TY - GEN
T1 - 5G AI-IoT system for bird species monitoring and bird song classification
AU - Segura-Garcia, Jaume
AU - Arevalillo-Herraez, Miguel
AU - Felici-Castell, Santiago
AU - Navarro-Camba, Enrique A.
AU - Sturley, Sean
AU - Alcaraz-Calero, Jose M.
N1 - Copyright © 2024 Copyright held by the owner/author(s). This work is licensed under a Creative Commons Attribution International 4.0 License.
PY - 2025/3/11
Y1 - 2025/3/11
N2 - Identification of animal species is a crucial aspect of biology and ecology, particularly in ornithology, where collaboration with other disciplines aims to develop effective methods for bird protection and environmental quality assessment. Leveraging artificial intelligence (AI) and Internet of Things (IoT) technologies, advancements in birdsong identification have been achieved. Machine learning and deep learning techniques, including Imagenet-based Convolutional Neural Networks (CNNs) like EfficientNet and MobileNet, have been employed for image feature comparison. Spectrograms of birdsongs have been analyzed, with Deep CNNs (DCNNs) proving effective in reducing model size for birdsong classification. A 5G IoT-based system for raw audio collection has been implemented, testing various CNNs for bird identification from audio recordings. While Imagenet-based CNNs exhibit high accuracy (up to 75%), their training requires a substantial number of parameters, hindering efficiency during inference. In response, two Deep CNNs were designed to reduce parameters while maintaining accuracy, enabling integration into Small Board Computers (SBCs) or Microcontroller Units (MCUs). These DCNNs demonstrated a 6.7% improvement in overall accuracy compared to other networks, offering a lighter solution for deployment in SBCs and MCUs.
AB - Identification of animal species is a crucial aspect of biology and ecology, particularly in ornithology, where collaboration with other disciplines aims to develop effective methods for bird protection and environmental quality assessment. Leveraging artificial intelligence (AI) and Internet of Things (IoT) technologies, advancements in birdsong identification have been achieved. Machine learning and deep learning techniques, including Imagenet-based Convolutional Neural Networks (CNNs) like EfficientNet and MobileNet, have been employed for image feature comparison. Spectrograms of birdsongs have been analyzed, with Deep CNNs (DCNNs) proving effective in reducing model size for birdsong classification. A 5G IoT-based system for raw audio collection has been implemented, testing various CNNs for bird identification from audio recordings. While Imagenet-based CNNs exhibit high accuracy (up to 75%), their training requires a substantial number of parameters, hindering efficiency during inference. In response, two Deep CNNs were designed to reduce parameters while maintaining accuracy, enabling integration into Small Board Computers (SBCs) or Microcontroller Units (MCUs). These DCNNs demonstrated a 6.7% improvement in overall accuracy compared to other networks, offering a lighter solution for deployment in SBCs and MCUs.
KW - Artificial Intelligence (AI)
KW - birdsong monitoring and classification
KW - convolutional neural networks
KW - deep learning
KW - Internet of Things (IoT)
KW - wireless acoustic sensor networks
UR - https://dl.acm.org/doi/10.1145/3685243.3685244
UR - http://www.scopus.com/inward/record.url?scp=105002302236&partnerID=8YFLogxK
U2 - 10.1145/3685243.3685244
DO - 10.1145/3685243.3685244
M3 - Conference publication
AN - SCOPUS:105002302236
T3 - Proceedings of the 12th Euro-American Conference on Telematics and Information Systems, EATIS 2024
BT - EATIS 2024: Proceedings of the 12th Euro-American Conference on Telematics and Information Systems
PB - ACM
T2 - 12th Euro-American Conference on Telematics and Information Systems, EATIS 2024
Y2 - 3 July 2024 through 5 July 2024
ER -