[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-1969":3,"related-1969":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":35,"classification":36,"search_phrases":79,"slug":82,"view_count":83,"doi":84,"paper":85,"created_at":103},1969,"A lightweight domain-specific appearance embedding for Turkey re-identification in dense barn environments","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.atech.2026.102549","Individual-level monitoring of poultry in commercial barns requires identity-consistent tracking, which in turn depends on appearance features that can discriminate between visually homogeneous animals. Generic appearance models used in trackers such as DeepSORT are trained on human re-identification data and transfer poorly to livestock, where individuals lack the distinctive clothing and texture cues that drive pedestrian re-identification. In this work we present a lightweight domain-specific Siamese feature extractor for turkey re-identification, designed through a systematic, ablation-driven refinement process and trained with a combined batch-hard triplet and identity-classification objective. The final architecture combines pre-activation residual blocks, squeeze-and-excitation channel attention, and a BNNeck embedding head, and contains only 714K parameters — approximately 3.9 × fewer than the 2.8M-parameter mars-small128 model used by default in DeepSORT. On an open-set evaluation of 16 unseen turkey identities, the proposed embedding raises ROC AUC from 0.890 to 0.943, classification accuracy from 0.849 to 0.911, and the distribution separability index from 1.14 to 1.71, while reducing model storage by 3.8 × and inference latency relative to the baseline. A t-SNE projection of the learned space shows tight, well-separated clusters for the majority of identities, with residual overlap confined to the most visually similar individuals. When integrated into a DeepSORT tracking pipeline and evaluated on three commercial turkey-barn video sequences, the domain-specific embedding yields consistent gains in identity-related tracking metrics (IDF1 81.3 → 83.2%, association accuracy 68.8 → 69.9%). The results demonstrate that careful, domain-specific architectural design can substantially improve re-identification of visually homogeneous animals while simultaneously reducing computational cost. Within the scope of this controlled evaluation, the compact embedding is therefore well suited to resource-constrained edge hardware for continuous precision-livestock monitoring; large-scale field validation remains future work.","商业禽舍中对个体家禽的监测需要身份一致的跟踪，这依赖于能够区分视觉上同质动物的外观特征。DeepSORT等跟踪器中使用的通用外观模型基于行人重识别数据训练，难以有效迁移至牲畜场景，因为个体缺乏驱动行人重识别的独特服装和纹理线索。本研究提出了一种轻量级、面向特定领域的Siamese特征提取器，用于火鸡重识别，通过系统性的消融驱动优化流程设计，并采用批量硬三元组与身份分类联合目标进行训练。最终架构结合了预激活残差块、挤压激励通道注意力及BNNeck嵌入头，仅含71.4万参数——约为DeepSORT默认使用的280万参数mars-small128模型的3.9分之一。在包含16个未见火鸡身份的开放集评估中，所提出的嵌入将ROC AUC从0.890提升至0.943，分类准确率从0.849提升至0.911，分布可分性指数从1.14提升至1.71，同时模型存储量减少3.8倍，推理延迟相对基线降低。学习空间的t-SNE投影显示，大多数身份形成紧密且分离良好的簇，残余重叠仅限于视觉上最相似的个体。当集成至DeepSORT跟踪流程并在三段商业火鸡禽舍视频序列上评估时，该领域特定嵌入在身份相关跟踪指标上取得一致提升（IDF1从81.3%提升至83.2%，关联准确率从68.8%提升至69.9%）。结果表明，精细的领域特定架构设计能显著改善视觉同质动物的重识别性能，同时降低计算成本。在本受控评估范围内，该紧凑嵌入非常适合资源受限的边缘硬件，用于持续精准畜牧业监测；大规模现场验证仍为未来工作方向。",null,"Smart Agricultural Technology","2026-09-06T00:00:00Z","论文",10,false,74,{"impact":17,"substance":18,"depth":17,"authority":19,"freshness":20,"relevant":21,"comment":22},18,22,12,4,1,"针对火鸡重识别的轻量级专用模型，显著提升密集养殖环境下的个体追踪精度并降低算力需求，对精准畜牧有实质推进。",[24],{"name":10,"url":6},[26,27,28,29],"智慧农业","农业人工智能","边缘计算","畜禽识别",{"code":31,"slug":32,"name":33,"path":34,"parent_code":9},"C","livestock","畜牧兽医","\u002Ftopic\u002Flivestock",[],{"status":37,"locked":14,"version":38,"method":39,"evidence":40},"partial","2026-10-22.2","rules",{"candidates":41,"agricultural_evidence":44,"reason":78},[42,49,56,63,68,73],{"code":31,"score":43,"supported":44,"title":45,"abstract":46,"tags":48},6,true,[],[47,32],"畜牧",[],{"code":50,"score":43,"supported":44,"title":51,"abstract":52,"tags":55},"C3",[],[53,54],"家禽","poultry",[],{"code":57,"score":43,"supported":44,"title":58,"abstract":59,"tags":62},"C6",[],[60,61],"精准畜牧","livestock monitoring",[],{"code":64,"score":21,"supported":14,"title":65,"abstract":66,"tags":67},"I1",[],[],[26],{"code":69,"score":21,"supported":14,"title":70,"abstract":71,"tags":72},"I2",[],[],[27],{"code":74,"score":21,"supported":14,"title":75,"abstract":76,"tags":77},"I5",[],[],[28],"一级领域明确，二级方向需要细分",[80,81],"农业人工智能 智慧农业 畜禽识别 边缘计算","农业人工智能 智慧农业","农业人工智能智慧农业畜禽识别边缘计算-1969",2,"10.1016\u002Fj.atech.2026.102549",{"doi":84,"openalex_id":86,"authors":87,"venue":10,"cited_by_count":94,"oa_url":95,"card":96,"direction":100,"ingested_from":102},"W7210262200",[88,91],{"name":89,"orcid":90},"Debayan Sen","https:\u002F\u002Forcid.org\u002F0009-0009-0069-9548",{"name":92,"orcid":93},"Theo Lutz","https:\u002F\u002Forcid.org\u002F0000-0001-5405-044X",0,"https:\u002F\u002Fwww.sciencedirect.com\u002Fscience\u002Farticle\u002Fpii\u002FS2772375526007744\u002Fpdf",{"tldr":97,"method":98,"finding":99,"direction":100,"opportunity":101},"提出轻量级火鸡重识别模型，提升密集圈舍中个体追踪精度并降低计算成本。","基于Siamese网络，结合预激活残差、SE注意力、BNNeck，用三元组和分类","模型参数仅714K，AUC从0.890升至0.943，IDF1提升至83.2%，优于通用模型。","智慧农业 \u002F 农业物联网","可扩展至其他家禽或牲畜，验证大规模现场部署，并探索跨品种泛化能力。","openalex","2026-09-09T23:30:03.401167Z",{"total":43,"page":21,"page_size":43,"items":105},[106,155,210,274,325,406],{"id":107,"title":108,"url":109,"summary":110,"summary_zh":9,"content":111,"source_name":112,"source_url":9,"published_at":113,"category":114,"cover_url":9,"hotness":13,"is_selected":14,"score":115,"score_detail":116,"sources":120,"tags":122,"primary_topic":127,"secondary_topics":128,"classification":129,"search_phrases":150,"slug":153,"view_count":21,"doi":9,"paper":9,"created_at":154},3710,"牧医所第八届农科开放日：智启畜牧解锁美好生活的科技密码","https:\u002F\u002Fias.caas.cn\u002Fxwzx\u002Ftpxw\u002Fe199736e1b5d4ff785a6ed9ecb5cc266.htm","中国农业科学院北京畜牧兽医研究所9月19日举办第八届农科开放日活动。围绕智启畜牧、享美好生活主题，主会场集中展示人工智能与大数据在畜牧领域的创新应用，演示畜牧通用机器人底盘、气溶胶病原检测机器人等智能设备。活动共吸引1800余人次到展台参加。","9月19日，中国农业科学院第八届农科开放日成功举办。中国农业科学院北京畜牧兽医研究所在中关村院区主会场和所区分会场同步举办活动，围绕“智启畜牧 享美好生活”主题，开启一场智慧畜牧科普盛宴，带领公众零距离接触、体验畜牧前沿科研成果。\n\n主会场集中展示人工智能与大数据在畜牧领域的创新应用成果，介绍国家畜禽种质资源库在智能计算、样本保藏、开放共享等方面的开创性突破。现场演示了畜牧通用机器人底盘、气溶胶病原检测机器人等智能设备作业场景，展现牧医所在现代智慧畜牧业建设、畜禽疫病科学防控等方向的最新研究成果，让公众直观感受“人工智能+”赋能畜牧产业的创新活力与发展潜力。\n\n分会场系统呈现优质畜禽品种培育、高效绿色养殖、畜禽疫病科学防控、饲草栽培利用、畜产品质量安全等各领域最新研究进展。现场设置趣味问答、互动体验项目，吸引青少年参与，激发大家对畜牧科学的探索兴趣。现场展出白羽肉鸡、白羽肉鸭等一批攻克畜禽种源“卡脖子”难题的新品种与新技术，直观感受畜禽种业自主创新的科技实力。大家还能手动操作显微镜等各种专业科研仪器，品鉴红三叶草牛奶、功能鸡蛋等特色畜产品，读懂其背后的科技原理，树立科学膳食理念。同时，围绕畜禽健康养殖，现场展示单胃动物仿生消化系统等科研装备以及优质苜蓿新品种等。\n\n此次活动共吸引1800余人次到牧医所展台参加，公众在互动体验、食品品鉴中，深入了解畜牧兽医科研人员守护百姓舌尖安全、赋能现代畜牧业高质量发展的使命担当，激发了全社会对畜牧科技的关注与参与热情，为推动畜牧科技知识普及、凝聚种业创新发展共识搭建了良好的沟通桥梁。\n\n下一步，牧医所将持续举办这类面向公众的科普开放活动，打通农业科研成果从实验室到公众认知的“最后一公里”，让更多人了解现代畜牧科技，助力畜牧科技成果更好地服务百姓美好生活。","中国农科院北京畜牧兽医研究所","2026-09-19T12:00:00Z","报道",61,{"impact":117,"substance":118,"depth":19,"authority":117,"freshness":43,"relevant":21,"comment":119},14,15,"国家级科研机构举办的智慧畜牧科普开放日，展示AI+畜牧与种业自主创新成果，有实质内容但属活动报道，时效性一般。",[121],{"name":112,"url":109},[27,123,124,125,126],"种业振兴","农业科普","智慧畜牧","畜牧机器人",{"code":31,"slug":32,"name":33,"path":34,"parent_code":9},[],{"status":37,"locked":14,"version":38,"method":39,"evidence":130},{"candidates":131,"agricultural_evidence":44},[132,137,141,146],{"code":31,"score":133,"supported":44,"title":134,"abstract":135,"tags":136},11,[47],[47],[],{"code":57,"score":21,"supported":14,"title":138,"abstract":139,"tags":140},[],[],[125],{"code":142,"score":21,"supported":14,"title":143,"abstract":144,"tags":145},"F1",[],[],[123],{"code":69,"score":21,"supported":14,"title":147,"abstract":148,"tags":149},[],[],[27],[151,152],"中国农科院 牧医所 农科开放日","畜牧通用机器人 气溶胶病原检测机器人","中国农科院牧医所农科开放日-3710","2026-09-29T00:08:22.273274Z",{"id":156,"title":157,"url":158,"summary":159,"summary_zh":9,"content":160,"source_name":161,"source_url":9,"published_at":162,"category":163,"cover_url":9,"hotness":13,"is_selected":14,"score":164,"score_detail":165,"sources":170,"tags":172,"primary_topic":177,"secondary_topics":178,"classification":179,"search_phrases":205,"slug":208,"view_count":21,"doi":9,"paper":9,"created_at":209},519,"农业农村部答复人大建议:持续推进智慧农业建设,加大农牧业科技投入","https:\u002F\u002Fh.mffb.com.cn\u002Fa\u002F568059.html","农业农村部答复关于培育农牧业新质生产力的建议时表示,将持续推进智慧农业建设,印发关于大力发展智慧农业的指导意见、全国智慧农业行动计划(2024—2028年),成立部智慧农业专家咨询委员会,建设国家智慧农业畜牧业(生猪)创新分中心,加大农牧业科技投入。十四五以来已支持国家智慧畜牧业创新应用项目,示范带动农牧业智慧化建设。","山东京琪农业科技有限公司成立于2018年，总部位于山东潍坊。作为一家高效农业产业园区规划、建设、运营一体化服务商，主营葡萄产业。我们集生态有机农业、现代高效设施农业、智慧农业、订单农业于一体，是国家级高新技术企业。\n\n我们秉持“科技兴农、生态惠民、产业报国”的核心理念，构建了“产、学、研、用”一体化创新体系，致力于推动农业科技的发展与应用。\n\n公司在山东、云南、甘肃、新疆等地区布局了2000- 3000亩高效特色农业产业示范区，形成了“生态修复- 品种改良- 智慧种植- 订单销售-品牌建设”的全产业链模式，有效促进了农业的可持续高质量发展。\n\n京琪农业通过规划、建设、运营标准化产业园区，制定标准化种植方案及技术培训计划、订单农业等措施，辐射带动周边区域产业升级。采用 “核心示范区 - 卫星基地 - 散户”“公司 + 基地 + 农户” 双模式，以 “新建一批、改建一批、带动一批” 策略快速形成产业辐射圈；预计可创造 2000-3000个就业岗位，优先录用退役军人与返乡青年；配套建设 “新农人创客空间”，提供创业孵化服务，培养新农人；助农转型，以京琪模式助力乡村振兴，实现农业兴、农村美、农民富。\n\n本文来自网友投稿或网络内容，如有侵犯您的权益请联系我们删除，联系邮箱：wyl860211@qq.com 。","中国农机化导报","2026-08-14T23:57:35Z","政策",17,{"impact":166,"substance":94,"depth":94,"authority":167,"freshness":168,"relevant":21,"comment":169},5,3,9,"标题为政策答复，但正文实为企业宣传稿，内容空洞，无实质信息，信源不明。",[171],{"name":161,"url":158},[26,173,174,175,176],"新质生产力","农业农村部","畜牧业","农牧业科技",{"code":31,"slug":32,"name":33,"path":34,"parent_code":9},[],{"status":37,"locked":14,"version":38,"method":39,"evidence":180},{"candidates":181,"agricultural_evidence":44,"reason":78},[182,186,190,196,200],{"code":64,"score":19,"supported":44,"title":183,"abstract":184,"tags":185},[26],[26],[26],{"code":31,"score":20,"supported":44,"title":187,"abstract":188,"tags":189},[],[47],[175],{"code":191,"score":167,"supported":44,"title":192,"abstract":193,"tags":195},"C1",[],[194],"生猪",[],{"code":57,"score":167,"supported":44,"title":197,"abstract":198,"tags":199},[],[125],[],{"code":201,"score":21,"supported":14,"title":202,"abstract":203,"tags":204},"J2",[],[],[173],[206,207],"农业农村部 农牧业科技 新质生产力 智慧农业","农业农村部 农牧业科技","农业农村部农牧业科技新质生产力智慧农业-519","2026-08-15T00:02:52.815760Z",{"id":211,"title":212,"url":213,"summary":214,"summary_zh":9,"content":215,"source_name":216,"source_url":9,"published_at":217,"category":163,"cover_url":9,"hotness":13,"is_selected":44,"score":218,"score_detail":219,"sources":223,"tags":225,"primary_topic":229,"secondary_topics":230,"classification":231,"search_phrases":268,"slug":271,"view_count":272,"doi":9,"paper":9,"created_at":273},226,"农业农村部答复第2049号建议——加强农牧业新质生产力培育,推进智慧农业和农业品牌建设","https:\u002F\u002Fwww.moa.gov.cn\u002Fgovpublic\u002FSCYJJXXS\u002F202608\u002Ft20260804_6486456.htm","农业农村部答复十四届全国人大四次会议第2049号建议(王银香代表提出的关于培育农牧业新质生产力的建议),经商财政部,围绕农业品牌建设、农牧业科技投入、产业人才支撑、市场需求拓展四方面部署:印发《农业品牌精品培育计划(2022—2025年)》,将科尔沁牛、宁乡花猪等纳入区域公用品牌;推广中农科·龙腾、家禽产业数智化平台等国产饲料配方软件;印发《农业农村部关于大力发展智慧农业的指导意见》《全国智慧农业行动计划(2024—2028年)》,建立部智慧农业专家咨询委员会;联合财政部启动乡村产业振兴带头人培育头雁项目;印发《促进农产品消费实施方案》9方面23条举措;推进互联网+农产品出村进城工程,启动星乡村、星农人培育。","农业农村部会同有关部门，加强工作统筹，推动产销衔接，丰富消费场景，有力有效促进农产品消费。一是健全工作机制。会同国家发展改革委等部门印发《促进农产品消费实施方案》，提出9方面23条具体举措，从优化供给端、创新流通端、激活市场端共同发力，释放多样化、品质化、差异化消费潜力，引领供需结构升级。制定实施方案分工安排，加强部门协作、深化部省联动、动员社会参与，构建多方协同、上下贯通的促进农产品消费工作格局。二是搭建产销平台。举办中国国际农产品交易会、中国农民丰收节金秋消费季等节庆展会，带动各地开展丰富多彩的消费促进活动。推进“互联网＋”农产品出村进城工程，启动“星乡村”、“星农人”培育，拓宽农产品线上销售渠道。三是拓展消费空间。推进农业与文化、旅游、农遗等深度融合，加快发展农事体验、科普研学等新业态，丰富农产品消费场景。推动农文旅深度融合，举办美丽乡村休闲旅游行推介活动，带动特色农产品地产地销。四是加大产品创新力度。持续优化畜禽养殖屠宰布局，逐步实现就地就近屠宰，引导屠宰企业开展精细分割、精深加工，开发分割肉、调味肉、熟食制品等高附加值产品。","农业农村部 2026-08-04","2026-08-04T00:00:00Z",84,{"impact":220,"substance":221,"depth":118,"authority":118,"freshness":168,"relevant":21,"comment":222},25,20,"农业农村部官方答复，涉及智慧农业和农产品消费促进，政策层级高，内容具体，时效性好。",[224],{"name":216,"url":213},[26,173,174,226,227,228],"农业品牌","头雁项目","答复建议",{"code":31,"slug":32,"name":33,"path":34,"parent_code":9},[],{"status":37,"locked":14,"version":38,"method":39,"evidence":232},{"candidates":233,"agricultural_evidence":44,"reason":78},[234,238,242,248,254,259,264],{"code":64,"score":19,"supported":44,"title":235,"abstract":236,"tags":237},[26],[26],[26],{"code":50,"score":167,"supported":44,"title":239,"abstract":240,"tags":241},[],[53],[],{"code":243,"score":167,"supported":44,"title":244,"abstract":245,"tags":247},"C4",[],[246],"饲料",[],{"code":249,"score":167,"supported":44,"title":250,"abstract":251,"tags":253},"G4",[],[252],"乡村产业",[],{"code":255,"score":21,"supported":14,"title":256,"abstract":257,"tags":258},"E5",[],[],[226],{"code":260,"score":21,"supported":14,"title":261,"abstract":262,"tags":263},"G1",[],[],[227],{"code":201,"score":21,"supported":14,"title":265,"abstract":266,"tags":267},[],[],[173],[269,270],"农业农村部 新质生产力 农业品牌 头雁项目","农业农村部 新质生产力","农业农村部新质生产力农业品牌头雁项目-226",29,"2026-08-05T23:52:59.794994Z",{"id":275,"title":276,"url":277,"summary":278,"summary_zh":279,"content":9,"source_name":280,"source_url":277,"published_at":281,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":282,"score_detail":283,"sources":287,"tags":289,"primary_topic":294,"secondary_topics":295,"classification":296,"search_phrases":303,"slug":306,"view_count":94,"doi":307,"paper":308,"created_at":324},5544,"Sustainable service scenes: formation mechanism of consumers’ premium purchase of specialty agricultural and livestock products in short-video live streaming","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffsufs.2026.1993041","Advancing the market realization of premium pricing for high-quality agricultural and livestock products is essential to facilitating the transition of traditional agriculture toward a sustainable, resource-efficient, and quality-driven development paradigm. However, Information asymmetry in the agricultural and livestock products market gives rise to the “lemons problem,” impeding the sustainable consumption of high-quality, differentiated products and undermining their ability to command premium pricing. With the development of the digital economy, short-video live streaming has emerged as a new driver for promoting the sustainable consumption of such products at premium prices. Drawing on servicescape theory, this study uses Inner Mongolia mutton as a representative case and constructs a structural equation model based on 402 valid questionnaires to examine the formation mechanism of consumers’ premium purchase intentions for specialty agricultural and livestock products in short-video live streaming. In addition, multi-group analysis is conducted to examine whether these mechanisms differ across consumers with different demographic characteristics. The results indicate that short-video live streaming effectively encourages consumers to purchase specialty agricultural and livestock products at premium prices through the dual pathways of “scene reconstruction–value upgrading” and “scene reconstruction–trust establishment.” Further, multi-group analysis reveals significant differences in consumers’ psychological responses and purchase intentions across demographic groups. This study provides a theoretical basis and practical insights for promoting the sustainable consumption of specialty agricultural and livestock products at premium prices, and thereby contribute to the long-term sustainability of the agricultural sector.","推进优质农产品和畜产品优质优价的市场实现，对于促进传统农业向可持续、资源节约型和品质驱动型发展范式转型至关重要。然而，农产品和畜产品市场中的信息不对称引发了“柠檬问题”，阻碍了优质差异化产品的可持续消费，并削弱了其实现优质优价的能力。随着数字经济的发展，短视频直播已成为促进此类产品优质优价可持续消费的新动力。本研究基于服务场景理论，以内蒙古羊肉为代表性案例，基于402份有效问卷构建结构方程模型，考察短视频直播中消费者对特色农产品和畜产品溢价购买意愿的形成机制。此外，通过多群组分析检验这些机制在不同人口统计特征消费者之间是否存在差异。结果表明，短视频直播通过“场景重构—价值升级”和“场景重构—信任建立”的双重路径，有效促进消费者以溢价购买特色农产品和畜产品。进一步的多群组分析揭示，不同人口统计群体消费者在心理反应和购买意愿方面存在显著差异。本研究为促进特色农产品和畜产品优质优价的可持续消费提供了理论基础和实践启示，进而有助于农业部门的长期可持续发展。","Frontiers in Sustainable Food Systems","2026-10-22T00:00:00Z",71,{"impact":19,"substance":221,"depth":284,"authority":285,"freshness":13,"relevant":21,"comment":286},16,13,"基于402份问卷的结构方程模型实证，揭示短视频直播场景重构驱动特色农产品溢价消费的双路径机制，对农产品电商与品牌溢价有参考价值，但属单案例学术研究，产业影响有限。",[288],{"name":280,"url":277},[175,290,291,292,293],"特色农产品","短视频直播","溢价购买","服务场景",{"code":31,"slug":32,"name":33,"path":34,"parent_code":9},[],{"status":37,"locked":14,"version":38,"method":39,"evidence":297},{"candidates":298,"agricultural_evidence":44},[299],{"code":31,"score":19,"supported":44,"title":300,"abstract":301,"tags":302},[32],[32],[175],[304,305],"内蒙古羊肉 短视频直播 溢价购买","特色农产品 短视频直播 服务场景 溢价购买","内蒙古羊肉短视频直播溢价购买-5544","10.3389\u002Ffsufs.2026.1993041",{"doi":307,"openalex_id":309,"authors":310,"venue":280,"cited_by_count":94,"oa_url":277,"card":318,"direction":322,"ingested_from":102},"W7223146436",[311,313,316],{"name":312,"orcid":9},"Pei Jie",{"name":314,"orcid":315},"Liangyuan Song","https:\u002F\u002Forcid.org\u002F0009-0001-0240-5269",{"name":317,"orcid":9},"Liu Hehe",{"tldr":319,"method":320,"finding":321,"direction":322,"opportunity":323},"基于服务场景理论，用内蒙古羊肉案例研究短视频直播中特色农产品溢价购买的形成机制。","服务场景理论+结构方程模型，402份问卷，多群组分析。","直播通过“场景重构-价值升级”和“场景重构-信任建立”双路径促进溢价购买，且存在人口统计差异。","数字乡村与农业信息化","可延伸至不同品类与平台对比，或将直播场景要素量化接入农产品溯源与信任机制研究。","2026-10-22T11:20:15.054936Z",{"id":326,"title":327,"url":328,"summary":329,"summary_zh":330,"content":9,"source_name":331,"source_url":328,"published_at":332,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":333,"score_detail":334,"sources":336,"tags":338,"primary_topic":9,"secondary_topics":341,"classification":342,"search_phrases":376,"slug":379,"view_count":94,"doi":380,"paper":381,"created_at":405},5402,"AI‐Enabled RGB Light‐to‐Frequency Sensor for Nondestructive Salinity Stress Monitoring in Medicinal Plants","https:\u002F\u002Fdoi.org\u002F10.1002\u002Faisy.70561","Salinity stress constrains medicinal plant productivity, particularly in coastal and salt affected agroecosystems where rapid, deployable diagnostics are essential. Here, we develop an AI‐enabled RGB light‐to‐frequency proximal sensing platform integrated with Tiny Machine Learning (TinyML) for nondestructive, real‐time salinity discrimination. Plants are exposed to three salinity levels (0, 100, and 200 mM NaCl). RGB‐derived and CIELAB chromatic descriptors are engineered, normalized, and partitioned (75:25) into training and test datasets. ReliefF‐based feature ranking and systematic subset optimization are combined with supervised learning using fivefold cross‐validation, and interpretability is achieved through SHAP analysis. Biomass reductions under saline treatments confirm physiological perturbations underlying spectral variability. Subspace KNN achieved the highest predictive performance (96.28% validation; 95.55% independent test accuracy). Framing model selection as a multiobjective optimization problem identified an optimal 10‐feature subset. Under this constraint, a Wide Neural Network attained 0.904 accuracy with an ultracompact 0.017 MB model size and >246 000 observations s −1 inference speed, demonstrating full TinyML compatibility. SHAP attribution consistently highlighted green intensity, blue channel metrics, and chromatic ratios as dominant predictors. This work establishes a lightweight, interpretable Edge‐AI framework for scalable, real‐time salinity diagnostics in precision agriculture.","盐胁迫制约药用植物的生产力，尤其是在沿海及受盐影响的农业生态系统中，亟需可快速部署的诊断手段。本研究开发了一种基于人工智能的RGB光-频率近端传感平台，并集成微型机器学习（TinyML），用于无损、实时的盐胁迫判别。植物暴露于三个盐浓度水平（0、100和200 mM NaCl）。研究构建了RGB衍生描述符与CIELAB色度描述符，经归一化后按75:25划分为训练集与测试集。将基于ReliefF的特征排序与系统性特征子集优化相结合，采用五折交叉验证进行监督学习，并通过SHAP分析实现模型可解释性。盐处理下的生物量下降证实了光谱变异性背后的生理扰动。子空间KNN取得了最高的预测性能（验证集准确率96.28%；独立测试集准确率95.55%）。将模型选择构建为多目标优化问题，确定了最优的10特征子集。在该约束下，宽神经网络（Wide Neural Network）达到0.904的准确率，模型体积仅0.017 MB，推理速度超过246 000次观测\u002F秒，展现出完全的TinyML兼容性。SHAP归因一致表明，绿色强度、蓝色通道指标及色度比是主要预测因子。本研究为精准农业中可扩展的实时盐胁迫诊断建立了一个轻量、可解释的边缘人工智能框架。","Advanced Intelligent Systems","2026-10-19T00:00:00Z",81,{"impact":17,"substance":18,"depth":17,"authority":117,"freshness":168,"relevant":21,"comment":335},"该研究提出一种轻量、可解释的边缘AI盐胁迫诊断框架，方法新颖、数据扎实，对精准农业具有参考价值，但属于实验室阶段成果，产业影响有限。",[337],{"name":331,"url":328},[26,27,28,339,340],"盐胁迫监测","药用植物",[],{"status":343,"locked":14,"version":38,"method":39,"evidence":344},"needs_review",{"candidates":345,"agricultural_evidence":44,"reason":375},[346,353,359,365,371],{"code":347,"score":348,"supported":44,"title":349,"abstract":350,"tags":352},"B6",7,[],[340,351],"medicinal plant",[340],{"code":64,"score":348,"supported":44,"title":354,"abstract":355,"tags":358},[],[356,357],"精准农业","precision agriculture",[26],{"code":69,"score":348,"supported":44,"title":360,"abstract":361,"tags":364},[],[362,363],"机器学习","machine learning",[27],{"code":366,"score":167,"supported":44,"title":367,"abstract":368,"tags":370},"H6",[],[369],"农业生态",[],{"code":74,"score":21,"supported":14,"title":372,"abstract":373,"tags":374},[],[],[28],"多个产业证据相当，需要确认主归属",[377,378],"RGB 光频传感器 盐胁迫","TinyML 药用植物 无损监测","RGB光频传感器盐胁迫-5402","10.1002\u002Faisy.70561",{"doi":380,"openalex_id":382,"authors":383,"venue":331,"cited_by_count":94,"oa_url":328,"card":399,"direction":404,"ingested_from":102},"W7222914402",[384,387,390,393,396],{"name":385,"orcid":386},"Ahmad Ali","https:\u002F\u002Forcid.org\u002F0000-0001-5530-7374",{"name":388,"orcid":389},"Vinie Lee Silva-Alvarado","https:\u002F\u002Forcid.org\u002F0009-0000-5857-3248",{"name":391,"orcid":392},"Arman Heydari","https:\u002F\u002Forcid.org\u002F0009-0002-4705-0729",{"name":394,"orcid":395},"Sandra Sendra","https:\u002F\u002Forcid.org\u002F0000-0001-9556-9088",{"name":397,"orcid":398},"Jaime Lloret","https:\u002F\u002Forcid.org\u002F0000-0002-0862-0533",{"tldr":400,"method":401,"finding":402,"direction":100,"opportunity":403},"开发AI驱动的RGB光频传感器，实现药用植物盐胁迫无损实时监测。","RGB与CIELAB色度特征、ReliefF特征选择、SHAP解释及TinyML","Subspace KNN验证准确率96.28%，10特征Wide NN模型仅0.017MB且推理超2","可探索多作物多胁迫通用色度特征库，及田间光照变化下的模型鲁棒性与长期部署验证。","农业人工智能与决策模型","2026-10-20T23:30:35.809539Z",{"id":407,"title":408,"url":409,"summary":410,"summary_zh":411,"content":9,"source_name":412,"source_url":409,"published_at":413,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":414,"score_detail":415,"sources":419,"tags":421,"primary_topic":424,"secondary_topics":430,"classification":431,"search_phrases":455,"slug":458,"view_count":94,"doi":459,"paper":460,"created_at":480},5401,"A HIERARCHICAL DISTRIBUTED EDGE AI FRAMEWORK FOR REAL-TIME APPLE LEAF DISEASE CLASSIFICATION","https:\u002F\u002Fdoi.org\u002F10.22190\u002Ffuacr260506002g","The application of artificial intelligence (AI) in agriculture has transformed crop management, particularly in the detection of plant diseases. Apple trees, a key agricultural commodity, are vulnerable to various diseases, which can severely impact crop yields. Traditional disease detection methods, often reliant on manual inspections, are time-consuming and prone to error. In response, this study proposes a novel two-stage edge AI framework for apple leaf disease classification that integrates RGB imagery with distributed edge computing. The first stage performs binary classification to distinguish between healthy and diseased leaves, achieving an F1 score of 95.50%. This optimization is achieved by utilizing lightweight models on edge devices, thereby enhancing computational efficiency. The second stage employs a consensus-based multiclass classification approach, achieving a 96.44% F1 score in identifying specific diseases. This dual-stage system, supported by an edge AI architecture, ensures real-time disease detection while minimizing resource consumption and enhancing scalability in large-scale agricultural environments. The full system achieved a 95.50% accuracy and F1 score on the special dataset. The results demonstrate the system’s efficacy in controlled laboratory conditions, offering a promising solution for precise, real-time agricultural monitoring. This study underscores the potential of distributed edge AI systems for scalable and efficient disease detection in precision agriculture.","人工智能（AI）在农业中的应用已深刻改变了作物管理方式，尤其是在植物病害检测方面。苹果树作为重要的农业经济作物，易受多种病害侵袭，严重影响作物产量。传统的病害检测方法通常依赖人工检查，耗时且易出错。为此，本研究提出了一种新颖的两阶段边缘AI框架，用于苹果叶片病害分类，该框架将RGB图像与分布式边缘计算相结合。第一阶段执行二分类以区分健康叶片与患病叶片，F1分数达到95.50%。该优化通过在边缘设备上采用轻量级模型实现，从而提升了计算效率。第二阶段采用基于共识的多类分类方法，在识别具体病害方面F1分数达到96.44%。该双阶段系统在边缘AI架构的支持下，实现了实时病害检测，同时最大限度地降低了资源消耗，并增强了在大规模农业环境中的可扩展性。完整系统在专用数据集上达到了95.50%的准确率和F1分数。结果表明，该系统在受控实验室条件下具有有效性，为精准、实时的农业监测提供了一种有前景的解决方案。本研究凸显了分布式边缘AI系统在精准农业中实现可扩展且高效病害检测的潜力。","Facta Universitatis Series Automatic Control and Robotics","2026-10-18T00:00:00Z",76,{"impact":17,"substance":416,"depth":164,"authority":19,"freshness":417,"relevant":21,"comment":418},21,8,"该研究提出两级边缘AI框架，在苹果叶片病害识别上取得95%以上F1值，方法新颖、数据可靠，对精准农业实时监测有参考价值，但尚处实验室验证阶段，产业影响有限。",[420],{"name":412,"url":409},[26,27,28,422,423],"作物病害识别","苹果病害",{"code":425,"slug":426,"name":427,"path":428,"parent_code":429},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit","B",[],{"status":432,"locked":14,"version":38,"method":39,"evidence":433},"classified",{"candidates":434,"agricultural_evidence":44},[435,441,445,450],{"code":425,"score":17,"supported":44,"title":436,"abstract":438,"tags":440},[437],"apple",[427,439,437],"苹果",[423],{"code":64,"score":348,"supported":44,"title":442,"abstract":443,"tags":444},[],[356,357],[26],{"code":74,"score":348,"supported":44,"title":446,"abstract":447,"tags":449},[],[28,448],"edge computing",[28],{"code":69,"score":166,"supported":44,"title":451,"abstract":452,"tags":454},[],[453],"artificial intelligence",[422,27],[456,457],"苹果叶片病害 边缘AI","分布式边缘计算 病害分类","苹果叶片病害边缘AI-5401","10.22190\u002Ffuacr260506002g",{"doi":459,"openalex_id":461,"authors":462,"venue":412,"cited_by_count":94,"oa_url":409,"card":475,"direction":404,"ingested_from":102},"W7222964752",[463,466,469,472],{"name":464,"orcid":465},"Milan Grujev","https:\u002F\u002Forcid.org\u002F0009-0002-3211-6844",{"name":467,"orcid":468},"Dragan H. Stojanovic","https:\u002F\u002Forcid.org\u002F0000-0003-4893-3814",{"name":470,"orcid":471},"Miloš Ilić","https:\u002F\u002Forcid.org\u002F0000-0002-9696-2874",{"name":473,"orcid":474},"Aleksandar Milosavljević","https:\u002F\u002Forcid.org\u002F0000-0003-3057-7727",{"tldr":476,"method":477,"finding":478,"direction":100,"opportunity":479},"提出两级边缘AI框架，用RGB图像实时分类苹果叶片病害。","分布式边缘计算+轻量模型，先二分类再共识多分类。","两级系统准确率与F1均达95.50%，多分类F1为96.44%。","仅在受控实验室验证，可延伸至田间复杂光照与多作物泛化及边缘能耗优化。","2026-10-20T23:30:33.830748Z"]