{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T10:32:58Z","timestamp":1785407578420,"version":"3.56.0"},"reference-count":43,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Open Research Fund of State Key Laboratory for Novel Software Technology","award":["KFKT2025B41"],"award-info":[{"award-number":["KFKT2025B41"]}]},{"name":"Key Discipline Improvement Project of Guangdong Province","award":["2025ZDJS023"],"award-info":[{"award-number":["2025ZDJS023"]}]},{"name":"University-Industry Collaborative Education Program of Ministry of Education","award":["241003632084003"],"award-info":[{"award-number":["241003632084003"]}]},{"name":"Scientific Research Capacity Improvement Project of the Doctoral Program Construction Unit of Guangdong Polytechnic Normal University","award":["22GPNUZDJS17"],"award-info":[{"award-number":["22GPNUZDJS17"]}]},{"award":["22GPNUZDJS17"],"award-info":[{"award-number":["22GPNUZDJS17"]}],"id":[{"id":"https:\/\/ror.org\/02pcb5m77","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Graduate Education Demonstration Base Project of Guangdong Polytechnic Normal University","award":["2023YJSY04002"],"award-info":[{"award-number":["2023YJSY04002"]}]},{"award":["2023YJSY04002"],"award-info":[{"award-number":["2023YJSY04002"]}],"id":[{"id":"https:\/\/ror.org\/02pcb5m77","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Higher Education Teaching Research and Reform Project","award":["202430803"],"award-info":[{"award-number":["202430803"]}]},{"name":"Graduate Education Innovation Program of Guangdong Polytechnic Normal University","award":["2026XJANLK006"],"award-info":[{"award-number":["2026XJANLK006"]}]},{"award":["2026XJANLK006"],"award-info":[{"award-number":["2026XJANLK006"]}],"id":[{"id":"https:\/\/ror.org\/02pcb5m77","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Veterinary Sciences"],"abstract":"<jats:p>This study aims to develop a lightweight, edge-deployable artificial intelligence (AI) system for real-time, non-contact recognition of cattle eating, standing, and lying behaviors in farm environments. Automated monitoring of these behaviors in cattle provides fundamental behavioral data for the future development of systems that analyze feeding duration, lying duration, and behavioral rhythms. Nevertheless, practical deployment on farms is hindered by data imbalance, dense animal groupings, scale variation, occlusion, and the need for low-cost edge computing. To address these challenges, we propose BoviFusionNet, a lightweight, edge-deployable AI system. A box balanced augmentation strategy rebalances training instances at the object level without altering the validation or test sets. Built upon YOLO11n, the model integrates three targeted enhancements: information-preserving downsampling (ADown), adaptive bidirectional feature fusion (BiFPN), and local window attention (C2CGA) to improve multi-scale representation and fine-grained behavior discrimination. Experimental results show that BoviFusionNet achieves 0.7851 recall, 0.7763 F1-score, 0.7976 mAP@0.50, and 0.6305 mAP@0.50:0.95, with only 5.4 GFLOPs and a 3.4 MB model size. Compared with the YOLO11n baseline, it improves mAP@0.50:0.95 by 9.92% and reduces the parameter count by 39.8%. After INT8 quantization and deployment on an RK3588S edge device, real-time inference reaches 28.08 frames per second (FPS). Therefore, BoviFusionNet offers an effective accuracy-complexity trade-off for on-farm edge AI applications. By enabling continuous, non-invasive monitoring of health-relevant behaviors, it provides fundamental behavioral data for the future development of veterinary health assessment tools without relying on cloud services or wearable sensors.<\/jats:p>","DOI":"10.3390\/vetsci13070697","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T09:32:54Z","timestamp":1784539974000},"page":"697","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["BoviFusionNet: A Lightweight Edge-Deployable AI System for Cattle Behavior Recognition in Livestock Monitoring"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8586-9535","authenticated-orcid":false,"given":"Jiawen","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China"},{"name":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China"},{"name":"ZUMRI-LYG Joint Laboratory, Zhuhai UM Science and Technology Research Institute, Zhuhai 519031, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6668-9420","authenticated-orcid":false,"given":"Weidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ximing","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3142-6057","authenticated-orcid":false,"given":"Jiarui","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5222-0015","authenticated-orcid":false,"given":"Leijun","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7294-4172","authenticated-orcid":false,"given":"Jujian","family":"Lv","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6153-3722","authenticated-orcid":false,"given":"Kaihan","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0428-0057","authenticated-orcid":false,"given":"Wencai","family":"Du","sequence":"additional","affiliation":[{"name":"Institute for Data Engineering and Science, University of Saint Joseph, Macau 999078, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3075-460X","authenticated-orcid":false,"given":"Rongjun","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science, Guangdong Polytechnic Normal University, Guangzhou 510665, China"},{"name":"Guangdong Provincial Key Laboratory of Intellectual Property and Big Data, Guangdong Polytechnic Normal University, Guangzhou 510665, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Antognoli, V., Presutti, L., Bovo, M., Torreggiani, D., and Tassinari, P. (2025). Computer vision in dairy farm management: A literature review of current applications and future perspectives. Animals, 15.","DOI":"10.3390\/ani15172508"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Linst\u00e4dt, J., Th\u00f6ne-Reineke, C., and Merle, R. (2024). Animal-based welfare indicators for dairy cows and their validity and practicality: A systematic review of the existing literature. Front. Vet. Sci., 11.","DOI":"10.3389\/fvets.2024.1429097"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Ma, W., Sun, Y., Qi, X., Xue, X., Chang, K., Xu, Z., Li, M., Wang, R., Meng, R., and Li, Q. (2024). Computer-vision-based sensing technologies for livestock body dimension measurement: A survey. Sensors, 24.","DOI":"10.3390\/s24051504"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"100091","DOI":"10.1016\/j.atech.2022.100091","article-title":"Monitoring and classification of cattle behavior: A survey","volume":"3","author":"Da","year":"2023","journal-title":"Smart Agric. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"190","DOI":"10.55730\/1300-0128.4355","article-title":"Monitoring cow behavior based on lying, standing, eating, and ruminating recognition using YOLOv8","volume":"48","author":"Saifudin","year":"2024","journal-title":"Turk. J. Vet. Anim. Sci."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"jzae111","DOI":"10.1093\/jigpal\/jzae111","article-title":"A review and future trends of precision livestock over dairy and beef cow cattle with artificial intelligence","volume":"33","author":"Michelena","year":"2024","journal-title":"Log. J. IGPL"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.20517\/ir.2024.01","article-title":"Recognition of the behaviors of dairy cows by an improved YOLO","volume":"4","author":"Bai","year":"2024","journal-title":"Intell. Robot."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Mu, Y., Hu, J., Wang, H., Li, S., Zhu, H., Luo, L., Wei, J., Ni, L., Chao, H., and Hu, T. (2024). Research on the behavior recognition of beef cattle based on the improved lightweight CBR-YOLO model based on YOLOv8 in multi-scene weather. Animals, 14.","DOI":"10.3390\/ani14192800"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Li, C., Ma, J., Cao, S., and Guo, L. (2025). RFR-YOLO-based recognition method for dairy cow behavior in farming environments. Agriculture, 15.","DOI":"10.3390\/agriculture15181952"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"107638","DOI":"10.1016\/j.compag.2023.107638","article-title":"Transformer neural network to predict and interpret pregnancy loss from activity data in Holstein dairy cows","volume":"205","author":"Lin","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"109426","DOI":"10.1016\/j.compag.2024.109426","article-title":"New method for modeling digital twin behavior perception of cows: Cow daily behavior recognition based on multimodal data","volume":"226","author":"Zhang","year":"2024","journal-title":"Comput. Electron. Agric."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Paulauskaite-Taraseviciene, A., Nakrosis, A., Zymantiene, J., Jurenas, V., Vezys, J., Sederevicius, A., Gruzauskas, R., Oberauskas, V., Japertiene, R., and Bubulis, A. (2026). AI\u2013Driven multimodal sensing for early detection of health disorders in dairy cows. Animals, 16.","DOI":"10.3390\/ani16030411"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"104885","DOI":"10.1016\/j.compag.2019.104885","article-title":"Deep cascaded convolutional models for cattle pose estimation","volume":"164","author":"Li","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"108172","DOI":"10.1016\/j.compag.2023.108172","article-title":"PrunedYOLO-Tracker: An efficient multi-cows basic behavior recognition and tracking technique","volume":"213","author":"Zheng","year":"2023","journal-title":"Comput. Electron. Agric."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yao, J., Zhang, Y., Li, M., Li, J., Liu, Y., Kang, F., and Liu, F. (2025). Research on a lightweight recognition model for daily cattle behavior toward real-time monitoring. Vet. Sci., 12.","DOI":"10.3390\/vetsci12121166"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Jing, Q., Wu, R., Zhang, Z., Li, Y., Chang, Q., Liu, W., and Huang, X. (2025). A YOLO11-based method for segmenting secondary phases in Cu-Fe alloy microstructures. Information, 16.","DOI":"10.3390\/info16070570"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"141748","DOI":"10.1109\/ACCESS.2020.3013005","article-title":"Overview of edge computing in the agricultural internet of things: Key technologies, applications, challenges","volume":"8","author":"Zhang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"23583","DOI":"10.1109\/JIOT.2022.3210154","article-title":"Recent trends in Internet-of-Things-enabled sensor technologies for smart agriculture","volume":"9","author":"Shaikh","year":"2022","journal-title":"IEEE Internet Things J."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1093\/af\/vfae028","article-title":"Computer vision algorithms to help decision-making in cattle production","volume":"14","author":"Pi","year":"2024","journal-title":"Anim. Front."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Fuentes, A., Han, S., Nasir, M.F., Park, J., Yoon, S., and Park, D.S. (2023). Multiview monitoring of individual cattle behavior based on action recognition in closed barns using deep learning. Animals, 13.","DOI":"10.3390\/ani13122020"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"100539","DOI":"10.1016\/j.iot.2022.100539","article-title":"A deep learning-based cow behavior recognition scheme for improving cattle behavior modeling in smart farming","volume":"19","author":"Shakeel","year":"2022","journal-title":"Internet Things"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"106143","DOI":"10.1016\/j.compag.2021.106143","article-title":"Intelligent perception for cattle monitoring: A review for cattle identification, body condition score evaluation, and weight estimation","volume":"185","author":"Qiao","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"122212","DOI":"10.1016\/j.eswa.2023.122212","article-title":"E-YOLO: Recognition of estrus cow based on improved YOLOv8n model","volume":"238","author":"Wang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_24","first-page":"193","article-title":"Cow-YOLO: Automatic cow mounting detection based on non-local CSPDarknet53 and multiscale neck","volume":"17","author":"Wang","year":"2024","journal-title":"Int. J. Agric. Biol. Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2351","DOI":"10.1109\/JIOT.2023.3294944","article-title":"An intelligence cattle reidentification system over transport by Siamese neural networks and YOLO","volume":"11","author":"Bakhshayeshi","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"de Andrade Porto, J.V., Rezende, F.P.C., Astolfi, G., de Moraes Weber, V.A., Pache, M.C.B., and Pistori, H. (2021). Automatic counting of cattle with faster R-CNN on UAV images. Proceedings of the Anais do XVII Workshop de Vis\u00e3o Computacional (WVC 2021), Online, 22\u201323 November 2021, Sociedade Brasileira de Computa\u00e7\u00e3o\u2014SBC.","DOI":"10.5753\/wvc.2021.18880"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1007\/s11554-024-01613-7","article-title":"RTDETR-Refa: A real-time detection method for multi-breed classification of cattle","volume":"22","author":"Li","year":"2025","journal-title":"J. Real-Time Image Process."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wu, C., Fang, J., Wang, X., and Zhao, Y. (2025). DMSF-YOLO: Cow behavior recognition algorithm based on dynamic mechanism and multi-scale feature fusion. Sensors, 25.","DOI":"10.3390\/s25113479"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Liu, X., Peng, H., Zheng, N., Yang, Y., Hu, H., and Yuan, Y. (2023, January 18\u201322). EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Feng, T., Guo, Y., Huang, X., and Qiao, Y. (2023). Cattle target segmentation method in multi-scenes using improved DeepLabV3+ method. Animals, 13.","DOI":"10.3390\/ani13152521"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"110101","DOI":"10.1016\/j.compag.2025.110101","article-title":"An efficient multi-scale attention two-stream inflated 3D ConvNet network for cattle behavior recognition","volume":"232","author":"Yang","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Qazi, A., Razzaq, T., and Iqbal, A. (2024, January 17\u201318). AnimalFormer: Multimodal vision framework for behavior-based precision livestock farming. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPRW63382.2024.00795"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Long, T., Yu, R., You, X., Shen, W., Wei, X., and Gu, Z. (2025). FSCA-YOLO: An enhanced YOLO-based model for multi-target dairy cow behavior recognition. Animals, 15.","DOI":"10.3390\/ani15172631"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Sim, H., Kim, T., Lee, C., Choi, C., Kim, J.S., and Cho, H. (2024). Optimizing cattle behavior analysis in precision livestock farming: Integrating YOLOv7-E6E with AutoAugment and GridMask to enhance detection accuracy. Appl. Sci., 14.","DOI":"10.3390\/app14093667"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"111329","DOI":"10.1016\/j.compag.2025.111329","article-title":"Lightweight model for beef cattle behavior recognition from quadruped robot video in grassland pastures","volume":"242","author":"Wei","year":"2025","journal-title":"Comput. Electron. Agric."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, W., Xiao, S., Chen, X., Huang, Y., Lv, J., Lin, K., Hu, X., Zeng, X., and Chen, R. (2026). An edge-ready lightweight computer vision framework for on-site fish disease detection in aquaculture management. Fishes, 11.","DOI":"10.3390\/fishes11050280"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"e3357","DOI":"10.7717\/peerj-cs.3357","article-title":"A systematic literature review of lightweight YOLO models for object detection","volume":"11","author":"Wang","year":"2025","journal-title":"PeerJ Comput. Sci."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Li, J., Ling, C., Zhang, W., Lv, J., Hu, X., Lin, K., Yuan, J., Zhang, S., and Chen, R. (2026). Multi-entropy feature concatenation for data-efficient cross-subject classification of Alzheimer\u2019s disease and frontotemporal dementia from single-channel EEG. Entropy, 28.","DOI":"10.3390\/e28020212"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Li, J., Feng, G., Ling, C., Ren, X., Liu, X., Zhang, S., Wang, L., Chen, Y., Zeng, X., and Chen, R. (2025). A resource-efficient multi-entropy fusion method and its application for EEG-based emotion recognition. Entropy, 27.","DOI":"10.3390\/e27010096"},{"key":"ref_40","first-page":"14","article-title":"Prism-OBI: A novel framework for oracle bone inscription recognition via visual perception and feature decoupling","volume":"218","author":"Li","year":"2026","journal-title":"npj Herit. Sci."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1007\/s44443-025-00441-4","article-title":"MEF-Net: A generalized hybrid multi-entropy feature fusion neural network model for cross-subject EEG-based emotion recognition","volume":"38","author":"Li","year":"2026","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"114698","DOI":"10.1016\/j.knosys.2025.114698","article-title":"Large-scale cross-modal hashing via Kolmogorov-Arnold representation theorem and optimal transport","volume":"330","author":"Chen","year":"2025","journal-title":"Knowl.-Based Syst."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"132398","DOI":"10.1016\/j.eswa.2026.132398","article-title":"EDA-net: Efficient deformable attention network for aero-engine damage detection and recognition","volume":"322","author":"Lv","year":"2026","journal-title":"Expert Syst. Appl."}],"container-title":["Veterinary Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-7381\/13\/7\/697\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T10:07:41Z","timestamp":1784542061000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-7381\/13\/7\/697"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"references-count":43,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["vetsci13070697"],"URL":"https:\/\/doi.org\/10.3390\/vetsci13070697","relation":{},"ISSN":["2306-7381"],"issn-type":[{"value":"2306-7381","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]}}}