Evaluasi Kelayakan Penggunaan Model Machine Learning pada Klasifikasi Perilaku Ayam di Bawah Kondisi Suhu dan Kelembapan yang Bervariasi
Main Article Content
Abstract
Penelitian ini mengkaji penerapan model pembelajaran mesin untuk mengklasifikasikan perilaku ayam pada kondisi suhu dan kelembapan yang bervariasi, dengan tujuan mengoptimalkan kesejahteraan dan produktivitas unggas melalui pemantauan otomatis. Analisis difokuskan pada perilaku utama seperti Beristirahat, Makan/Minum, dan Aktivitas Fisik, serta meneliti bagaimana fluktuasi lingkungan memengaruhi respons fisiologis ayam, khususnya dalam termoregulasi. Selama periode pengamatan selama 21 hari, data dikumpulkan dari enam ayam menggunakan sensor suhu dan kelembapan, disertai dengan rekaman video. Sebanyak lima model pembelajaran mesin diuji, yaitu Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), dan metode ensemble, untuk mengidentifikasi model yang paling efektif di antara lima model yang digunakan. Model Random Forest menunjukkan kinerja terbaik dengan akurasi sebesar 98,65%, membuktikan kemampuannya dalam membedakan berbagai aktivitas dengan efektif. Selain itu, temuan penelitian ini menekankan pentingnya mengintegrasikan data lingkungan secara real-time dan meningkatkan teknik ekstraksi fitur untuk meningkatkan keandalan klasifikasi. Wawasan dari penelitian ini berpotensi memberikan kontribusi terhadap pengembangan sistem pemantauan cerdas adaptif, meskipun masih memerlukan validasi lebih lanjut dengan jumlah sampel yang lebih besar, sekaligus menjadi landasan awal yang berpotensi mendukung kemajuan di masa depan dalam manajemen unggas komersial dengan memungkinkan intervensi kesejahteraan yang tepat waktu dan mendukung operasi yang efisien serta berorientasi pada kesejahteraan.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
Akter, S., Cheng, B., West, D., Liu, Y., Qian, Y., Zou, X., Classen, J., Cordova, H., Oviedo, E., & Wang-li, L. (2022). Impacts of Air Velocity Treatments under Summer Condition : Part I — Heavy Broiler’ s Surface Temperature Response. Animals, 12(3), 1–18. https://doi.org/https://doi.org/10.3390/ani12030328
Bergen, S., Huso, M. M., Duerr, A. E., Braham, M. A., Schmuecker, S., Miller, T. A., Katzner, T. E., & Bergen, S. (2023). A review of supervised learning methods for classifying animal behavioural states from environmental features. Methods in Ecology and Evolution, 14(1), 189–202. https://doi.org/10.1111/2041-210X.14019
Brugaletta, G., Teyssier, J., Rochell, S. J., Dridi, S., & Sirri, F. (2022). A review of heat stress in chickens. Part I : Insights into physiology and gut health. Frontiers in Physiology, 13, 1–15. https://doi.org/10.3389/fphys.2022.934381
Evans, L., Brooks, G. C., Anderson, M. G., Campbell, A. M., & Jacobs, L. (2023). Environmental Complexity and Reduced Stocking Density Promote Positive Behavioral Outcomes in Broiler Chickens. Animals, 13(13), 1–17. https://doi.org/https://doi.org/10.3390/ani13132074
Fernandes, E., Raymundo, A., Martins, L. L., Lordelo, M., & Almeida, A. M. de. (2023). The Naked Neck Gene in the Domestic Chicken : A Genetic Strategy to Mitigate the Impact of Heat Stress in Poultry Production — A Review. Animals, 13(6), 1–15. https://doi.org/https://doi.org/10.3390/ani13061007
Fujinami, K., Takuno, R., Sato, I., & Shimmura, T. (2023). Evaluating Behavior Recognition Pipeline of Laying Hens. Sensors, 23(11), 1–27. https://doi.org/https://doi.org/10.3390/s23115077
Guo, Y., Aggrey, S. E., Wang, P., & Oladeinde, A. (2022). Monitoring Behaviors of Broiler Chickens at Different Ages with Deep Learning. Animals, 12(23), 1–12. https://doi.org/https://doi.org/10.3390/ani12233390
Hemanth, M., Venugopal, S., Devaraj, C., Shashank, C. G., Ponnuvel, P., Mandal, P. K., & Sejian, V. (2024). Comparative assessment of growth performance, heat resistance and carcass traits in four poultry genotypes reared in hot-humid tropical environment. Journal of Animal Physiology and Animal Nutrition, 108(5), 1510–1523. https://doi.org/https://doi.org/10.1111/jpn.13994Digital Object Identifier (DOI)
Kim, H., Ryu, C., Lee, S., Cho, J., & Kang, H. (2024). Effects of Heat Stress on the Laying Performance, Egg Quality, and Physiological Response of Laying Hens. Animals, 14(1076), 1–12. https://doi.org/https://doi.org/10.3390/ani14071076
Massari, J. M., Moura, D. J. De, Nääs, I. D. A., Pereira, D. F., Robson, S., Oliveira, D. M., Branco, T., Souza, J. De, & Barros, G. (2024). Sequential Behavior of Broiler Chickens in Enriched Environments under Varying Thermal Conditions Using the Generalized Sequential Pattern Algorithm : A Proof of Concept. Animals, 14(13), 1–14. https://doi.org/https://doi.org/10.3390/ani14132010
Pearce, J., Chang, Y., Xia, D., & Abeyesinghe, S. (2024). Classification of Behaviour in Conventional and Slow-Growing Strains of Broiler Chickens Using Tri-Axial Accelerometers. Animals, 14(13), 1–21. https://doi.org/https://doi.org/10.3390/ani14131957
Quintana-ospina, G. A., Alfaro-wisaquillo, M. C., Oviedo-rondon, E. O., Ruiz-ramirez, J. R., Bernal-arango, L. C., & Martinez-bernal, G. D. (2023). Effect of Environmental and Farm-Associated Factors on Live Tropical Conditions. Animals, 13(3312), 1–21. https://doi.org/https://doi.org/10.3390/ani13213312
Solis, I. L., Oliveira-boreli, F. P. De, Sousa, R. V. De, Martello, L. S., & Pereira, D. F. (2024). Using Thermal Signature to Evaluate Heat Stress Levels in Laying Hens with a Machine-Learning-Based Classifier. Animals, 14(13), 1–12. https://doi.org/https://doi.org/10.3390/ani14131996
Sozzi, M., Pillan, G., Ciarelli, C., Marinello, F., Pirrone, F., Bordignon, F., Bordignon, A., Xiccato, G., & Trocino, A. (2023). Measuring Comfort Behaviours in Laying Hens Using Deep-Learning Tools. Animals, 13(1), 1–11. https://doi.org/https://doi.org/10.3390/ani13010033
Yan, Y., Sheng, Z., Gu, Y., Heng, Y., Zhou, H., & Wang, S. (2024). Research note : A method for recognizing and evaluating typical behaviors of laying hens in a thermal environment. Poultry Science, 103(11), 1–6. https://doi.org/10.1016/j.psj.2024.104122
Yang, X., Bist, R. B., Paneru, B., & Chai, L. (2024). Deep Learning Methods for Tracking the Locomotion of Individual Chickens. Animals, 14(6), 1–13. https://doi.org/https://doi.org/10.3390/ani14060911
Yang, X., Bist, R., Paneru, B., & Chai, L. (2016). Monitoring activity index and behaviors of cage-free hens with advanced deep learning technologies. Poultry Science, 103(11), 104193. https://doi.org/10.1016/j.psj.2024.104193
Yang, X., Zhao, Y., Street, G. M., Huang, Y., To, S. D. F., & Purswell, J. L. (2021). Animal The international journal of animal biosciences Classification of broiler behaviours using triaxial accelerometer and machine learning. Animal, 15(7), 1–11. https://doi.org/10.1016/j.animal.2021.100269
Yu, Z., Liu, L., Jiao, H., & Chen, J. (2023). Leveraging SOLOv model to detect heat stress of poultry in complex environments. Frontiers in Venterinary Science, 9, 1–13. https://doi.org/https://doi.org/10.3389/fvets.2022.1062559