Chicktech AI: Automated Detection of Poultry Diseases Through Transfer Learning and Multi-Class Convolutional Neural Network Classification
DOI:
https://doi.org/10.63503/acset.120Keywords:
Poultry Disease Detection, Deep Learning, Convolutional Neural Networks, Transfer Learning, VGG16, MobileNetV2, Clinical Decision Support, Cloud Deployment, Precision Livestock FarmingAbstract
Poultry production is a critical component of global food security, yet disease outbreaks remain a persistent challenge for smallholder farmers who lack timely and affordable diagnostic tools. Diseases such as coccidiosis, bumblefoot, and fowlpox cause severe financial losses and high flock mortality. This paper presents ChickTech AI, a fully deployed, cloud-based poultry disease-diagnostics platform that integrates deep learning with a multilingual, mobile-responsive web interface. The system employs a dual-pipeline transfer learning architecture: VGG16 for fecal texture analysis (coccidiosis detection) and MobileNetV2 for external lesion classification (bumblefoot and fowlpox), both fine-tuned using a progressive three-phase training strategy. Evaluated on a held-out test set of 465 images, the system achieves an overall classification accuracy of 98.2% with all-class AUC > 0.96. The platform incorporates multilingual voice interaction (speech-to-text, text-to-speech, and batch translation) and a tiered clinical decision support module (CRITICAL / IMPORTANT / SUPPORTIVE) that translates AI predictions into actionable treatment guidance. Unlike prior works that report only algorithmic accuracy, ChickTech AI bridges the research-to-practice gap through a production-ready, cloud-hosted deployment accessible via smartphone, demonstrating that AI-driven precision livestock diagnostics can be scalable, inclusive, and practically deployable.
References
[1] M. A. Akhter, M. M. Rahman, and S. Islam. Deep learning in poultry disease diagnosis from visual symptoms: A systematic review. Computers and Electronics in Agriculture, 2023. 204: art. no. 107519. DOI: 10.1016/j.compag.2022.107519.
[2] OECD/FAO. OECD-FAO Agricultural Outlook 2024–2033. Paris: OECD Publishing, 2024. Available: https://doi.org/10.1787/4c6b30af-en
[3] O. Shirley and K. Yibrah. Economic significance and global burden of avian coccidiosis: A contemporary review. World’s Poultry Science Journal, 2023. 79(4): p. 897–915.
[4] D. E. Swayne, Ed. Diseases of Poultry, 14th ed. Hoboken, NJ: Wiley-Blackwell, 2023.
[5] A. O. Ojo et al. Barriers to veterinary diagnostic access in sub-Saharan African smallholder poultry systems. Preventive Veterinary Medicine, 2023. 218: art. no. 106002. DOI: 10.1016/j.prevetmed.2023.106002.
[6] V. Kumar, D. Chauhan, and N. Sharma. A comprehensive survey on transfer learning approaches for agricultural image classification. Artificial Intelligence in Agriculture, 2023. 10: p. 54–78. DOI: 10.1016/j.aiia.2023.08.001.
[7] R. Ahmed, M. Sarkar, and R. Hassan. Bridging the AI deployment gap in precision agriculture. IEEE Access, 2023. 11: p. 72314–72335. DOI: 10.1109/ACCESS.2023.3291654.
[8] R. O. Alabi, A. O. Ojo, and O. E. Ojo. Automated classification of coccidiosis severity in broiler chickens using customised VGG16 models. Poultry Science, 2023. 102(9): art. no. 102855. DOI: 10.1016/j.psj.2023.102855.
[9] H. Li, R. Zhao, and Y. Wang. Deep learning-based automated scoring of footpad dermatitis in broiler flocks. Biosystems Engineering, 2024. 238: p. 31–43. DOI: 10.1016/j.biosystemseng.2023.12.009.
[10] S. A. Olaniyi, A. J. Alade, and T. O. Adewuyi. Multi-class poultry disease classification from body and fecal images using fine-tuned CNN architectures. Neural Computing and Applications, 2023. 35(18): p. 13521–13540. DOI: 10.1007/s00521-023-08431-3.
[11] Z. Zhang, L. Zhou, and J. Zhao. Real-time poultry disease detection using lightweight CNNs on edge devices. IEEE Internet of Things Journal, 2024. 11(4): p. 6214–6225. DOI: 10.1109/JIOT.2023.3327012.
[12] K. McKee et al. YOLOv5-based automated detection of bumblefoot in cage-free laying hens. Computers and Electronics in Agriculture, 2024. 217: art. no. 108587. DOI: 10.1016/j.compag.2024.108587.
[13] J. Kim. Deployment challenges and cloud-native solutions for bringing AI to rural livestock farming. IEEE Access, 2024. 12: p. 45890–45902. DOI: 10.1109/ACCESS.2024.3378812.
[14] S. K. Singh and P. Kumar. Bridging the digital divide in precision agriculture: Multilingual voice user interfaces for smallholder farmers. Artificial Intelligence in Agriculture, 2023. 8: p. 112–124. DOI: 10.1016/j.aiia.2023.04.005.
[15] A. Das, S. Mukherjee, and D. Roy. Towards inclusive AgriTech: Integrating LLMs and native audio processing for rural farm management. Computers in Industry, 2024. 154: art. no. 104035. DOI: 10.1016/j.compind.2023.104035.
[16] Q. Liu, X. He, and C. Wu. A survey of web deployment frameworks for deep learning models in agricultural disease monitoring. Computers and Electronics in Agriculture, 2023. 215: art. no. 108419. DOI: 10.1016/j.compag.2023.108419.
[17] C. Wang, Y. Li, and H. Chen. A dual-backbone deep learning architecture for multi-class avian disease classification. Expert Systems with Applications, 2024. 238: art. no. 121748. DOI: 10.1016/j.eswa.2023.121748.
[18] X. Li, W. Li, and Q. Zhang. Effective dropout regularization for agricultural image classification models. Precision Agriculture, 2024. 25(1): p. 212–229. DOI: 10.1007/s11119-023-10074-6.
[19] T. R. Patel and J. M. Patel. A comparative study of progressive unfreezing techniques for fine-tuning visual AI models. Journal of Agricultural Informatics, 2025. 15(1): p. 45–59.
[20] F. Ganaie, M. Mushtaq, and N. Bashir. Addressing class imbalance in agricultural disease image datasets. Agronomy, 2023. 13(6): art. no. 1533. DOI: 10.3390/agronomy13061533.
[21] Merck Veterinary Manual. Coccidiosis in poultry. 12th ed. Kenilworth, NJ: Merck & Co., 2023. Available: https://www.merckvetmanual.com/poultry/coccidiosis/coccidiosis-in-poultry
[22] B. O. Aina, T. Adedeji, and L. Oyelaran. YOLOv8-based multi-class poultry disease detection from skin and fecal images. Computers and Electronics in Agriculture, 2024. 222: art. no. 109013. DOI: 10.1016/j.compag.2024.109013.
[23] M. N. Luštrek, A. Gradišek, and S. Poličnik. Evaluating multi-class veterinary diagnostic classifiers: A guide to ROC-AUC analysis. Veterinary Sciences, 2023. 10(11): art. no. 658. DOI: 10.3390/vetsci10110658.
[24] E. A. Godyński, G. Ziołkowska, and M. Pawlak. The potential roles of AI in poultry welfare monitoring. Animal, 2024. 18(4): art. no. 101094. DOI: 10.1016/j.animal.2024.101094.
[25] M. A. Hossain, P. Kamruzzaman, and A. B. M. Islam. Federated learning for privacy-preserving collaborative disease surveillance across poultry farms. Computers and Electronics in Agriculture, 2024. 220: art. no. 108872. DOI: 10.1016/j.compag.2024.108872.
Downloads
Published
Conference Proceedings Volume
Section
License
Copyright (c) 2026 Adroid Conference Series: Engineering and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
