了一个有效和必要的工具.
- 这项技术支持蝙蝠保护,通过对大型声学数据集进行有效分析,特别是在风力发电场等受人类影响的环境中.
- 该模型在各种条件下的高精度验证了其对了解蝙蝠种群和生态健康的有用性.
相关概念视频
01:06Echo
534
The human ear cannot distinguish between two sources of sound if they happen to reach within a specific time interval, typically 0.1 seconds apart. More than this, and they are perceived as separate sources.
Imagine the sound is reflected back to the ears. Assuming that the source is very close to the human, the difference between hearing the two sounds—the emitted sound and the reflected sound—may be more than the minimum time for perceiving distinct sounds. If this is the case,...
Imagine the sound is reflected back to the ears. Assuming that the source is very close to the human, the difference between hearing the two sounds—the emitted sound and the reflected sound—may be more than the minimum time for perceiving distinct sounds. If this is the case,...
534
01:30Classification of Signals
529
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...
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...
529