Manikandan Venkatraman, Neethirajan Suresh
Faculty of Computer Science, Dalhousie University, Halifax, NS B3H 4R2, Canada.
Faculty of Agriculture, Dalhousie University, Halifax, NS B3H 4R2, Canada.
Sensors (Basel). 2025 Jun 29;25(13):4058. doi: 10.3390/s25134058.
Artificial intelligence and bioacoustics represent a paradigm shift in non-invasive poultry welfare monitoring through advanced vocalization analysis. This comprehensive systematic review critically examines the transformative evolution from traditional acoustic feature extraction-including Mel-Frequency Cepstral Coefficients (MFCCs), spectral entropy, and spectrograms-to cutting-edge deep learning architectures encompassing Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, attention mechanisms, and groundbreaking self-supervised models such as wav2vec2 and Whisper. The investigation reveals compelling evidence for edge computing deployment via TinyML frameworks, addressing critical scalability challenges in commercial poultry environments characterized by acoustic complexity and computational constraints. Advanced applications spanning emotion recognition, disease detection, and behavioral phenotyping demonstrate unprecedented potential for real-time welfare assessment. Through rigorous bibliometric co-occurrence mapping and thematic clustering analysis, this review exposes persistent methodological bottlenecks: dataset standardization deficits, evaluation protocol inconsistencies, and algorithmic interpretability limitations. Critical knowledge gaps emerge in cross-species domain generalization and contextual acoustic adaptation, demanding urgent research prioritization. The findings underscore explainable AI integration as essential for establishing stakeholder trust and regulatory compliance in automated welfare monitoring systems. This synthesis positions acoustic AI as a cornerstone technology enabling ethical, transparent, and scientifically robust precision livestock farming, bridging computational innovation with biological relevance for sustainable poultry production systems. Future research directions emphasize multi-modal sensor integration, standardized evaluation frameworks, and domain-adaptive models capable of generalizing across diverse poultry breeds, housing conditions, and environmental contexts while maintaining interpretability for practical farm deployment.
人工智能和生物声学通过先进的发声分析，代表了非侵入式家禽福利监测的范式转变。本全面的系统综述批判性地审视了从传统声学特征提取（包括梅尔频率倒谱系数（MFCC）、频谱熵和频谱图）到前沿深度学习架构（包括卷积神经网络（CNN）、长短期记忆（LSTM）网络、注意力机制以及诸如wav2vec2和Whisper等开创性的自监督模型）的变革性演变。调查揭示了通过TinyML框架进行边缘计算部署的有力证据，解决了商业家禽环境中以声学复杂性和计算限制为特征的关键可扩展性挑战。涵盖情感识别、疾病检测和行为表型分析的先进应用展示了实时福利评估的前所未有的潜力。通过严格的文献共现映射和主题聚类分析，本综述揭示了持续存在的方法学瓶颈：数据集标准化不足、评估协议不一致以及算法可解释性限制。在跨物种领域泛化和上下文声学适应方面出现了关键的知识空白，需要紧急优先开展研究。研究结果强调，可解释人工智能集成对于在自动化福利监测系统中建立利益相关者信任和符合监管要求至关重要。这一综合将声学人工智能定位为一项基石技术，实现道德、透明且科学稳健的精准畜牧业，将计算创新与生物相关性相结合，以实现可持续的家禽生产系统。未来的研究方向强调多模态传感器集成、标准化评估框架以及能够在不同家禽品种、饲养条件和环境背景下进行泛化同时保持对实际农场部署的可解释性的领域自适应模型。
