[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2015":3,"related-2015":104},{"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":23,"tags":25,"primary_topic":30,"secondary_topics":36,"classification":43,"search_phrases":68,"slug":71,"view_count":72,"doi":73,"paper":74,"created_at":103},2015,"Mitigating artificial intelligence-related animal welfare risks in animal farming","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112408","Mitigating artificial intelligence-related animal welfare risks in animal farming。Computers and Electronics in Agriculture","减轻畜牧业中与人工智能相关的动物福利风险。《计算机与电子农业》",null,"Computers and Electronics in Agriculture","2026-09-10T00:00:00Z","论文",10,false,79,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":13,"relevant":21,"comment":22},18,20,17,14,1,"核心期刊新论文，聚焦AI在畜牧养殖中的动物福利风险与缓解路径，属智慧养殖前沿议题，具行业参考价值。",[24],{"name":10,"url":6},[26,27,28,29],"农业人工智能","智慧养殖","风险治理","动物福利",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},"C6","smart-livestock","养殖环境与智慧畜牧","\u002Ftopic\u002Flivestock\u002Fsmart-livestock","C",[37],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":44,"locked":14,"version":45,"method":46,"evidence":47},"classified","2026-10-22.2","rules",{"candidates":48,"agricultural_evidence":51},[49,56,62],{"code":31,"score":50,"supported":51,"title":52,"abstract":54,"tags":55},15,true,[53],"animal welfare",[29,53],[29],{"code":38,"score":57,"supported":51,"title":58,"abstract":60,"tags":61},12,[59],"artificial intelligence",[59],[26],{"code":35,"score":63,"supported":51,"title":64,"abstract":65,"tags":67},3,[],[66],"畜牧",[],[69,70],"农业人工智能 动物福利 智慧养殖 风险治理","农业人工智能 动物福利","农业人工智能动物福利智慧养殖风险治理-2015",4,"10.1016\u002Fj.compag.2026.112408",{"doi":73,"openalex_id":75,"authors":76,"venue":10,"cited_by_count":95,"oa_url":6,"card":96,"direction":100,"ingested_from":102},"W7211988489",[77,80,82,84,86,88,90,92],{"name":78,"orcid":79},"Joshua Jarvis‐Campbell","https:\u002F\u002Forcid.org\u002F0009-0008-7307-703X",{"name":81,"orcid":9},"Marina A.G. von Keyserlingk",{"name":83,"orcid":9},"Albert Didriksen",{"name":85,"orcid":9},"Maximus Rafla",{"name":87,"orcid":9},"Carmen Lopez",{"name":89,"orcid":9},"Jack Zhu",{"name":91,"orcid":9},"Alistair Bugg",{"name":93,"orcid":94},"Borbala Foris","https:\u002F\u002Forcid.org\u002F0000-0002-0901-3057",0,{"tldr":97,"method":98,"finding":99,"direction":100,"opportunity":101},"探讨如何缓解动物养殖中人工智能应用带来的动物福利风险。","综述分析AI在养殖中的福利风险与缓解策略。","需建立伦理框架与技术措施以降低AI对动物福利的负面影响。","智慧农业 \u002F 农业物联网","可研究AI养殖中动物福利风险的量化评估与实时监测预警系统。","openalex","2026-09-10T23:30:01.332132Z",{"total":105,"page":21,"page_size":105,"items":106},6,[107,172,275,343,392,469],{"id":108,"title":109,"url":110,"summary":111,"summary_zh":112,"content":9,"source_name":113,"source_url":110,"published_at":114,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":115,"score_detail":116,"sources":119,"tags":121,"primary_topic":125,"secondary_topics":126,"classification":128,"search_phrases":151,"slug":154,"view_count":21,"doi":155,"paper":156,"created_at":171},4426,"Animal welfare in the world of digitalization: Computer Vision in the context of foundational structures","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs43681-026-01417-4","Abstract Computer Vision is an emerging technology within Precision Livestock Farming (PLF), combining camera systems with artificial intelligence to monitor animal welfare. While animal ethicists recognize its potential benefits, they also raise concerns about possible negative implications for animal welfare. This paper argues that addressing ethical concerns cannot rely on solutions targeting isolated ethical risks; rather, potential solutions must account for the technology’s embeddedness within society-wide structures. The focus in this paper will be on foundational structures, these structures concern how the world is experienced and understood, what is taken as self-evident. Over centuries, humans have increasingly delegated tasks to machines and standardized the world in doing so. This process has fostered growing trust in the outcomes of (digital) technologies. These developments have changed human experience and understanding of the world in various ways. Farmers, as members of society, are unlikely to be exempt from this trend. Therefore, reflection on Computer Vision must go beyond the farming practice and take into account these foundational structures that are currently reshaping society at large. Computer Vision examined as embedded within foundational structures demonstrates that ethical issues are also embedded within these structures, consequently, potential solutions must take account of them to increase their effectiveness.","摘要 计算机视觉是精准畜牧业（PLF）中的一项新兴技术，它将摄像系统与人工智能相结合，以监测动物福利。尽管动物伦理学家认可其潜在益处，但也对其可能给动物福利带来的负面影响表示担忧。本文认为，解决伦理关切不能依赖于针对孤立伦理风险的方案；相反，潜在的解决方案必须考虑到该技术嵌入于全社会结构之中的事实。本文的关注重点将是基础性结构，这些结构关乎世界如何被体验和理解，以及什么被视为不言自明。几个世纪以来，人类越来越多地将任务委托给机器，并在此过程中使世界标准化。这一进程培育了人们对（数字）技术产物的日益信任。这些发展以多种方式改变了人类对世界的体验和理解。农民作为社会成员，不太可能置身于这一趋势之外。因此，对计算机视觉的反思必须超越养殖实践，并考虑到这些当前正在重塑整个社会的基础性结构。将计算机视觉置于基础性结构中加以审视表明，伦理问题同样嵌入于这些结构之中，因此，潜在的解决方案必须将其纳入考量，以提高其有效性。","AI and Ethics","2026-10-06T00:00:00Z",72,{"impact":57,"substance":18,"depth":17,"authority":20,"freshness":117,"relevant":21,"comment":118},8,"从社会基础结构层面反思计算机视觉在精准畜牧中的伦理嵌入，视角新颖、论证扎实，对智慧农业伦理治理有参考价值。",[120],{"name":113,"url":110},[122,26,123,29,124],"智慧农业","计算机视觉","精准畜牧",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[127],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":129},{"candidates":130,"agricultural_evidence":51},[131,136,141,146],{"code":31,"score":132,"supported":51,"title":133,"abstract":134,"tags":135},19,[53],[124,29,53],[29,124],{"code":38,"score":132,"supported":51,"title":137,"abstract":139,"tags":140},[138],"computer vision",[123,59,138],[26,123],{"code":35,"score":105,"supported":51,"title":142,"abstract":143,"tags":145},[],[66,144],"livestock",[],{"code":147,"score":21,"supported":14,"title":148,"abstract":149,"tags":150},"I1",[],[],[122],[152,153],"计算机视觉 精准畜牧 动物福利","农业人工智能 计算机视觉 动物福利 智慧农业","计算机视觉精准畜牧动物福利-4426","10.1007\u002Fs43681-026-01417-4",{"doi":155,"openalex_id":157,"authors":158,"venue":113,"cited_by_count":95,"oa_url":165,"card":166,"direction":100,"ingested_from":102},"W7220695950",[159,162],{"name":160,"orcid":161},"Mariska Thalitha Bosschaert","https:\u002F\u002Forcid.org\u002F0000-0002-9160-7638",{"name":163,"orcid":164},"Bart Gremmen","https:\u002F\u002Forcid.org\u002F0000-0002-9652-6407","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs43681-026-01417-4.pdf",{"tldr":167,"method":168,"finding":169,"direction":100,"opportunity":170},"论文论证计算机视觉用于动物福利时，伦理问题须置于社会基础结构中理解。","概念分析与伦理反思，结合精准畜牧中计算机视觉技术。","伦理问题嵌入社会基础结构，孤立风险方案无效，需整体考量。","可实证研究农民对计算机视觉的信任如何受社会基础结构影响，并设计嵌入伦理的监测系统。","2026-10-08T23:30:12.350082Z",{"id":173,"title":174,"url":175,"summary":176,"summary_zh":177,"content":9,"source_name":178,"source_url":175,"published_at":179,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":180,"score_detail":181,"sources":185,"tags":187,"primary_topic":191,"secondary_topics":192,"classification":194,"search_phrases":233,"slug":236,"view_count":237,"doi":238,"paper":239,"created_at":274},3917,"Risk-based prioritization of official animal welfare inspections using machine learning","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffvets.2026.1938469","Introduction For official animal welfare inspections in Austria, at least 2% of agricultural livestock farms must be selected and inspected on the basis of a risk-based random sample. In the federal state of Styria, more than 19,000 farms keep livestock, while the inspection capacity of official veterinarians is limited, requiring efficient prioritization of farm checks. This study aimed to develop a machine learning model leveraging routinely collected administrative and animal health data to identify farms in Styria at higher risk of animal welfare violations. Methods The statistical analyses incorporated the outcomes of animal welfare inspections from 2019 to 2023, aggregated by farm and year. A total of 2,647 aggregated inspection results were used to train an Extreme Gradient Boosting (XGBoost) model, with a further 475 results used for testing purposes. Information about farms (e.g., production type, farmer and regional data, livestock data), as well as slaughter and meat inspection data, was acquired from the Consumer Health Information System database ( Verbrauchergesundheitsinformationssystem , VIS). Additionally, data from local fallen stock rendering plants and information on antibiotics dispensed to farmers were available and incorporated into the model. Results Results showed a moderate model performance with AUC (Area under the curve) of 0.75 (95%-CI [0.66, 0.82]), MCC (Matthews Correlation Coefficient) of 0.25 (95%-CI [0.19, 0.37]) and AP (Average Precision) of 0.19 (95%-CI [0.11–0.31]) for the test set. Post-hoc model interpretation revealed as most important influencing features antibiotic dispensing in cattle production, particularly overall quantities and European Medicines Agency Category D antibiotics, followed by farmer-related characteristics such as farmer age and the distance between the farm and the farmer’s residence. Membership in the Animal Health Service ( Tiergesundheitsdienst , TGD) was associated with a decrease in the model-predicted probability of animal welfare violations. Other relevant factors included the number of livestock units (cattle and poultry) on farm, cattle mortality recorded by rendering plants, and certain findings at meat inspection, such as pericarditis in pigs. Discussion These results indicate that routinely recorded administrative and veterinary data can provide meaningful indicators for identifying farms with a higher risk of animal welfare violations. Although some predictors appear indirectly linked to welfare, they likely reflect broader farm management practices and animal health status. Risk-based sampling could support veterinary authorities in prioritizing farms for inspection and allocating inspection resources more efficiently.","引言 在奥地利，官方动物福利检查要求至少对2%的农业牲畜养殖场进行基于风险的随机抽样检查。在施泰尔马克州，超过19,000个养殖场饲养牲畜，而官方兽医的检查能力有限，因此需要高效地确定养殖场检查的优先顺序。本研究旨在开发一种机器学习模型，利用常规收集的行政和动物健康数据，识别施泰尔马克州动物福利违规风险较高的养殖场。方法 统计分析纳入了2019年至2023年动物福利检查的结果，按养殖场和年份汇总。共有2,647条汇总检查结果用于训练极端梯度提升（XGBoost）模型，另有475条结果用于测试。养殖场相关信息（如生产类型、养殖者及区域数据、牲畜数据）以及屠宰和肉类检验数据均获取自消费者健康信息系统数据库（Verbrauchergesundheitsinformationssystem，VIS）。此外，当地病死动物无害化处理厂的数据以及养殖者抗生素发放信息也可获取，并纳入模型。结果 结果显示模型性能中等，测试集的AUC（曲线下面积）为0.75（95%-CI [0.66, 0.82]），MCC（马修斯相关系数）为0.25（95%-CI [0.19, 0.37]），AP（平均精度）为0.19（95%-CI [0.11–0.31]）。事后模型解释显示，最重要的影响因素是养牛生产中的抗生素发放，特别是总体用量和欧洲药品管理局D类抗生素，其次是养殖者相关特征，如养殖者年龄和养殖场与养殖者住所之间的距离。加入动物健康服务（Tiergesundheitsdienst，TGD）与模型预测的动物福利违规概率降低相关。其他相关因素包括养殖场牲畜单位数（牛和家禽）、无害化处理厂记录的牛死亡率，以及肉类检验中的某些发现，如猪心包炎。讨论 这些结果表明，常规记录的行政和兽医数据可为识别动物福利违规风险较高的养殖场提供有意义的指标。尽管一些预测因素似乎间接相关","Frontiers in Veterinary Science","2026-09-30T00:00:00Z",81,{"impact":17,"substance":182,"depth":17,"authority":20,"freshness":183,"relevant":21,"comment":184},22,9,"奥地利用XGBoost整合屠宰、抗生素与病死畜数据预测动物福利违规风险，为有限兽医检验资源提供风险分级抽样依据，方法可迁移至我国畜牧监管信息化。",[186],{"name":178,"url":175},[122,188,189,29,190],"机器学习","畜牧兽医","风险分级监管",{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},[193],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":195},{"candidates":196,"agricultural_evidence":51},[197,201,206,213,217,223,229],{"code":31,"score":50,"supported":51,"title":198,"abstract":199,"tags":200},[53],[29,53],[29],{"code":38,"score":50,"supported":51,"title":202,"abstract":204,"tags":205},[203],"machine learning",[188,203],[188],{"code":207,"score":105,"supported":51,"title":208,"abstract":209,"tags":212},"C3",[],[210,211],"家禽","poultry",[],{"code":35,"score":72,"supported":51,"title":214,"abstract":215,"tags":216},[],[144],[189],{"code":218,"score":63,"supported":51,"title":219,"abstract":220,"tags":222},"C2",[],[221],"cattle",[],{"code":224,"score":63,"supported":51,"title":225,"abstract":226,"tags":228},"C5",[],[227],"veterinary",[],{"code":147,"score":21,"supported":14,"title":230,"abstract":231,"tags":232},[],[],[122],[234,235],"奥地利 施蒂里亚 动物福利 机器学习","XGBoost 动物福利 风险评估","奥地利施蒂里亚动物福利机器学习-3917",2,"10.3389\u002Ffvets.2026.1938469",{"doi":238,"openalex_id":240,"authors":241,"venue":178,"cited_by_count":95,"oa_url":175,"card":268,"direction":272,"ingested_from":102},"W7214951739",[242,244,246,248,250,253,255,257,259,262,265],{"name":243,"orcid":9},"Eva Obenaus",{"name":245,"orcid":9},"Sabrina Kuchling",{"name":247,"orcid":9},"Tadej Zerak",{"name":249,"orcid":9},"Corina Schleicher",{"name":251,"orcid":252},"Ian Kopacka","https:\u002F\u002Forcid.org\u002F0000-0003-4106-1742",{"name":254,"orcid":9},"Sven Budik",{"name":256,"orcid":9},"Sabine Grimme",{"name":258,"orcid":9},"Jörg Hiesel",{"name":260,"orcid":261},"Peter Eckhardt","https:\u002F\u002Forcid.org\u002F0009-0005-5015-4846",{"name":263,"orcid":264},"Johannes Baumgartner","https:\u002F\u002Forcid.org\u002F0000-0001-8555-1378",{"name":266,"orcid":267},"Clair L. Firth","https:\u002F\u002Forcid.org\u002F0000-0002-4919-7786",{"tldr":269,"method":270,"finding":271,"direction":272,"opportunity":273},"用机器学习基于常规行政与兽医数据，对奥地利农场动物福利违规风险进行优先级排序。","XGBoost模型，使用2019-2023年2647条检查结果及VIS等行政兽医","模型AUC 0.75，抗生素发放量、农户年龄和距离等是动物福利违规的重要预测因子。","农业人工智能与决策模型","可探索将常规兽医行政数据与机器学习结合，用于其他农业合规监管的精准抽查与风险预警。","2026-10-01T23:30:54.115236Z",{"id":276,"title":277,"url":278,"summary":279,"summary_zh":280,"content":9,"source_name":281,"source_url":278,"published_at":282,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":180,"score_detail":283,"sources":285,"tags":287,"primary_topic":290,"secondary_topics":291,"classification":293,"search_phrases":322,"slug":325,"view_count":326,"doi":327,"paper":328,"created_at":342},2746,"Fostering artificial intelligence in the livestock sector: Adoption factors and policy insights from the case of Spain","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.agsy.2026.104956","CONTEXT AND PURPOSE The integration of Artificial Intelligence (AI) and Precision Livestock Farming (PLF) offers significant opportunities to improve the productivity, animal welfare and sustainability of the livestock sector. However, the adoption of these technologies remains highly uneven. Moving beyond descriptive statistics, this study investigates the complex, interacting factors associated with AI adoption in the Spanish livestock sector. METHODOLOGY Utilising a survey-based sample of 666 Spanish livestock holdings, drawn from a national survey whose sampling was designed to be proportional to the 2020 Agricultural Census by subsector and region, a Partial Least Squares Structural Equation Modelling (PLS-SEM) approach was employed to evaluate a comprehensive adoption framework across different farming systems and operational scales. AI adoption was modelled as a formative composite of five self-reported AI system categories, and the framework was tested through mediation, moderation, subgroup and out-of-sample predictive analyses with a 10,000-resample bootstrap. MAIN FINDINGS The empirical results indicate that AI adoption is most strongly associated with a holding's baseline technological infrastructure (β = 0.6464, p \u003C 0.001); advanced predictive tools appear to presuppose a pre-existing ecosystem of digital farm books, automated feeding systems and interoperable sensors. A ‘perception-capability gap’ is formally supported: perceived benefits are associated with adoption only indirectly, through the infrastructure baseline (indirect-only mediation), and their association strengthens as infrastructure increases (positive interaction). Recognition of AI's theoretical benefits or awareness of public subsidies is thus not independently associated with adoption in the absence of foundational digital capability. Furthermore, the study identifies a stark structural divide: adoption reaches 56.3% in intensive and semi-intensive holdings but only 24.4% in extensive ones (χ2 = 57.61, p \u003C 0.001), as traditional extensive systems face severe physical and connectivity barriers that leave them systematically disadvantaged. Results are robust across reflective, count, reduced-indicator and logistic specifications, and the model shows substantial out-of-sample predictive power (Q 2 predict ≈ 0.53). CONCLUSIONS To facilitate a more inclusive digital transformation, the findings suggest that policymakers should adopt a ‘readiness-conditional’ model, ensuring farms meet baseline digital prerequisites and have access to robust extension services before subsidising advanced AI tools.","背景与目的 人工智能（Artificial Intelligence, AI）与精准畜牧业（Precision Livestock Farming, PLF）的融合为提升畜牧部门的生产力、动物福利和可持续性提供了重要机遇。然而，这些技术的采用仍然极不均衡。本研究超越描述性统计，探讨了西班牙畜牧部门中与AI采用相关的复杂交互因素。方法 基于一项全国性调查中抽取的666个西班牙畜牧养殖场的样本（该调查的抽样设计按2020年农业普查的子部门和地区比例进行），采用偏最小二乘结构方程模型（Partial Least Squares Structural Equation Modelling, PLS-SEM）方法，评估了一个跨不同养殖系统和经营规模的综合采用框架。AI采用被建模为五个自我报告的AI系统类别的形成性复合变量，并通过中介、调节、子组和样本外预测分析（10,000次重抽样自助法）对框架进行了检验。主要发现 实证结果表明，AI采用与养殖场的基线技术基础设施关联最为密切（β = 0.6464，p \u003C 0.001）；先进的预测工具似乎以已有的数字牧场记录、自动化饲喂系统和可互操作传感器生态系统为前提。“感知—能力差距”得到正式支持：感知收益仅通过基础设施基线间接与采用相关（仅间接中介），且其关联随基础设施的增加而增强（正向交互）。因此，在缺乏基础数字能力的情况下，对AI理论效益的认可或对公共补贴的知晓与采用并无独立关联。此外，研究识别出一条鲜明的结构性分界线：集约化和半集约化养殖场的采用率达到56.3%，而粗放型养殖场仅为24.4%（χ2 = 57.61，p \u003C 0.001），因为传统粗放型系统面临严重的物理和连接障碍，使其处于系统性劣势。结果在反映性、计数、简化指标和逻辑斯谛设定下均稳健，且模型显示出显著的样本外预测能力（Q 2 predict ≈ 0.53）。结论 为促进更具包容性的数字化转型，研究结果表明政策制定者应采取“就绪条件”模型，确保养殖场","Agricultural Systems","2026-09-16T00:00:00Z",{"impact":17,"substance":182,"depth":17,"authority":20,"freshness":183,"relevant":21,"comment":284},"基于666个西班牙牧场样本的实证研究，揭示AI采纳受数字基础设施制约的“感知—能力鸿沟”，并提出“就绪条件式”补贴政策思路，对智慧畜牧推广与数字乡村政策设计有参考价值。",[286],{"name":281,"url":278},[122,26,288,289,124],"数字素养","农业补贴",{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},[292],{"code":31,"slug":32,"name":33,"path":34,"parent_code":35},{"status":44,"locked":14,"version":45,"method":46,"evidence":294},{"candidates":295,"agricultural_evidence":51},[296,300,304,308,313,317],{"code":35,"score":20,"supported":51,"title":297,"abstract":298,"tags":299},[144],[66,144],[],{"code":38,"score":57,"supported":51,"title":301,"abstract":302,"tags":303},[59],[59],[26],{"code":31,"score":13,"supported":51,"title":305,"abstract":306,"tags":307},[],[124,29,53],[124],{"code":309,"score":21,"supported":14,"title":310,"abstract":311,"tags":312},"G3",[],[],[289],{"code":147,"score":21,"supported":14,"title":314,"abstract":315,"tags":316},[],[],[122],{"code":318,"score":21,"supported":14,"title":319,"abstract":320,"tags":321},"I6",[],[],[288],[323,324],"农业人工智能 农业补贴 数字素养 智慧农业","农业人工智能 农业补贴","农业人工智能农业补贴数字素养智慧农业-2746",5,"10.1016\u002Fj.agsy.2026.104956",{"doi":327,"openalex_id":329,"authors":330,"venue":281,"cited_by_count":95,"oa_url":278,"card":336,"direction":340,"ingested_from":102},"W7213425399",[331,333],{"name":332,"orcid":9},"Carlos Parra-Lopez",{"name":334,"orcid":335},"Carmen Carmona‐Torres","https:\u002F\u002Forcid.org\u002F0000-0002-6982-1363",{"tldr":337,"method":338,"finding":339,"direction":340,"opportunity":341},"基于西班牙666家养殖场调查，用PLS-SEM分析AI采纳的影响因素与政策启示。","666份养殖场问卷，PLS-SEM建模，含中介、调节与分组分析。","AI采纳最依赖既有数字基础设施；感知收益仅间接起作用，集约场采纳率远高于粗放场。","数字乡村与农业信息化","可研究粗放养殖场数字基础设施与连接性短板，设计‘就绪度条件’式推广与补贴机制。","2026-09-17T23:30:04.844104Z",{"id":344,"title":345,"url":346,"summary":347,"summary_zh":9,"content":9,"source_name":348,"source_url":9,"published_at":349,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":350,"score_detail":351,"sources":355,"tags":357,"primary_topic":361,"secondary_topics":365,"classification":367,"search_phrases":379,"slug":382,"view_count":95,"doi":9,"paper":383,"created_at":391},5534,"DC-YOLO：应对遮挡与光照变化的湖羊行为检测模型","https:\u002F\u002Ffinance.sina.com.cn\u002Froll\u002F2026-10-19\u002Fdoc-inivumaf7730137.shtml","中国农业大学团队针对集约化养殖中多目标严重遮挡、光照多变与类别不均问题，引入自适应细节—上下文注意力机制构建模块，并采用边界框相似度软抑制防止误删遮挡目标，预训练光照编码器迁移参数应对光照变化。数据集来自湖羊养殖场全天候监控，含505张标注图像、5类行为。","智慧农业（中英文）2026-10-19","2026-10-19T00:00:00Z",75,{"impact":17,"substance":352,"depth":19,"authority":353,"freshness":105,"relevant":21,"comment":354},21,13,"论文提出面向湖羊行为检测的DC-YOLO模型，方法有新意、数据来自真实养殖场，属智慧养殖细分领域实质进展，值得精选。",[356],{"name":348,"url":346},[26,27,358,359,360],"目标检测","湖羊","动物行为检测",{"code":218,"slug":362,"name":363,"path":364,"parent_code":35},"ruminants","草食牲畜","\u002Ftopic\u002Flivestock\u002Fruminants",[366],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":368},{"candidates":369,"agricultural_evidence":51},[370,374],{"code":218,"score":57,"supported":51,"title":371,"abstract":372,"tags":373},[359],[359],[359],{"code":38,"score":13,"supported":51,"title":375,"abstract":377,"tags":378},[376],"YOLO",[],[26,358],[380,381],"中国农业大学 湖羊 行为检测","DC-YOLO 遮挡 光照","中国农业大学湖羊行为检测-5534",{"doi":9,"openalex_id":9,"authors":384,"venue":9,"cited_by_count":95,"oa_url":9,"card":385,"direction":100,"ingested_from":390},[],{"tldr":386,"method":387,"finding":388,"direction":100,"opportunity":389},"提出DC-YOLO模型，用于湖羊行为检测，解决遮挡与光照变化问题。","自适应细节-上下文注意力、边界框相似度软抑制、光照编码器迁移，505张标注图像。","模型在遮挡和光照变化下有效检测湖羊行为，减少误删。","可探索多模态融合与轻量化部署，提升复杂养殖场景下的实时行为监测能力。","agent","2026-10-22T00:07:09.998247Z",{"id":393,"title":394,"url":395,"summary":396,"summary_zh":9,"content":9,"source_name":397,"source_url":395,"published_at":398,"category":12,"cover_url":9,"hotness":399,"is_selected":14,"score":400,"score_detail":401,"sources":404,"tags":408,"primary_topic":412,"secondary_topics":413,"classification":415,"search_phrases":442,"slug":445,"view_count":237,"doi":446,"paper":447,"created_at":468},2780,"基于深度学习数据增强技术的肉牛行为识别 与养殖状态评估研究","https:\u002F\u002Fdoi.org\u002F10.65436\u002Fhssj.v1i9.50","摘 要：肉牛行为的准确识别是智慧养殖中个体状态监测和精细化管理的重要基础。针对实际养殖场景中光照变化、行为姿态差异以及训练样本规模对识别性能影响不明确等问题，本文以9类肉牛典型行为图像为研究对象，构建基于深度学习骨干网络与组合数据增强的行为识别流程。数据集包含饮水、进食、争斗、舔舐、躺卧、爬跨、探究、站立和行走9类行为，覆盖低光、正常光照、高光和黑暗4种光照条件，共4500张图像。首先，在统一训练条件下比较ResNet-50、DenseNet-121、EfficientNet-B0和Swin-T四种骨干网络。实验结果表明，EfficientNet-B0的测试准确率为98.37%±1.36%，参数量为4.02 M，MACs为0.41 G；其准确率较ResNet-50高0.07个百分点，较DenseNet-121和Swin-T均高0.59个百分点，同时具有四种网络中最低的参数量与计算量，因此选其作为后续实验的固定骨干。进一步设置不同训练样本规模实验与数据增强消融实验，以分析样本量和翻转、颜色抖动、旋转、随机擦除等增强操作的影响。实验二结果表明，当每类训练样本由每类10张增至全量训练集（每类400张）时，测试准确率由69.70%±0.76%提升至98.37%±1.36%，训练样本规模对识别性能影响显著，且随样本量增大边际收益总体呈递减趋势。数据增强消融实验表明，逐项去除翻转、颜色抖动、旋转和随机擦除后，测试准确率较完整增强基线（98.37%±1.36%）分别下降2.74、3.11、2.89和2.96个百分点，验证了各增强操作对复杂光照与姿态条件下识别性能的贡献，其中颜色抖动的作用最为显著。研究可为复杂光照条件下肉牛行为的自动识别与智能养殖监测提供参考。 基金项目：安徽省教育厅优秀青年教师培育项目（YQYB2026117）；安徽省智慧农业技术与装备重点实验室开放基金（AEC2026016；AEC2025009）；安徽省教育厅自然科学研究项目（重大）（2024AH040217）；省级质量工程-教学研究项目（2023jyxm1009；2023xjzlts117；2023sdxx145）;基于人工智能下的家禽康养与疾病预警技术研究（S202413620055）；基于自监督学习与对抗增强的小样本信号的智能感知研究（2025SK019）；基于深度学习的生猪识别与康养研究（S202513620083）","人文与社会研究学报","2026-09-17T00:00:00Z",25,78,{"impact":402,"substance":182,"depth":17,"authority":57,"freshness":13,"relevant":21,"comment":403},16,"论文以4500张多光照肉牛行为图像系统比较四种骨干网络并完成样本规模与数据增强消融实验，方法扎实、结论可靠，对复杂光照下智能养殖监测有直接参考价值，值得进入每日精选。",[405,406],{"name":397,"url":395},{"name":397,"url":407},"https:\u002F\u002Fdoi.org\u002F10.65436\u002Fhssj.v1i9.48",[26,409,27,410,411],"深度学习","数据增强","肉牛行为识别",{"code":218,"slug":362,"name":363,"path":364,"parent_code":35},[414],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":416},{"candidates":417,"agricultural_evidence":51},[418,422,428,434,438],{"code":38,"score":353,"supported":51,"title":419,"abstract":420,"tags":421},[409],[409],[26,409],{"code":218,"score":423,"supported":51,"title":424,"abstract":426,"tags":427},11,[425],"肉牛",[425],[],{"code":429,"score":63,"supported":51,"title":430,"abstract":431,"tags":433},"C1",[],[432],"生猪",[],{"code":207,"score":63,"supported":51,"title":435,"abstract":436,"tags":437},[],[210],[],{"code":147,"score":63,"supported":51,"title":439,"abstract":440,"tags":441},[],[122],[],[443,444],"农业人工智能 肉牛行为识别 数据增强 智慧养殖","农业人工智能 肉牛行为识别","农业人工智能肉牛行为识别数据增强智慧养殖-2780","10.65436\u002Fhssj.v1i9.50",{"doi":446,"openalex_id":448,"authors":449,"venue":397,"cited_by_count":95,"oa_url":395,"card":463,"direction":100,"ingested_from":102},"W7213445826",[450,452,454,456,458,460],{"name":451,"orcid":9},"孙帅",{"name":453,"orcid":9},"赵永才",{"name":455,"orcid":9},"李慢",{"name":457,"orcid":9},"郜静茹",{"name":459,"orcid":9},"关曼玉",{"name":461,"orcid":462},"Yanbo Li","https:\u002F\u002Forcid.org\u002F0000-0001-5144-2309",{"tldr":464,"method":465,"finding":466,"direction":100,"opportunity":467},"比较四种骨干网络并做数据增强消融，实现9类肉牛行为识别与养殖状态评估。","4500张9类行为图像，ResNet-50、DenseNet-121、Effic","EfficientNet-B0最优（98.37%，4.02M参数）；样本量影响显著，颜色抖动贡献最大","可探索轻量模型在边缘设备实时部署及跨牧场域适应，并引入时序视频行为识别。","2026-09-17T23:30:22.897005Z",{"id":470,"title":471,"url":472,"summary":473,"summary_zh":9,"content":474,"source_name":475,"source_url":9,"published_at":476,"category":477,"cover_url":9,"hotness":13,"is_selected":14,"score":478,"score_detail":479,"sources":481,"tags":483,"primary_topic":486,"secondary_topics":487,"classification":488,"search_phrases":505,"slug":508,"view_count":183,"doi":9,"paper":9,"created_at":509},126,"AI+农业如何从云上落到地里——从\"会养\"\"会种\"到\"慧养\"\"慧种\",2025年农业人工智能Token年度消耗超2.4亿","https:\u002F\u002Ffinance.sina.com.cn\u002Fjjxw\u002F2026-07-27\u002Fdoc-inikekzt3337234.shtml","新华社报道:人工智能正深度融入农田,从温室喷雾机器人、牛脸识别、北大荒多光谱无人机AI查苗到河北卢龙78座高标准智能温室蓝莓基地,各地探索\"慧养\"\"慧种\"。2025年中国智慧农业市场规模从2017年384.74亿元增至1200亿元,年复合增长率15.28%。但产业仍面临三重短板:一是初始投入大(智慧大棚每平方米300-1500元,种植集装箱20-30万元);二是农村主力为中老年群体,数字化操作能力不足、青年人才短缺;三是山区丘陵复杂地形数据与算法迁移困难,许多AI应用仍停留在监测识别预警阶段。寿光\"AI机器人银发专家\"将40年寿光模式经验提炼为数智化内核,技术服务效率提升5倍以上,业内认为\"让技术找人\"比\"让人学技术\"更易实现。","内蒙古自治区和林格尔县的蒙牛嘉立荷生态牧场，和江苏连云港的东旺奶牛养殖基地，正运行着同一套“牛脸识别”系统。无需近距离拍摄，后台屏幕动态框出牛脸，饮食、健康、行为数据一目了然。\n\n“这不是保险理赔用的识别工具，而是智慧养殖工具。”系统研发方寿光市翔天农业科技有限公司副总经理刘守城说。每头牛都有“数字身份证”，全天候“点名”，可实现精确投喂。养殖数据直传农业、防疫部门，食品安全可追溯。试点以来，已覆盖超7000头牛，饲料利用率提升25%，发病率降低20%。","新华社\u002F兵团日报 2026-07-27","2026-07-27T00:00:00Z","报道",60,{"impact":17,"substance":402,"depth":57,"authority":57,"freshness":237,"relevant":21,"comment":480},"报道了AI在奶牛养殖中的实际应用，有具体数据和案例，但时效性较差，且为地方性进展。",[482],{"name":475,"url":472},[122,484,26,27,485],"智慧大棚","寿光模式",{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},[],{"status":44,"locked":14,"version":45,"method":46,"evidence":489},{"candidates":490,"agricultural_evidence":51},[491,495,501],{"code":38,"score":183,"supported":51,"title":492,"abstract":493,"tags":494},[26],[],[26],{"code":496,"score":72,"supported":51,"title":497,"abstract":498,"tags":500},"B7",[],[499],"温室",[484],{"code":147,"score":72,"supported":51,"title":502,"abstract":503,"tags":504},[],[122],[122],[506,507],"农业人工智能 寿光模式 智慧养殖 智慧农业","农业人工智能 寿光模式","农业人工智能寿光模式智慧养殖智慧农业-126","2026-08-01T06:01:52.387430Z"]