• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

蝙蝠 2 网络：一种使用音频传感器数据实时分类蝙蝠物种回声定位信号的框架。

Bat2Web: A Framework for Real-Time Classification of Bat Species Echolocation Signals Using Audio Sensor Data.

机构信息

Department of Computer Science and Engineering, American University of Sharjah, Sharjah 26666, United Arab Emirates.

Nature & Ecosystem Restoration, Soudah Development, Riyadh 13519, Saudi Arabia.

出版信息

Sensors (Basel). 2024 May 1;24(9):2899. doi: 10.3390/s24092899.

DOI:10.3390/s24092899
PMID:38733008
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11086295/
Abstract

Bats play a pivotal role in maintaining ecological balance, and studying their behaviors offers vital insights into environmental health and aids in conservation efforts. Determining the presence of various bat species in an environment is essential for many bat studies. Specialized audio sensors can be used to record bat echolocation calls that can then be used to identify bat species. However, the complexity of bat calls presents a significant challenge, necessitating expert analysis and extensive time for accurate interpretation. Recent advances in neural networks can help identify bat species automatically from their echolocation calls. Such neural networks can be integrated into a complete end-to-end system that leverages recent internet of things (IoT) technologies with long-range, low-powered communication protocols to implement automated acoustical monitoring. This paper presents the design and implementation of such a system that uses a tiny neural network for interpreting sensor data derived from bat echolocation signals. A highly compact convolutional neural network (CNN) model was developed that demonstrated excellent performance in bat species identification, achieving an F1-score of 0.9578 and an accuracy rate of 97.5%. The neural network was deployed, and its performance was evaluated on various alternative edge devices, including the NVIDIA Jetson Nano and Google Coral.

摘要

蝙蝠在维持生态平衡方面发挥着关键作用，研究它们的行为为环境健康提供了重要的见解，并有助于保护工作。确定环境中各种蝙蝠物种的存在对于许多蝙蝠研究至关重要。专门的音频传感器可用于记录蝙蝠的回声定位叫声，然后可用于识别蝙蝠物种。然而，蝙蝠叫声的复杂性带来了重大挑战，需要专家进行分析，并花费大量时间进行准确解释。最近在神经网络方面的进展可以帮助自动从其回声定位叫声中识别蝙蝠物种。这种神经网络可以集成到一个完整的端到端系统中，该系统利用最近的物联网 (IoT) 技术和远程、低功耗通信协议来实现自动化声学监测。本文介绍了这样一个系统的设计和实现，该系统使用微小的神经网络来解释来自蝙蝠回声定位信号的传感器数据。开发了一个高度紧凑的卷积神经网络 (CNN) 模型，该模型在蝙蝠物种识别方面表现出色，F1 得分为 0.9578，准确率为 97.5%。部署了神经网络，并在各种替代边缘设备上评估了其性能，包括 NVIDIA Jetson Nano 和 Google Coral。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/39d377fc9218/sensors-24-02899-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/377ca279498c/sensors-24-02899-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/de57edfd0a1d/sensors-24-02899-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/24387720c92d/sensors-24-02899-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/5d8e991fdca0/sensors-24-02899-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/54b941d0d32f/sensors-24-02899-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/27c789b33b4f/sensors-24-02899-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/d15dc4709e92/sensors-24-02899-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/f33254abb465/sensors-24-02899-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/362a0cdca402/sensors-24-02899-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/a499dbbfe9ac/sensors-24-02899-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/52e2515e0011/sensors-24-02899-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/31aab109aa72/sensors-24-02899-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/d951f51c6454/sensors-24-02899-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/8a4dc3361ed7/sensors-24-02899-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/b1caffda615b/sensors-24-02899-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/dde8e79ce083/sensors-24-02899-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/39d377fc9218/sensors-24-02899-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/377ca279498c/sensors-24-02899-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/de57edfd0a1d/sensors-24-02899-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/24387720c92d/sensors-24-02899-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/5d8e991fdca0/sensors-24-02899-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/54b941d0d32f/sensors-24-02899-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/27c789b33b4f/sensors-24-02899-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/d15dc4709e92/sensors-24-02899-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/f33254abb465/sensors-24-02899-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/362a0cdca402/sensors-24-02899-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/a499dbbfe9ac/sensors-24-02899-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/52e2515e0011/sensors-24-02899-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/31aab109aa72/sensors-24-02899-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/d951f51c6454/sensors-24-02899-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/8a4dc3361ed7/sensors-24-02899-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/b1caffda615b/sensors-24-02899-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/dde8e79ce083/sensors-24-02899-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/9613/11086295/39d377fc9218/sensors-24-02899-g017.jpg

相似文献

1
Bat2Web: A Framework for Real-Time Classification of Bat Species Echolocation Signals Using Audio Sensor Data.蝙蝠 2 网络：一种使用音频传感器数据实时分类蝙蝠物种回声定位信号的框架。
Sensors (Basel). 2024 May 1;24(9):2899. doi: 10.3390/s24092899.
2
Bat detective-Deep learning tools for bat acoustic signal detection.蝙蝠侦探——蝙蝠声学信号检测的深度学习工具。
PLoS Comput Biol. 2018 Mar 8;14(3):e1005995. doi: 10.1371/journal.pcbi.1005995. eCollection 2018 Mar.
3
Separating overlapping bat calls with a bi-directional long short-term memory network.使用双向长短时记忆网络分离重叠的蝙蝠叫声。
Integr Zool. 2022 Sep;17(5):741-751. doi: 10.1111/1749-4877.12549. Epub 2021 May 30.
4
Acoustic identification of twelve species of echolocating bat by discriminant function analysis and artificial neural networks.通过判别函数分析和人工神经网络对12种回声定位蝙蝠进行声学识别。
J Exp Biol. 2000 Sep;203(Pt 17):2641-56. doi: 10.1242/jeb.203.17.2641.
5
Buzzfindr: Automating the detection of feeding buzzes in bat echolocation recordings.Buzzfindr：自动检测蝙蝠回声定位记录中的喂食声。
PLoS One. 2024 Aug 20;19(8):e0306063. doi: 10.1371/journal.pone.0306063. eCollection 2024.
6
The calls of Vietnamese bats: a major step toward the acoustic characterization of Asian bats.越南蝙蝠的叫声：亚洲蝙蝠声学特征研究的重要一步。
Sci Rep. 2024 Oct 7;14(1):23335. doi: 10.1038/s41598-024-72436-6.
7
Development of echolocation calls and neural selectivity for echolocation calls in the pallid bat.苍白蝙蝠回声定位叫声的发育以及对回声定位叫声的神经选择性
Dev Neurobiol. 2015 Oct;75(10):1125-39. doi: 10.1002/dneu.22226. Epub 2014 Aug 28.
8
Automated echolocation classifiers vary in accuracy for northeastern U.S. bat species.自动化回声定位分类器在识别美国东北部蝙蝠物种的准确率上存在差异。
PLoS One. 2024 Jun 3;19(6):e0300664. doi: 10.1371/journal.pone.0300664. eCollection 2024.
9
Jamming bat echolocation: the dogbane tiger moth Cycnia tenera times its clicks to the terminal attack calls of the big brown bat Eptesicus fuscus.干扰蝙蝠回声定位：夹竹桃虎蛾（Cycnia tenera）会根据大棕蝠（Eptesicus fuscus）的最终攻击叫声来调整其点击声的时间。
J Exp Biol. 1994 Sep;194:285-98. doi: 10.1242/jeb.194.1.285.
10
Parameter estimation of the hyperbolic frequency-modulated bat calls using hyperbolic scale transform.使用双曲标度变换估计双曲调频蝙蝠叫声的参数。
J Acoust Soc Am. 2024 Jul 1;156(1):16-28. doi: 10.1121/10.0026454.

引用本文的文献

1
Artificial Intelligence in Aquatic Biodiversity Research: A PRISMA-Based Systematic Review.水生生物多样性研究中的人工智能：基于PRISMA的系统评价
Biology (Basel). 2025 May 8;14(5):520. doi: 10.3390/biology14050520.

本文引用的文献

1
Experimental Investigation of Acoustic Features to Optimize Intelligibility in Cochlear Implants.实验研究优化人工耳蜗植入中可懂度的声学特征。
Sensors (Basel). 2023 Aug 31;23(17):7553. doi: 10.3390/s23177553.
2
An Efficient Neural Network Design Incorporating Autoencoders for the Classification of Bat Echolocation Sounds.一种结合自动编码器用于蝙蝠回声定位声音分类的高效神经网络设计。
Animals (Basel). 2023 Aug 8;13(16):2560. doi: 10.3390/ani13162560.
3
Automated Bowel Sound and Motility Analysis with CNN Using a Smartphone.基于智能手机的 CNN 自动肠音和蠕动分析
Sensors (Basel). 2022 Dec 30;23(1):407. doi: 10.3390/s23010407.
4
Intelligent Fault Diagnosis of Industrial Bearings Using Transfer Learning and CNNs Pre-Trained for Audio Classification.基于迁移学习和预先训练用于音频分类的卷积神经网络的工业轴承智能故障诊断。
Sensors (Basel). 2022 Dec 25;23(1):211. doi: 10.3390/s23010211.
5
Smart Strawberry Farming Using Edge Computing and IoT.智能草莓种植利用边缘计算和物联网。
Sensors (Basel). 2022 Aug 5;22(15):5866. doi: 10.3390/s22155866.
6
LoRa Based IoT Platform for Remote Monitoring of Large-Scale Agriculture Farms in Chile.基于 LoRa 的物联网平台，用于智利大规模农业农场的远程监控。
Sensors (Basel). 2022 Apr 7;22(8):2824. doi: 10.3390/s22082824.
7
Feature-Based Fusion Using CNN for Lung and Heart Sound Classification.基于特征融合的 CNN 用于心肺音分类。
Sensors (Basel). 2022 Feb 16;22(4):1521. doi: 10.3390/s22041521.
8
Design, Implementation, and Empirical Validation of an IoT Smart Irrigation System for Fog Computing Applications Based on LoRa and LoRaWAN Sensor Nodes.基于LoRa和LoRaWAN传感器节点的用于雾计算应用的物联网智能灌溉系统的设计、实现与实证验证
Sensors (Basel). 2020 Nov 30;20(23):6865. doi: 10.3390/s20236865.
9
Edge-Computing Architectures for Internet of Things Applications: A Survey.物联网应用的边缘计算架构：一项综述。
Sensors (Basel). 2020 Nov 11;20(22):6441. doi: 10.3390/s20226441.
10
Acoustic localization of terrestrial wildlife: Current practices and future opportunities.陆地野生动物的声学定位：当前实践与未来机遇
Ecol Evol. 2020 Jun 13;10(13):6794-6818. doi: 10.1002/ece3.6216. eCollection 2020 Jul.