[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2411":3,"related-2411":113},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":78,"slug":81,"view_count":82,"doi":83,"paper":84,"created_at":112},2411,"Deep reinforcement learning for simulated autonomous heat stress mitigation in dairy cattle","https:\u002F\u002Fdoi.org\u002F10.1080\u002F1828051x.2026.2728340","Heat stress significantly constrains dairy cattle productivity and welfare, compromising milk production and fertility. Yet, despite advances in heat stress detection and prediction, conventional mitigation strategies still rely on fixed thresholds, overlooking inter-animal variability and cumulative thermal load. In this simulation-based proof-of-concept study, we evaluated deep reinforcement learning (DRL) for individualised heat-stress decision support. Using multi-modal sensor data from the MmCows dataset, we developed a Deep Q-Network (DQN) framework for simulated cooling decisions. Cooling interventions were not experimentally applied to animals; their expected effects were computationally modelled as action-specific reductions in effective thermal load with corresponding energy penalties. We trained and evaluated four DQN variants, namely Standard, Double, Duelling and Double Duelling DQN with Prioritised Experience Replay, on real-world sensor data from 10 Holstein dairy cows over a 14–day period. The environment incorporated core body temperature (CBT), Temperature-Humidity Index (THI), behavioural indicators and milk-yield. The Double DQN agent achieved the highest numerical reward (18.26 ± 3.89), but its learned policy selected no intervention in essentially all evaluation cases, and its reward was not significantly different from the No Action baseline (17.66 ± 5.10; Welch t-test, p = 0.510). This pattern was reproduced across five independent random seeds, with all agents converging on low- or no-intervention policies. The moderate heat-stress conditions and reward formulation favoured low-energy policies. These findings indicate that DRL is a promising framework for testing animal-centred control policies in precision livestock farming and developing field-validated autonomous cooling systems with safety constraints through controlled trials and reward-weight sensitivity analysis.","热应激显著制约奶牛的生产性能与福利，损害产奶量和繁殖力。然而，尽管热应激检测与预测技术取得了进展，传统的缓解策略仍依赖于固定阈值，忽视了动物个体差异和累积热负荷。在这项基于仿真的概念验证研究中，我们评估了深度强化学习（DRL）用于个体化热应激决策支持的可行性。利用MmCows数据集的多模态传感器数据，我们开发了一个深度Q网络（DQN）框架用于模拟降温决策。降温干预未在动物身上进行实验性施加；其预期效果通过计算建模为动作特定的有效热负荷降低及相应的能量代价。我们在10头荷斯坦奶牛为期14天的真实传感器数据上训练并评估了四种DQN变体，即标准DQN、双深度Q网络（Double DQN）、竞争深度Q网络（Duelling DQN）和带优先经验回放的双竞争深度Q网络。环境纳入的核心体温（CBT）、温湿度指数（THI）、行为指标和产奶量。Double DQN智能体获得了最高的数值奖励（18.26 ± 3.89），但其学习策略在几乎所有评估案例中均选择不进行干预，其奖励与不采取行动基线（17.66 ± 5.10；Welch t检验，p = 0.510）无显著差异。这一模式在五个独立随机种子下均得到重现，所有智能体均收敛于低干预或不干预策略。中等热应激条件和奖励函数设计倾向于低能量策略。这些发现表明，DRL是精准畜牧业中测试以动物为中心的控制策略的一个有前景的框架，并可通过对照试验和奖励权重敏感性分析开发具有安全约束的田间验证自主降温系统。",null,"Italian Journal of Animal Science","2026-09-12T00:00:00Z","论文",10,false,65,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},8,18,17,13,9,1,"仿真验证的深度强化学习个体化降温决策研究，方法新颖但结论为阴性、未做田间验证，属细分领域前沿探索，可作为智慧畜牧主题聚合素材。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","强化学习","精准畜牧","奶牛热应激",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"C2","ruminants","草食牲畜","\u002Ftopic\u002Flivestock\u002Fruminants","C",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,53,60,67,73],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":52},14,true,[49],"cattle",[51,49],"奶牛",[],{"code":37,"score":54,"supported":47,"title":55,"abstract":56,"tags":59},6,[],[57,58],"畜牧","livestock",[],{"code":61,"score":62,"supported":47,"title":63,"abstract":64,"tags":66},"I2",5,[],[65],"decision support",[28,29],{"code":68,"score":69,"supported":47,"title":70,"abstract":71,"tags":72},"C6",4,[],[30],[30],{"code":74,"score":22,"supported":14,"title":75,"abstract":76,"tags":77},"I1",[],[],[27],[79,80],"农业人工智能 奶牛热应激 强化学习 智慧农业","农业人工智能 奶牛热应激","农业人工智能奶牛热应激强化学习智慧农业-2411",2,"10.1080\u002F1828051x.2026.2728340",{"doi":83,"openalex_id":85,"authors":86,"venue":10,"cited_by_count":102,"oa_url":103,"card":104,"direction":110,"ingested_from":111},"W7212350875",[87,90,93,96,99],{"name":88,"orcid":89},"Jan Saro","https:\u002F\u002Forcid.org\u002F0009-0001-4355-5271",{"name":91,"orcid":92},"Jaromír Ducháček","https:\u002F\u002Forcid.org\u002F0000-0002-6347-8541",{"name":94,"orcid":95},"Jana Mazancová","https:\u002F\u002Forcid.org\u002F0000-0002-7735-5606",{"name":97,"orcid":98},"Luděk Stádník","https:\u002F\u002Forcid.org\u002F0000-0002-7880-0089",{"name":100,"orcid":101},"Vít Malinovský","https:\u002F\u002Forcid.org\u002F0000-0002-7138-6655",0,"https:\u002F\u002Fwww.tandfonline.com\u002Fdoi\u002Fpdf\u002F10.1080\u002F1828051X.2026.2728340?needAccess=true",{"tldr":105,"method":106,"finding":107,"direction":108,"opportunity":109},"用深度强化学习在仿真中为奶牛个体化热应激缓解做决策支持。","基于MmCows多模态传感器数据，训练四种DQN变体模拟降温决策。","Double DQN奖励最高但策略几乎不干预，与无动作基线无显著差异。","农业人工智能与决策模型","可引入安全约束与奖励权重敏感性分析，开展田间验证的自主降温系统研究。","智慧农业 \u002F 农业物联网","openalex","2026-09-14T23:30:07.999063Z",{"total":54,"page":22,"page_size":54,"items":114},[115,166,256,307,371,464],{"id":116,"title":117,"url":118,"summary":119,"summary_zh":9,"content":9,"source_name":120,"source_url":9,"published_at":121,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":122,"score_detail":123,"sources":127,"tags":129,"primary_topic":132,"secondary_topics":133,"classification":134,"search_phrases":153,"slug":156,"view_count":82,"doi":9,"paper":157,"created_at":165},4160,"DGF-YOLOv12n-LiteP2: Dynamic Gated Local-Context Fusion with a High-Resolution Detection Head for Cattle Body-Part Detection in Complex Barns（基于YOLOv12n动态门控局部上下文融合的复杂牛舍牛体部位检测）","https:\u002F\u002Fwww.mdpi.com\u002F1424-8220\u002F26\u002F19\u002F6156","Yanhong Liu、Le Yang、Qingqing Li、Jiazi Han、Jingrong Wang、Meng Han、Hua Yang（MDPI Sensors 2026, 26(19): 6156；山西农业大学信息科学与工程学院、软件学院）。针对复杂牛舍场景中尺度变化、遮挡、光照变化、栏栅背景干扰等挑战，提出基于YOLOv12n的检测器DGF-YOLOv12n-LiteP2，结合动态局部-上下文特征融合与轻量级stride-4预测分支。在6991张图、132,302个身体部位标注的单站点数据集上：mAP50=93.92%、mAP75=79.27%、mAP50:95=69.88%（相对YOLOv12n提升9.61个百分点）。模型含1168万参数、需22.89 GFLOPs。","MDPI Sensors 2026, 26(19): 6156","2026-09-28T00:00:00Z",74,{"impact":124,"substance":125,"depth":18,"authority":20,"freshness":54,"relevant":22,"comment":126},15,22,"面向复杂牛舍的轻量化牛体部位检测模型，方法有创新、数据规模与精度指标扎实，对智慧畜牧视觉监测有实用参考价值。",[128],{"name":120,"url":118},[27,28,130,30,131],"目标检测","牛体部位检测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":135},{"candidates":136,"agricultural_evidence":47},[137,141,145,149],{"code":33,"score":17,"supported":47,"title":138,"abstract":139,"tags":140},[49],[],[],{"code":61,"score":82,"supported":14,"title":142,"abstract":143,"tags":144},[],[],[28,130],{"code":68,"score":22,"supported":14,"title":146,"abstract":147,"tags":148},[],[],[30],{"code":74,"score":22,"supported":14,"title":150,"abstract":151,"tags":152},[],[],[27],[154,155],"山西农业大学 牛体部位检测","DGF-YOLOv12n 牛舍检测","山西农业大学牛体部位检测-4160",{"doi":9,"openalex_id":9,"authors":158,"venue":9,"cited_by_count":102,"oa_url":9,"card":159,"direction":108,"ingested_from":164},[],{"tldr":160,"method":161,"finding":162,"direction":108,"opportunity":163},"提出DGF-YOLOv12n-LiteP2，实现复杂牛舍场景下牛体部位高精度检测。","基于YOLOv12n，融合动态门控局部-上下文特征与轻量stride-4预测分支","mAP50达93.92%，较YOLOv12n提升9.61个百分点，参数量1168万、22.89 GF","可探索多站点跨舍泛化、遮挡与光照鲁棒性提升，及轻量化模型在边缘设备的实时部署。","agent","2026-10-04T00:09:10.242632Z",{"id":167,"title":168,"url":169,"summary":170,"summary_zh":171,"content":9,"source_name":172,"source_url":169,"published_at":173,"category":12,"cover_url":9,"hotness":13,"is_selected":47,"score":174,"score_detail":175,"sources":179,"tags":181,"primary_topic":184,"secondary_topics":189,"classification":196,"search_phrases":232,"slug":235,"view_count":223,"doi":236,"paper":237,"created_at":255},2017,"Two Decades of Computer Vision in Precision Livestock Farming: an Umbrella Review of Applications, Benchmarking Evidence, and the Performance-to-Deployment Gap Across Cattle, Pig, and Poultry Systems","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112419","Computer vision is becoming a core technology in PLF, enabling non-contact monitoring, phenotyping, and decision support at both animal and group levels. This umbrella review synthesised review-level evidence from 112 reviews on cattle, pig, and poultry systems, covering visual applications for identification, phenotyping, health, behaviour, locomotion, body condition, growth, reproduction, mortality, and resource use. To preserve the review as the bibliographic unit while capturing multi-topic evidence, multi-label coding generated 328 review-domain assignments across six PLF computer vision domains. Health\u002Fstress and posture\u002Factivity were the most frequently reviewed areas; however, these patterns reflect review coverage rather than evidence strength. Benchmarking reporting averaged 11.09 out of 14 criteria, corresponding to 79.2%, but validation-critical items, including class balance, annotation protocols, validation splits, and farm or site reporting, remained less complete. Methodological confidence was limited: AMSTAR 2 classified 95 reviews as critically low and 17 as moderate, while ROBIS classified 78 as high, 17 as unclear, and 17 as low risk of bias. The corpus-level candidate-reference overlap estimate was 0.122% and is retained only as a sensitivity estimate, not as formal primary-study CCA or evidence of independence. Review-derived performance and readiness tiers identified a mean descriptive performance-to-deployment gap of 0.63 across 328 assignments. Overall, reported model performance continues to exceed documented farm-deployment evidence, highlighting the need for stronger external validation, transparent benchmarking, workflow integration, economic assessment, and user-readiness evidence before routine deployment claims can be supported.","计算机视觉正成为精准畜牧养殖（PLF）中的核心技术，能够在个体和群体层面实现非接触式监测、表型分析和决策支持。本伞状综述综合了112篇综述的综述级证据，涵盖牛、猪和家禽养殖系统，涉及识别、表型分析、健康、行为、运动、体况、生长、繁殖、死亡率和资源利用等视觉应用。为在保留综述作为文献计量单元的同时捕捉多主题证据，采用多标签编码在六个PLF计算机视觉领域中生成了328个综述-领域分配。健康\u002F应激和姿态\u002F活动是综述覆盖最多的领域；然而，这些模式反映的是综述覆盖情况而非证据强度。基准报告平均得分为14项标准中的11.09项，对应79.2%，但验证关键条目，包括类别平衡、标注方案、验证集划分以及农场或场地报告，仍不够完整。方法学可信度有限：AMSTAR 2将95篇综述评为极低质量，17篇评为中等质量；ROBIS将78篇评为高偏倚风险，17篇评为不明确，17篇评为低偏倚风险。语料库层面的候选参考文献重叠估计值为0.122%，仅作为敏感性估计保留，而非正式的一手研究CCA或独立性证据。基于综述推导的性能与就绪度分级在328个分配中识别出平均描述性性能-部署差距为0.63。总体而言，所报告的性能持续超过已记录的农场部署证据，凸显了在支持常规部署声明之前，需要更强的外部验证、透明的基准测试、工作流程整合、经济评估和用户就绪度证据。","Computers and Electronics in Agriculture","2026-09-09T00:00:00Z",87,{"impact":125,"substance":176,"depth":177,"authority":46,"freshness":21,"relevant":22,"comment":178},23,19,"基于112篇综述的伞式综述，系统揭示计算机视觉在牛猪禽精准养殖中性能与落地之间的差距，方法学与证据分级扎实，对智慧畜牧研发与部署具有较高参考价值。",[180],{"name":172,"url":169},[27,28,182,30,183],"计算机视觉","智能养殖",{"code":185,"slug":186,"name":187,"path":188,"parent_code":37},"C3","poultry","家禽","\u002Ftopic\u002Flivestock\u002Fpoultry",[190,195],{"code":61,"slug":191,"name":192,"path":193,"parent_code":194},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":197},{"candidates":198,"agricultural_evidence":47},[199,204,208,213,217,221,228],{"code":61,"score":177,"supported":47,"title":200,"abstract":202,"tags":203},[201],"computer vision",[182,201,65],[28,182],{"code":185,"score":46,"supported":47,"title":205,"abstract":206,"tags":207},[186],[187,186],[],{"code":37,"score":209,"supported":47,"title":210,"abstract":211,"tags":212},11,[58],[57],[],{"code":33,"score":209,"supported":47,"title":214,"abstract":215,"tags":216},[49],[49],[],{"code":68,"score":69,"supported":47,"title":218,"abstract":219,"tags":220},[],[30],[30],{"code":222,"score":223,"supported":47,"title":224,"abstract":225,"tags":227},"I7",3,[],[226],"文献计量",[],{"code":74,"score":22,"supported":14,"title":229,"abstract":230,"tags":231},[],[],[27],[233,234],"农业人工智能 计算机视觉 智慧农业 智能养殖","农业人工智能 计算机视觉","农业人工智能计算机视觉智慧农业智能养殖-2017","10.1016\u002Fj.compag.2026.112419",{"doi":236,"openalex_id":238,"authors":239,"venue":172,"cited_by_count":102,"oa_url":169,"card":250,"direction":110,"ingested_from":111},"W7212062011",[240,242,245,247],{"name":241,"orcid":9},"Alexey Ruchay",{"name":243,"orcid":244},"Vladimir Kolpakov","https:\u002F\u002Forcid.org\u002F0000-0001-9658-7034",{"name":246,"orcid":9},"Hao Guo",{"name":248,"orcid":249},"Andrea Pezzuolo","https:\u002F\u002Forcid.org\u002F0000-0002-9955-9896",{"tldr":251,"method":252,"finding":253,"direction":110,"opportunity":254},"伞式综述112篇综述，梳理牛猪禽精准养殖计算机视觉应用与部署差距。","伞式综述，多标签编码328项，AMSTAR 2与ROBIS评估方法学质量。","模型性能普遍高于农场部署证据，平均性能-部署差距0.63，验证与基准报告不足。","可研究外部验证、标准化基准与农场工作流集成，弥合性能到部署的鸿沟。","2026-09-10T23:30:01.497855Z",{"id":257,"title":258,"url":259,"summary":260,"summary_zh":9,"content":9,"source_name":261,"source_url":9,"published_at":262,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":263,"score_detail":264,"sources":268,"tags":270,"primary_topic":273,"secondary_topics":274,"classification":276,"search_phrases":294,"slug":297,"view_count":102,"doi":9,"paper":298,"created_at":306},5363,"牛肉牛区域特征计算机视觉分析:基于 YOLO 与深度估计的牛体况自动评分","https:\u002F\u002Fbioengineer.org\u002Fcameras-learn-to-read-a-cows-spine-tail-head-and-body-shape-to-score-its-condition","Islam M.N., Schrick F.N., Edwards J.L., Burns R.T., Qi H., Gan H. (2026) 开发一种基于区域特定计算机视觉特征的牛肉牛体况自动评分(BCS)方法。研究通过 YOLO 检测 + 深度估计提取脊柱、尾根、体廓等区域特征,使用 SHAP 进行可解释 AI 分析,并以 XGBoost 融合。在 5 折交叉验证中两种模式均稳定。验证集仅 72 只动物且极端值样本少,深度图来自推断而非实测。框架可作为后续发展的方法学基础。DOI: 10.1016\u002Fj.atech.2026.102628。","Smart Agricultural Technology Vol.15 Article 102628 2026-10-15","2026-10-15T00:00:00Z",68,{"impact":265,"substance":266,"depth":19,"authority":20,"freshness":54,"relevant":22,"comment":267},12,20,"方法学上有新意，但验证样本仅72头且深度图为推断值，属细分领域论文进展，未达每日精选门槛。",[269],{"name":261,"url":259},[27,28,182,271,272],"肉牛养殖","体况评分",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[275],{"code":61,"slug":191,"name":192,"path":193,"parent_code":194},{"status":40,"locked":14,"version":41,"method":42,"evidence":277},{"candidates":278,"agricultural_evidence":47},[279,285,290],{"code":61,"score":280,"supported":47,"title":281,"abstract":283,"tags":284},24,[182,282],"YOLO",[182,282],[28,182],{"code":33,"score":265,"supported":47,"title":286,"abstract":288,"tags":289},[287],"肉牛",[287],[271],{"code":74,"score":22,"supported":14,"title":291,"abstract":292,"tags":293},[],[],[27],[295,296],"YOLO 深度估计 牛体况评分","牛肉牛 计算机视觉 BCS","YOLO深度估计牛体况评分-5363",{"doi":9,"openalex_id":9,"authors":299,"venue":9,"cited_by_count":102,"oa_url":9,"card":300,"direction":304,"ingested_from":164},[],{"tldr":301,"method":302,"finding":303,"direction":304,"opportunity":305},"用YOLO检测与深度估计提取牛体区域特征，实现肉牛体况自动评分。","YOLO检测、深度估计、SHAP可解释分析与XGBoost融合，5折交叉验证。","区域特征融合评分稳定，但验证集仅72头且深度图为推断值。","农业遥感与作物表型","可引入实测深度传感器与更大样本，提升极端体况评分鲁棒性。","2026-10-20T02:47:54.361149Z",{"id":308,"title":309,"url":310,"summary":311,"summary_zh":312,"content":9,"source_name":313,"source_url":310,"published_at":314,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":315,"score_detail":316,"sources":318,"tags":320,"primary_topic":323,"secondary_topics":324,"classification":326,"search_phrases":344,"slug":347,"view_count":22,"doi":348,"paper":349,"created_at":370},4975,"Detection of mounting behavior and mounted ewes in group-housed environments using HSM-YOLO algorithm","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102639","The detection of mounting behavior and the mounted ewe is critical for estrus monitoring in sheep. However, existing methods suffer from low detection efficiency and high false detection rates due to the similarity between non-sexual and sexual mounting behaviors and the complexity of group-housed environments. To address these challenges, this study introduced a fine-grained classification of mounting behaviors into sexual and non-sexual categories, and further proposed an improved detection algorithm named Hu Sheep Mounting-YOLO (HSM-YOLO) based on the YOLOv11n architecture for detecting sheep mounting behavior and the corresponding mounted ewes. The HSM-YOLO algorithm employed depthwise separable convolution (DWSConv) to reduce the model complexity. To improve behavioral feature extraction and pose discrimination capabilities, it further integrated the C3k2_RepViTBlock-RepBottleneck (C3k2_BiRep) module, an efficient multi-scale attention (EMA) module, and the Inner-SIoU loss function. To evaluate the performance of the proposed algorithm, comparative experiments were conducted on a multiple scenarios dataset. The experimental results showed that the HSM-YOLO model achieved an F1 score of 88.1%, a mean Average Precision (mAP) of 90.2%, with 2.2M parameters and 5.4G floating-point operations (FLOPs). Compared to the baseline YOLOv11n model, HSM-YOLO improved the F1 score by 5.8% and the mAP by 5.7%, while reducing both model parameters and computational complexity. When deployed and tested on an RTX 4090, the system delivered an average detection speed of 47.9 frames per second (FPS). Moreover, despite considerable variation in detection performance across the four different imaging scenarios, HSM-YOLO consistently demonstrated superior detection accuracy. These results confirm that the HSM-YOLO provides a robust and efficient solution for detecting sheep mounting behaviors and mounted ewes in complex and variable scenarios, paving the way for the development of automated estrus monitoring systems.","检测羊只的爬跨行为及被爬跨母羊对于绵羊发情监测至关重要。然而，由于非性爬跨行为与性爬跨行为之间的相似性以及群养环境的复杂性，现有方法存在检测效率低和误检率高的问题。为解决这些挑战，本研究将爬跨行为细粒度分类为性爬跨和非性爬跨两类，并进一步提出了一种基于YOLOv11n架构的改进检测算法——湖羊爬跨-YOLO（HSM-YOLO），用于检测绵羊爬跨行为及相应的被爬跨母羊。HSM-YOLO算法采用深度可分离卷积（DWSConv）以降低模型复杂度。为提高行为特征提取和姿态判别能力，该算法进一步集成了C3k2_RepViTBlock-RepBottleneck（C3k2_BiRep）模块、高效多尺度注意力（EMA）模块以及Inner-SIoU损失函数。为评估所提算法的性能，在多场景数据集上进行了对比实验。实验结果表明，HSM-YOLO模型的F1分数达到88.1%，平均精度均值（mAP）达到90.2%，参数量为2.2M，浮点运算量为5.4G。与基线YOLOv11n模型相比，HSM-YOLO的F1分数提高了5.8%，mAP提高了5.7%，同时降低了模型参数量和计算复杂度。在RTX 4090上部署测试时，系统平均检测速度达到47.9帧每秒（FPS）。此外，尽管在四种不同成像场景下检测性能存在较大差异，HSM-YOLO始终展现出优越的检测精度。这些结果证实，HSM-YOLO为复杂多变场景下检测绵羊爬跨行为和被爬跨母羊提供了一种鲁棒且高效的解决方案，为自动化发情监测系统的开发奠定了基础。","Smart Agricultural Technology","2026-10-12T00:00:00Z",81,{"impact":18,"substance":125,"depth":18,"authority":46,"freshness":21,"relevant":22,"comment":317},"提出HSM-YOLO算法实现羊只爬跨行为与受体母羊检测，为自动化发情监测提供高效方案，方法新颖、指标扎实，具行业参考价值。",[319],{"name":313,"url":310},[27,28,130,321,322],"畜牧养殖","羊只发情监测",{"code":61,"slug":191,"name":192,"path":193,"parent_code":194},[325],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":327},{"candidates":328,"agricultural_evidence":47},[329,333,340],{"code":61,"score":20,"supported":47,"title":330,"abstract":331,"tags":332},[282],[282],[28,130],{"code":33,"score":21,"supported":47,"title":334,"abstract":335,"tags":339},[],[336,337,338],"湖羊","绵羊","sheep",[],{"code":74,"score":22,"supported":14,"title":341,"abstract":342,"tags":343},[],[],[27],[345,346],"HSM-YOLO 羊只爬跨行为 检测","绵羊 发情监测 目标检测","HSM-YOLO羊只爬跨行为检测-4975","10.1016\u002Fj.atech.2026.102639",{"doi":348,"openalex_id":350,"authors":351,"venue":313,"cited_by_count":102,"oa_url":310,"card":365,"direction":108,"ingested_from":111},"W7221573347",[352,354,356,358,361,363],{"name":353,"orcid":9},"Yanchao Wang",{"name":355,"orcid":9},"Ming Gao",{"name":357,"orcid":9},"Zhixin Hua",{"name":359,"orcid":360},"Asim Shakeel","https:\u002F\u002Forcid.org\u002F0000-0003-2942-9081",{"name":362,"orcid":9},"Chengyu Ren",{"name":364,"orcid":9},"Kaiying Wang",{"tldr":366,"method":367,"finding":368,"direction":108,"opportunity":369},"提出HSM-YOLO算法，在群养环境下检测羊爬跨行为及被爬跨母羊，用于发情监测。","基于YOLOv11n改进，引入DWSConv、C3k2_BiRep、EMA和In","F1达88.1%、mAP达90.2%，参数量2.2M，较基线提升且更轻量，检测速度47.9 FPS。","可延伸至多物种发情行为细粒度识别与轻量化边缘部署，结合时序信息提升监测实时性。","2026-10-15T23:30:03.393878Z",{"id":372,"title":373,"url":374,"summary":375,"summary_zh":376,"content":9,"source_name":377,"source_url":374,"published_at":378,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":379,"score_detail":380,"sources":382,"tags":384,"primary_topic":388,"secondary_topics":389,"classification":390,"search_phrases":447,"slug":450,"view_count":102,"doi":451,"paper":452,"created_at":463},4879,"Smart and Mechanized Feeding Systems for Goat Farming: Integrating Agricultural Engineering, Precision Livestock Management, and Sustainable Rural Development","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23344398","2. Alternative Research Titles 1. Design and Development of an Automated Goat Feeding System for Improved Farm Productivity and Labour Efficiency 2. Mechanization of Goat Feeding Operations: Engineering Innovations for Sustainable Livestock Production 3. Smart Livestock Feeding Technologies: A Framework for Automated Feed Distribution and Precision Goat Farming 4. Low-Cost Automated Feeding Systems for Smallholder Goat Farms: Design Considerations, Operational Efficiency, and Economic Feasibility 5. Application of Sensor-Based Automation in Goat Farming: Advancing Feed Management and Rural Agricultural Productivity 6. Intelligent Feeding Mechanisms for Small Ruminants: Integrating Mechanical Design, Automation, and Digital Monitoring 7. Sustainable Goat Farming Through Feeding Automation: Opportunities, Challenges, and Technological Perspectives 8. Engineering Approaches to Livestock Feed Management: Development of Mechanized Feeding Systems for Small and Medium-Scale Goat Farms 9. Precision Feeding in Goat Production: Integrating Smart Sensors, Automated Dispensing, and Sustainable Farm Management 10. From Traditional Feeding to Smart Livestock Farming: A Technology-Driven Approach to Goat Feed Distribution 3. Suggested Subtitle An Engineering-Based Framework for Automated Feed Distribution, Labour Reduction, Feed-Waste Management, and Affordable Precision Livestock Production in India. 4. Detailed Research Description Research Description Research Description The proposed research investigates the design principles, operational requirements, and potential agricultural applications of smart and mechanized feeding systems for goat farming. Inspired by a Telugu newspaper article depicting a mechanized feeding arrangement, the study explores how engineering innovations can improve the efficiency, consistency, and sustainability of livestock feeding operations. Traditional goat-feeding practices frequently involve manual feed preparation, transportation, and distribution. These activities can require substantial labour and may result in inconsistent feed allocation, spillage, and limited documentation of feed consumption. The proposed research addresses these challenges through a conceptual framework that combines mechanical feed handling, controlled dispensing, suitable distribution mechanisms, and optional sensor-assisted monitoring. The study will examine the integration of feed-storage hoppers, metering devices, motor-driven mechanisms, weighing sensors, microcontrollers, and monitoring interfaces. Particular attention will be given to the suitability of these components for different feed materials, including chopped fodder, forage mixtures, and concentrated feed. The system will be designed around the operational requirements of small and medium-scale goat farms, with emphasis on affordability, reliability, ease of maintenance, and adaptability to Indian agricultural conditions. A central component of the research is the development of a quantitative evaluation framework for comparing mechanized and conventional feeding practices. Relevant performance indicators include labour time per feeding cycle, feed-distribution uniformity, feed wastage, energy consumption, equipment reliability, maintenance requirements, and overall operating cost. If a prototype is constructed, controlled testing and farm-based trials can be used to determine whether the proposed design provides measurable improvements under realistic operating conditions. The research will also consider the role of digital technologies in precision livestock farming. Sensors and automated recordkeeping could support monitoring of delivered feed quantities, feed-bin levels, and equipment performance. Future extensions may incorporate Internet of Things connectivity and data analytics to support farm-management decisions. However, the system will be designed to retain essential operating and safety functions even when internet connectivity is unavailable. Animal welfare, nutritional suitability, and farm economics will remain central considerations. Mechanization must ensure appropriate feed access, hygienic feeding conditions, safe equipment operation, and compatibility with the nutritional requirements of goats. Economic analysis will examine initial investment, labour savings, potential reductions in feed losses, maintenance costs, energy requirements, and estimated payback period. The expected contribution is an engineering framework for developing and evaluating practical feeding automation technologies for goat farming. By connecting mechanical design with livestock-management requirements and rural economic considerations, the study seeks to establish a foundation for affordable, scalable, and sustainable agricultural mechanization. The proposed benefits will need to be established through prototype development and empirical validation rather than assumed in advance. 5. Research Objectives To develop a conceptual design for a mechanized goat-feeding system. To identify suitable feed-storage, metering, and distribution mechanisms. To evaluate the potential integration of sensors and automated control. To establish quantitative measures of feeding efficiency and feed wastage. To assess operational safety, animal welfare, and maintenance requirements. To formulate an economic evaluation framework for smallholder adoption. To propose future opportunities for IoT-enabled precision livestock management. 6. Proposed Research Novelty The potential novelty lies in integrating affordable mechanical feeding, quantity-controlled dispensing, and sensor-assisted monitoring into a modular system specifically evaluated for small and medium-scale goat farms. The novelty should be established through a systematic review of existing patents and research publications, followed by a clear comparison with previously developed livestock-feeding systems. The combination of existing components alone does not establish scientific novelty; the contribution should be demonstrated through a new design, validated performance improvement, or original experimental findings. 7. Recommended Keywords Goat farming; mechanized feeding; automated feed distribution; precision livestock farming; agricultural engineering; smart agriculture; feed management; Internet of Things; sustainable livestock production; rural mechanization; sensor-based automation; smallholder farming. 8. Author Details Geruganti Sudhakar Faculty Rajiv Gandhi University of Knowledge Technologies (RGUKT), IIIT Basar Telangana, India. My recommendation: Use the combined title in Section 1 for a broad, interdisciplinary review paper. If you plan to fabricate and experimentally test a feeder, Alternative Title 1 is more appropriate because it clearly communicates an engineering-development and validation study.","2. 备选研究标题 1. 用于提高农场生产力和劳动效率的自动化山羊饲喂系统的设计与开发 2. 山羊饲喂作业的机械化：可持续畜牧生产的工程创新 3. 智能畜牧饲喂技术：自动化饲料分配与精准山羊养殖框架 4. 面向小农户山羊养殖场的低成本自动化饲喂系统：设计考量、运行效率与经济可行性 5. 基于传感器的自动化技术在山羊养殖中的应用：推进饲料管理与农村农业生产力 6. 小型反刍动物的智能饲喂机制：机械设计、自动化与数字化监测的集成 7. 通过饲喂自动化实现可持续山羊养殖：机遇、挑战与技术展望 8. 畜牧饲料管理的工程方法：面向中小规模山羊养殖场的机械化饲喂系统开发 9. 山羊生产中的精准饲喂：智能传感器、自动化投喂与可持续农场管理的集成 10. 从传统饲喂到智能畜牧养殖：一种技术驱动的山羊饲料分配方法 3. 建议副标题 一种基于工程的框架，用于印度自动化饲料分配、劳动力减少、饲料浪费管理及可负担的精准畜牧生产。 4. 详细研究描述 研究描述 研究描述 本研究拟探讨山羊养殖中智能化和机械化饲喂系统的设计原理、运行要求及潜在农业应用。受一篇描述机械化饲喂装置的泰卢固语报纸文章启发，本研究探索工程创新如何提升畜牧饲喂作业的效率、一致性和可持续性。传统的山羊饲喂方式通常涉及人工饲料制备、运输和分配。这些活动可能需要大量劳动力，并可能导致饲料分配不均、撒漏以及饲料消耗记录有限。本研究拟通过一个概念框架应对这些挑战，该框架结合机械饲料处理、受控投喂、适宜的分配机制以及可选的传感器辅助监测。研究将考察饲料储存料斗、计量装置、电机驱动机构、称重传感器、","Zenodo (CERN European Organization for Nuclear Research)","2026-10-13T00:00:00Z",45,{"impact":17,"substance":265,"depth":13,"authority":54,"freshness":21,"relevant":22,"comment":381},"概念性研究提案，聚焦小规模山羊养殖的机械化与精准饲喂框架，对智慧畜牧方向有参考价值但尚无实证数据。",[383],{"name":377,"url":374},[27,385,386,30,387],"农业物联网","农业机械化","山羊养殖",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":391},{"candidates":392,"agricultural_evidence":47},[393,397,403,409,415,422,429,436,442],{"code":37,"score":46,"supported":47,"title":394,"abstract":395,"tags":396},[58],[57,58],[],{"code":33,"score":46,"supported":47,"title":398,"abstract":400,"tags":402},[399],"goat",[401,399],"山羊",[],{"code":404,"score":17,"supported":47,"title":405,"abstract":407,"tags":408},"G",[406],"rural development",[],[],{"code":68,"score":410,"supported":47,"title":411,"abstract":412,"tags":414},7,[],[30,413],"animal welfare",[30],{"code":416,"score":410,"supported":47,"title":417,"abstract":418,"tags":421},"I5",[],[419,420],"internet of things","IoT",[385],{"code":423,"score":54,"supported":47,"title":424,"abstract":425,"tags":428},"C4",[],[426,427],"饲料","forage",[],{"code":430,"score":54,"supported":47,"title":431,"abstract":432,"tags":435},"G2",[],[433,434],"小农户","smallholder",[],{"code":437,"score":69,"supported":47,"title":438,"abstract":439,"tags":441},"F5",[],[440],"机械化",[386],{"code":74,"score":69,"supported":47,"title":443,"abstract":444,"tags":446},[],[445],"smart agriculture",[27],[448,449],"山羊 机械化饲喂 系统","精准畜牧 自动投喂 印度","山羊机械化饲喂系统-4879","10.5281\u002Fzenodo.23344398",{"doi":451,"openalex_id":453,"authors":454,"venue":377,"cited_by_count":102,"oa_url":374,"card":458,"direction":110,"ingested_from":111},"W7221716542",[455],{"name":456,"orcid":457},"Sudhakar Geruganti","https:\u002F\u002Forcid.org\u002F0009-0000-0039-7536",{"tldr":459,"method":460,"finding":461,"direction":110,"opportunity":462},"提出山羊养殖智能机械化喂料系统的设计框架，整合工程、精准畜牧与农村可持续发展。","概念框架设计，结合料斗、计量装置、电机驱动、称重传感器等。","机械化喂料可减少劳动力、稳定投喂量、降低饲料浪费并提升记录能力。","面向小农户的低成本自动化喂料系统缺乏实证，可研究其经济可行性与传感器集成效果。","2026-10-14T23:30:08.923193Z",{"id":465,"title":466,"url":467,"summary":468,"summary_zh":469,"content":9,"source_name":470,"source_url":467,"published_at":471,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":472,"score_detail":473,"sources":476,"tags":478,"primary_topic":482,"secondary_topics":483,"classification":485,"search_phrases":531,"slug":534,"view_count":62,"doi":535,"paper":536,"created_at":555},4422,"Artificial intelligence driven framework for enhancing sustainability and resilience in communal cattle insurance in Lupane District Zimbabwe","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44279-026-00786-y","Communal cattle farming in Sub-Saharan Africa continues to face destabilization from non-linear climate variability, yet insurance penetration remains negligible. In Lupane District, Zimbabwe, uptake is exceptionally low at approximately 0.01%, despite recurrent droughts that threaten household livelihoods. This study aimed to develop an AI-driven framework to enhance sustainability and resilience in communal cattle insurance within the district. A positivist research philosophy guided the study, and a quantitative approach was adopted. The Kothari sample size determination formula was applied to derive a statistically representative sample of 219 households from a population of 49,841 communal cattle farmers distributed across four villages in 23 wards. Data were collected through KoboCollect, transmitted to secure servers, and analyzed using JAMOVI version 2.6.44. Descriptive statistics indicated that the majority of farmers were male (62%), with an average age of 47 years and herd sizes ranging from 3 to 25 cattle. Education levels were generally low, with 54% reporting primary schooling and only 12% having secondary or higher qualifications. Income sources were largely subsistence-based, and 71% of respondents relied on cattle as their primary asset. Binary logistic regression revealed that affordability (β = 1.25, p \u003C 0.01) and awareness (β = 0.99, p \u003C 0.01) were the strongest determinants of adoption, while institutional trust (β = 0.74, p \u003C 0.05) emerged as a significant direct predictor of adoption willingness. The study was theoretically anchored in the Technology Acceptance Model (TAM), which explains how perceived usefulness and perceived ease of use influence uptake. Informed by findings from Objectives 1 and 2, the study proposes the Tri-Modular AI Resilience Engine (TMAIE). TMAIE integrates Convolutional Neural Networks (CNN) for biometric cattle identification, Recurrent Neural Networks (RNN) for satellite-derived NDVI index triggers, and Transformer-based Natural Language Processing (NLP) localized in IsiNdebele and ChiShona for inclusive voice-based access. The study findings suggest that adoption is not a linear process but an adaptive evolution requiring both technological and social mechanisms. The proposed framework reflects these relationships through the integration of technological precision and community-based mediation. Overall, the findings provide empirical evidence on the determinants of cattle insurance adoption and inform the development of a conceptual AI-driven framework that may support future climate-resilient livestock insurance innovations, subject to further validation and testing.","撒哈拉以南非洲的社区养牛业持续面临非线性气候变率的冲击，然而保险渗透率仍然微不足道。在津巴布韦卢潘内区，尽管反复发生的干旱威胁着家庭生计，但参保率仍极低，约为0.01%。本研究旨在开发一个人工智能驱动的框架，以提升该区社区养牛保险的可持续性和韧性。本研究以实证主义研究哲学为指导，采用定量研究方法。应用Kothari样本量确定公式，从分布于23个选区4个村庄的49841名社区养牛户总体中，推导出具有统计代表性的219户样本。数据通过KoboCollect采集，传输至安全服务器，并使用JAMOVI 2.6.44版本进行分析。描述性统计表明，大多数农户为男性（62%），平均年龄47岁，牛群规模为3至25头。教育水平普遍较低，54%报告仅接受过小学教育，仅12%拥有中学或更高学历。收入来源大多以自给自足为基础，71%的受访者将牛作为其主要资产。二元逻辑回归显示，可负担性（β = 1.25，p \u003C 0.01）和认知度（β = 0.99，p \u003C 0.01）是参保的最强决定因素，而制度信任（β = 0.74，p \u003C 0.05）则是参保意愿的显著直接预测因素。本研究在理论上以技术接受模型（TAM）为锚点，该模型解释了感知有用性和感知易用性如何影响采纳行为。基于目标1和目标2的研究结果，本研究提出了三模块人工智能韧性引擎（TMAIE）。TMAIE整合了用于牛只生物特征识别的卷积神经网络（CNN）、用于卫星衍生NDVI指数触发的循环神经网络（RNN），以及基于Transformer的、以恩德贝莱语和绍纳语本地化的自然语言处理（NLP），以实现包容性的语音访问。研究结果表明，采纳并非线性过程，而是一种需要技术和社会机制共同作用的自适应演化。所提出的框架通过整合技术精确性与社区中介来反映这些关系。总体而言，研究结果提供了关于养牛保险采纳决定因素的实证证据，并为","Discover Agriculture","2026-10-06T00:00:00Z",70,{"impact":265,"substance":474,"depth":19,"authority":265,"freshness":17,"relevant":22,"comment":475},21,"以津巴布韦Lupane地区社区养牛保险为对象，提出融合CNN牛只识别、NDVI遥感触发与本地语言NLP的AI框架，方法具体、数据扎实，但属区域性案例研究，对国内农业信息化有借鉴意义而非直接影响。",[477],{"name":470,"url":467},[479,27,28,480,481],"数字乡村","农业保险","遥感监测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[484],{"code":61,"slug":191,"name":192,"path":193,"parent_code":194},{"status":40,"locked":14,"version":41,"method":42,"evidence":486},{"candidates":487,"agricultural_evidence":47},[488,492,497,501,507,512,517,521,526],{"code":33,"score":209,"supported":47,"title":489,"abstract":490,"tags":491},[49],[49],[],{"code":61,"score":21,"supported":47,"title":493,"abstract":495,"tags":496},[494],"artificial intelligence",[],[28],{"code":37,"score":223,"supported":47,"title":498,"abstract":499,"tags":500},[],[58],[],{"code":502,"score":223,"supported":47,"title":503,"abstract":504,"tags":506},"H7",[],[505],"干旱",[],{"code":222,"score":223,"supported":47,"title":508,"abstract":509,"tags":511},[],[510],"研究方法",[],{"code":513,"score":22,"supported":14,"title":514,"abstract":515,"tags":516},"G3",[],[],[480],{"code":74,"score":22,"supported":14,"title":518,"abstract":519,"tags":520},[],[],[27],{"code":522,"score":22,"supported":14,"title":523,"abstract":524,"tags":525},"I3",[],[],[481],{"code":527,"score":22,"supported":14,"title":528,"abstract":529,"tags":530},"I6",[],[],[479],[532,533],"津巴布韦 Lupane 牛保险","AI 牲畜保险 框架","津巴布韦Lupane牛保险-4422","10.1007\u002Fs44279-026-00786-y",{"doi":535,"openalex_id":537,"authors":538,"venue":470,"cited_by_count":102,"oa_url":548,"card":549,"direction":110,"ingested_from":111},"W7220655164",[539,542,545],{"name":540,"orcid":541},"Nyasha Nyakuchena","https:\u002F\u002Forcid.org\u002F0009-0005-3219-2275",{"name":543,"orcid":544},"Joseph P. Musara","https:\u002F\u002Forcid.org\u002F0000-0002-2226-3616",{"name":546,"orcid":547},"Emmanuel Zivenge","https:\u002F\u002Forcid.org\u002F0000-0003-4740-8225","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs44279-026-00786-y.pdf",{"tldr":550,"method":551,"finding":552,"direction":553,"opportunity":554},"研究提出AI驱动的三模块框架，以提升津巴布韦Lupane地区社区牛保险的可持续性和韧性。","对219户农户进行问卷调查，用二元逻辑回归分析，并设计CNN、RNN和Trans","可负担性和意识是保险采纳的最强决定因素，机构信任也显著影响采纳意愿。","数字乡村与农业信息化","可验证TMAIE框架在类似地区的适用性，并探索AI语音交互对低教育水平农户保险采纳的长期影响。","2026-10-08T23:30:11.018464Z"]