article · Journal Of Big Data
Automated monitoring of poultry sounds offers a non-invasive way to track animal welfare and detect diseases early. A novel deep learning system has been developed to classify poultry audio signals while maintaining high resilience against background noise and signal variations. The architecture integrates digital audio processing with convolutional neural networks and introduces a custom Burn Layer, which deliberately injects controlled random noise during model training. This design prevents overfitting and significantly streamlines the system, requiring only 191,235 trainable parameters compared to more than 1.7 million in conventional networks. Using the Adamax optimizer, data augmentation, and early-stopping methods, the model achieved an overall accuracy of 98.55 per cent alongside 100 per cent specificity and precision during testing. The compact design delivers high performance without demanding heavy computational resources.
Monitoring farm animals through sound can help detect health issues and distress before visual symptoms emerge. By cutting down the computational size of deep learning models while preserving high accuracy, this method makes audio-based animal welfare monitoring far more practical. It provides an efficient foundation for developing responsive, continuous health tracking systems in poultry farming.
The model could enable automated animal health monitoring and early disease detection systems for commercial poultry producers and livestock technology developers. Because it dramatically reduces computational requirements, the software is well suited for deployment on lower-power edge devices within farming facilities. The technology appears to be at an applied research stage, validated on test datasets but awaiting full deployment in operational commercial farms.
AI-generated from the published abstract. Always read the original work before citing.
Abstract This study introduces a novel deep learning-based approach for classifying poultry audio signals, incorporating a custom Burn Layer to enhance model robustness. The methodology integrates digital audio signal processing, convolutional neural networks (CNNs), and the innovative Burn Layer, which injects controlled random noise during training to reinforce the model's resilience to input signal variations. The proposed architecture is streamlined, with convolutional blocks, densely connected layers, dropout, and an additional Burn Layer to fortify robustness. The model demonstrates efficiency by reducing trainable parameters to 191,235, compared to traditional architectures with over 1.7 million parameters. The proposed model utilizes a Burn Layer with burn intensity as a parameter and an Adamax optimizer to optimize and address the overfitting problem. Thorough evaluation using six standard classification metrics showcases the model's superior performance, achieving exceptional sensitivity (96.77%), specificity (100.00%), precision (100.00%), negative predictive value (NPV) (95.00%), accuracy (98.55%), F1 score (98.36%), and Matthew’s correlation coefficient (MCC) (95.88%). This research contributes valuable insights into the fields of audio signal processing, animal health monitoring, and robust deep-learning classification systems. The proposed model presents a systematic approach for developing and evaluating a deep learning-based poultry audio classification system. It processes raw audio data and labels to generate digital representations, utilizes a Burn Layer for training variability, and constructs a CNN model with convolutional blocks, pooling, and dense layers. The model is optimized using the Adamax algorithm and trained with data augmentation and early-stopping techniques. Rigorous assessment on a test dataset using standard metrics demonstrates the model's robustness and efficiency, with the potential to significantly advance animal health monitoring and disease detection through audio signal analysis.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1186/s40537-024-00985-8
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
