[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4156":3,"related-4156":83},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":8,"source_name":9,"source_url":8,"published_at":10,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":14,"score_detail":15,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":68,"slug":71,"view_count":53,"doi":8,"paper":72,"created_at":82},4156,"基于改进YOLOv8n的番茄果实检测模型","http:\u002F\u002Fwww.qikanvip.com\u002Fqkml\u002F174644.html","李慧琴、宋赵铭、肖亚涛、兰明明（河南农业大学学报2026年第02期；河南农业大学机电工程学院）。提出一种基于改进YOLOv8n的番茄果实检测模型，将CBAM注意力机制加入YOLOv8n模型的特征提取环节，引入BiFPN模块实现多尺度特征融合替换原PANet结构，结合损失函数S_I优化训练过程。结果：查准率P=95.3%、召回率R=92.1%、F1分数=93.7%、mAP@0.5=96.7%；检测速度最快1.5ms\u002F目标、最慢不超过19.6ms，可应用于番茄采摘机器人提升智能水平。",null,"河南农业大学学报2026年第02期","2026-10-01T00:00:00Z","论文",10,false,79,{"impact":16,"substance":17,"depth":18,"authority":19,"freshness":20,"relevant":21,"comment":22},16,22,18,14,9,1,"核心期刊论文，方法有改进且指标扎实，对采摘机器人视觉识别有实用价值，值得入选。",[24],{"name":9,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","目标检测","采摘机器人","番茄检测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[],{"status":39,"locked":13,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":46},[44,51,57,63],{"code":32,"score":45,"supported":46,"title":47,"abstract":49,"tags":50},11,true,[48],"番茄",[48],[],{"code":52,"score":53,"supported":46,"title":54,"abstract":55,"tags":56},"F6",4,[],[29],[29],{"code":58,"score":59,"supported":13,"title":60,"abstract":61,"tags":62},"I2",2,[],[],[27,28],{"code":64,"score":21,"supported":13,"title":65,"abstract":66,"tags":67},"I1",[],[],[26],[69,70],"河南农业大学 番茄 采摘机器人","改进YOLOv8n 番茄检测","河南农业大学番茄采摘机器人-4156",{"doi":8,"openalex_id":8,"authors":73,"venue":8,"cited_by_count":74,"oa_url":8,"card":75,"direction":79,"ingested_from":81},[],0,{"tldr":76,"method":77,"finding":78,"direction":79,"opportunity":80},"提出改进YOLOv8n番茄果实检测模型，提升采摘机器人识别精度与速度。","在YOLOv8n中引入CBAM注意力、BiFPN多尺度融合并优化损失函数S_I。","查准率95.3%、mAP@0.5达96.7%，单目标检测最快1.5ms。","农业人工智能与决策模型","可探索复杂光照与遮挡场景下的轻量化模型，并融合三维定位实现采摘决策闭环。","agent","2026-10-04T00:09:09.963710Z",{"total":84,"page":21,"page_size":84,"items":85},6,[86,158,219,290,343,399],{"id":87,"title":88,"url":89,"summary":90,"summary_zh":91,"content":8,"source_name":92,"source_url":89,"published_at":93,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":94,"score_detail":95,"sources":99,"tags":101,"primary_topic":103,"secondary_topics":104,"classification":105,"search_phrases":128,"slug":131,"view_count":59,"doi":132,"paper":133,"created_at":157},3356,"Simultaneous Maturity Recognition and Yield Counting of Truss and Individual Tomatoes Using Improved YOLOv8-EME and Optimized ByteTrack Tracker","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fhorticulturae12101199","Crop maturity detection and yield estimation are critical components of protected agriculture, supporting optimized harvest timing, fruit quality control, and coordination of production and marketing. Existing studies on detection and counting predominantly address a single category—either truss or individual fruits. To advance automation and intelligence in production management, this study proposes a tomato detection and counting system that integrates an improved YOLOv8-EME model with the ByteTrack algorithm, enabling simultaneous detection and counting of truss and individual fruits with maturity classification. The improved YOLOv8-EME model combines the EfficientNet architecture with the EffectiveSE attention mechanism, improving feature extraction and computational efficiency. In addition, the optimized network structure yields a lightweight design, reducing FLOPs to 6.9 G. The model attains a mean Average Precision (mAP) of 0.942, 0.883, 0.850, and 0.956 for the Ripe, Raw, Medium-Raw, and Truss categories, respectively. A proposed cross-line counting method integrated with an improved ByteTrack algorithm mitigates target loss, ID drift, and duplicate counting through ID drift association, trajectory fusion, historical trajectory cues, and a cooldown scheme. These designs significantly improve detection and counting accuracy for truss and fruit maturity, achieving a counting accuracy of 94%. The system offers efficient and accurate technical support for tomato detection and counting in smart agriculture.","作物成熟度检测与产量估测是设施农业的关键环节，可为优化采收时机、果实品质控制及产销协调提供支撑。现有检测与计数研究大多仅针对单一类别，即串收番茄或单个果实。为推动生产管理的自动化与智能化，本研究提出了一种融合改进YOLOv8-EME模型与ByteTrack算法的番茄检测与计数系统，可实现串收番茄与单个果实的同步检测与计数，并进行成熟度分类。改进后的YOLOv8-EME模型将EfficientNet架构与EffectiveSE注意力机制相结合，提升了特征提取能力与计算效率。此外，优化后的网络结构实现了轻量化设计，浮点运算次数（FLOPs）降至6.9 G。该模型在成熟、未成熟、半熟和串收四个类别上的平均精度均值（mAP）分别为0.942、0.883、0.850和0.956。所提出的跨线计数方法与改进的ByteTrack算法相结合，通过ID漂移关联、轨迹融合、历史轨迹线索和冷却机制，缓解了目标丢失、ID漂移和重复计数问题。这些设计显著提升了串收番茄和果实成熟度的检测与计数精度，计数准确率达到94%。该系统为智慧农业中的番茄检测与计数提供了高效、准确的技术支持。","Horticulturae","2026-09-23T00:00:00Z",77,{"impact":96,"substance":17,"depth":18,"authority":97,"freshness":20,"relevant":21,"comment":98},15,13,"该研究提出改进YOLOv8-EME与优化ByteTrack的番茄检测计数系统，可同时识别串收与单果成熟度并计数，方法新颖、数据详实，对智慧农业采摘自动化有实用价值。",[100],{"name":92,"url":89},[26,27,28,48,102],"产量估测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":106},{"candidates":107,"agricultural_evidence":46},[108,114,119,123],{"code":32,"score":109,"supported":46,"title":110,"abstract":111,"tags":113},7,[],[48,112],"tomato",[48],{"code":64,"score":109,"supported":46,"title":115,"abstract":116,"tags":118},[],[26,117],"smart agriculture",[26],{"code":58,"score":59,"supported":13,"title":120,"abstract":121,"tags":122},[],[],[27,28],{"code":124,"score":21,"supported":13,"title":125,"abstract":126,"tags":127},"I3",[],[],[102],[129,130],"YOLOv8 番茄 成熟度检测","番茄 串收 产量计数","YOLOv8番茄成熟度检测-3356","10.3390\u002Fhorticulturae12101199",{"doi":132,"openalex_id":134,"authors":135,"venue":92,"cited_by_count":74,"oa_url":89,"card":150,"direction":155,"ingested_from":156},"W7214123905",[136,138,141,143,145,147],{"name":137,"orcid":8},"Liying Shi",{"name":139,"orcid":140},"Sen Lin","https:\u002F\u002Forcid.org\u002F0000-0001-6521-3152",{"name":142,"orcid":8},"Haihang Zhao",{"name":144,"orcid":8},"Tianlong Sun",{"name":146,"orcid":8},"Dongdong Sun",{"name":148,"orcid":149},"Yuchen Yang","https:\u002F\u002Forcid.org\u002F0000-0001-5977-1617",{"tldr":151,"method":152,"finding":153,"direction":79,"opportunity":154},"提出改进YOLOv8-EME与ByteTrack结合的番茄检测计数系统，可同时识别串收与单果成熟度并","改进YOLOv8-EME（EfficientNet+EffectiveSE）结合","模型mAP达0.942\u002F0.883\u002F0.850\u002F0.956，计数准确率94%，FLOPs仅6.9G。","可探索多作物、多生长阶段通用模型，并融合边缘部署与产量预测决策。","智慧农业 \u002F 农业物联网","openalex","2026-09-24T23:30:10.615639Z",{"id":159,"title":160,"url":161,"summary":162,"summary_zh":8,"content":8,"source_name":163,"source_url":8,"published_at":164,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":165,"score_detail":166,"sources":168,"tags":170,"primary_topic":173,"secondary_topics":174,"classification":185,"search_phrases":206,"slug":209,"view_count":210,"doi":8,"paper":211,"created_at":218},3249,"设施番茄采摘机器人识别定位与采摘方法研究——江苏大学雷志龙等 基于改进YOLO v5-HSV融合算法识别准确率95.01%","http:\u002F\u002Fwww.qikanzj.com\u002Fhek\u002Fnyjxxb\u002Fmulu\u002F455758.html","智慧农业(中英文)期刊发表江苏大学雷志龙、刘畅、王权团队研究：针对设施单果番茄采摘需求，设计一款设施番茄智能采摘平台，主要由升降机构、采摘机构、识别与定位系统等部分组成。平台整体结构由低压一体化伺服滚珠丝杠副升降机构、六轴协作机械臂和力控末端执行器组成。基于改进YOLO v5-HSV融合算法来识别检测，通过对H分量进行图像阈值分割，提高对成熟目标果实识别的准确率，有效排除未成熟番茄和枝叶背景的干扰；通过眼在手外的标定方法，使用ZED双目相机进行定位。搭建的设施番茄采摘机样机平台在现场采摘试验中识别准确率达到95.01%，采摘成功率为87.96%，单果平均采摘时间为14.56s。","智慧农业(中英文)·江苏大学","2026-09-22T00:00:00Z",82,{"impact":18,"substance":17,"depth":18,"authority":19,"freshness":12,"relevant":21,"comment":167},"核心期刊论文，方法有改进、数据完整，识别准确率与采摘成功率等指标明确，对设施农业智能装备研发有参考价值。",[169],{"name":163,"url":161},[26,27,29,171,172],"机器视觉","设施番茄",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[175,180],{"code":58,"slug":176,"name":177,"path":178,"parent_code":179},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"code":52,"slug":181,"name":182,"path":183,"parent_code":184},"agricultural-robots","机器人与无人农场","\u002Ftopic\u002Finputs-equipment\u002Fagricultural-robots","F",{"status":39,"locked":13,"version":40,"method":41,"evidence":186},{"candidates":187,"agricultural_evidence":46},[188,193,198,202],{"code":58,"score":97,"supported":46,"title":189,"abstract":191,"tags":192},[190],"YOLO",[190],[27,171],{"code":32,"score":194,"supported":46,"title":195,"abstract":196,"tags":197},12,[48],[48],[172],{"code":52,"score":20,"supported":46,"title":199,"abstract":200,"tags":201},[29],[],[29],{"code":64,"score":53,"supported":46,"title":203,"abstract":204,"tags":205},[],[26],[26],[207,208],"江苏大学 设施番茄 采摘机器人","YOLO v5 番茄 识别定位","江苏大学设施番茄采摘机器人-3249",5,{"doi":8,"openalex_id":8,"authors":212,"venue":8,"cited_by_count":74,"oa_url":8,"card":213,"direction":79,"ingested_from":81},[],{"tldr":214,"method":215,"finding":216,"direction":79,"opportunity":217},"设计设施番茄智能采摘平台，融合改进YOLO v5与HSV实现识别定位与采摘。","改进YOLO v5-HSV融合算法、ZED双目相机眼在手外标定、六轴机械臂力控末","识别准确率95.01%，采摘成功率87.96%，单果平均采摘时间14.56秒。","可探索多果簇、遮挡与弱光环境下识别定位鲁棒性，并优化采摘效率与末端力控。","2026-09-23T00:04:33.401768Z",{"id":220,"title":221,"url":222,"summary":223,"summary_zh":224,"content":8,"source_name":225,"source_url":222,"published_at":226,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":227,"score_detail":228,"sources":231,"tags":233,"primary_topic":235,"secondary_topics":236,"classification":237,"search_phrases":256,"slug":259,"view_count":59,"doi":260,"paper":261,"created_at":289},2741,"A tomato maturity detection method against occlusion and variable illumination","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112423","A tomato maturity detection method against occlusion and variable illumination。Computers and Electronics in Agriculture","一种抗遮挡和可变光照的番茄成熟度检测方法","Computers and Electronics in Agriculture","2026-09-16T00:00:00Z",68,{"impact":194,"substance":18,"depth":16,"authority":19,"freshness":229,"relevant":21,"comment":230},8,"核心期刊论文，针对遮挡与光照变化下的番茄成熟度检测提出新方法，属农业人工智能细分领域实质进展，但应用范围有限，未达重大突破层级。",[232],{"name":225,"url":222},[26,27,28,48,234],"作物表型",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":238},{"candidates":239,"agricultural_evidence":46},[240,244,248,252],{"code":32,"score":96,"supported":46,"title":241,"abstract":242,"tags":243},[112],[48,112],[48],{"code":58,"score":59,"supported":13,"title":245,"abstract":246,"tags":247},[],[],[27,28],{"code":64,"score":21,"supported":13,"title":249,"abstract":250,"tags":251},[],[],[26],{"code":124,"score":21,"supported":13,"title":253,"abstract":254,"tags":255},[],[],[234],[257,258],"农业人工智能 作物表型 智慧农业 目标检测","农业人工智能 作物表型","农业人工智能作物表型智慧农业目标检测-2741","10.1016\u002Fj.compag.2026.112423",{"doi":260,"openalex_id":262,"authors":263,"venue":225,"cited_by_count":74,"oa_url":8,"card":284,"direction":79,"ingested_from":156},"W7213429689",[264,267,270,273,276,279,281],{"name":265,"orcid":266},"Hao Meng","https:\u002F\u002Forcid.org\u002F0000-0001-7511-2910",{"name":268,"orcid":269},"Wenzhe Li","https:\u002F\u002Forcid.org\u002F0009-0008-1630-4697",{"name":271,"orcid":272},"Di Wang","https:\u002F\u002Forcid.org\u002F0000-0002-3911-8159",{"name":274,"orcid":275},"Hui Zhao","https:\u002F\u002Forcid.org\u002F0009-0005-4192-5776",{"name":277,"orcid":278},"Ximing Li","https:\u002F\u002Forcid.org\u002F0000-0003-4022-1273",{"name":280,"orcid":8},"Dongdong Cui",{"name":282,"orcid":283},"Fernando Auat Cheein","https:\u002F\u002Forcid.org\u002F0000-0002-6347-7696",{"tldr":285,"method":286,"finding":287,"direction":79,"opportunity":288},"提出一种抗遮挡和光照变化的番茄成熟度检测方法。","基于深度学习的图像检测，针对遮挡与光照变化优化。","该方法在遮挡和变光照下仍能准确检测番茄成熟度。","可探索多模态融合与轻量化部署，提升田间复杂场景实时检测鲁棒性。","2026-09-17T23:30:01.491379Z",{"id":291,"title":292,"url":293,"summary":294,"summary_zh":8,"content":8,"source_name":295,"source_url":8,"published_at":296,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":297,"score_detail":298,"sources":300,"tags":302,"primary_topic":304,"secondary_topics":305,"classification":306,"search_phrases":331,"slug":334,"view_count":74,"doi":8,"paper":335,"created_at":342},2264,"南京农业大学等单位3MSP2多簇番茄序贯采摘规划在Computers and Electronics in Agriculture发表","https:\u002F\u002Fpubscholar.cn\u002Fheadlines\u002F1fe11dc4f9cf2a7db5fd265751febd525e0c4ea77d8edb8ce4d6232ff27da05120c65eab10d9c0dbda65b8d76671d51f","山东农业大学学者在Computers and Electronics in Agriculture发表3MSP2方法,结合\"眼在臂上\"和\"眼在手上\"双RGB-D相机视角,从簇级排序到单果姿态估计的完整决策链,实现温室大果型番茄\"低损伤高效率\"连续采收。","PubScholar 智慧设施种养研究专题","2026-09-08T16:00:00Z",80,{"impact":18,"substance":17,"depth":18,"authority":19,"freshness":229,"relevant":21,"comment":299},"双RGB-D视角簇级序贯采摘规划方法发表于农业工程核心期刊，方法新颖、决策链完整，对温室番茄自动化采收有实质参考价值。",[301],{"name":295,"url":293},[26,27,29,48,303],"设施园艺",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":13,"version":40,"method":41,"evidence":307},{"candidates":308,"agricultural_evidence":46},[309,313,319,323,327],{"code":32,"score":194,"supported":46,"title":310,"abstract":311,"tags":312},[48],[48],[48],{"code":314,"score":53,"supported":46,"title":315,"abstract":316,"tags":318},"B7",[],[317],"温室",[303],{"code":52,"score":21,"supported":13,"title":320,"abstract":321,"tags":322},[],[],[29],{"code":64,"score":21,"supported":13,"title":324,"abstract":325,"tags":326},[],[],[26],{"code":58,"score":21,"supported":13,"title":328,"abstract":329,"tags":330},[],[],[27],[332,333],"农业人工智能 采摘机器人 智慧农业 设施园艺","农业人工智能 采摘机器人","农业人工智能采摘机器人智慧农业设施园艺-2264",{"doi":8,"openalex_id":8,"authors":336,"venue":8,"cited_by_count":74,"oa_url":8,"card":337,"direction":79,"ingested_from":81},[],{"tldr":338,"method":339,"finding":340,"direction":79,"opportunity":341},"提出3MSP2方法，实现温室大果番茄从簇级排序到单果姿态估计的序贯采摘规划。","双RGB-D相机（眼在臂上+眼在手上）与簇级排序、单果姿态估计决策链。","该方法可实现温室大果型番茄低损伤、高效率的连续采收。","可探索多臂协同采摘与动态障碍物下的实时重规划，提升复杂温室环境适应性。","2026-09-13T00:04:03.523312Z",{"id":344,"title":345,"url":346,"summary":347,"summary_zh":348,"content":8,"source_name":349,"source_url":346,"published_at":350,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":351,"score_detail":352,"sources":354,"tags":356,"primary_topic":360,"secondary_topics":361,"classification":363,"search_phrases":379,"slug":382,"view_count":74,"doi":383,"paper":384,"created_at":398},5387,"LIGHTWEIGHT FEATURE FUSED ATTENTION DRIVEN MULTI LEVEL HYBRID MOBILENET V2 FRAMEWORK FOR EARLY TOMATO LEAF DISEASE DETECTION","https:\u002F\u002Fdoi.org\u002F10.62441\u002Factainnovations.vi.1918","It is crucial to find and treat tomato crop diseases early and accurately to improve crop efficiency and make sure there is no scarcity of crop. However, computerized analysis is provocative due to lighting differences, compound backgrounds, and graphic likenesses among infection regions. Research work proposed a lightweight Attention Driven Multi Level Hybrid MobileNet-V2 algorithm that fuses the handcrafted texture structures with Deep Learning (DL) features, then image preprocessing is incorporated using Gaussian, Bilateral, and Guided filters to minimize noise by preserving the disease lesions. LAB color model along with Contrast Limited Adaptive Histogram Equalization (CLAHE) are used to improve the contrast. Otsu thresholding is involved to effectively separate the leaf segment from diseased parts. Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) descriptors are used to obtain fine-grained features, while high level features are gained by pretrained MobileNet-V2 model. Features fusion is fed to the fully connected layers of deep learning model for training and validation purpose. Results have revealed that the suggested model attains better classification performance as compared to existing models, making it an effective explanation for real time tomato leaf disease detection for smart agriculture applications.","早期准确发现并治疗番茄作物病害，对于提高作物效率、确保作物不短缺至关重要。然而，由于光照差异、复杂背景以及感染区域之间的图形相似性，计算机化分析具有挑战性。研究提出了一种轻量级注意力驱动多层混合MobileNet-V2算法，该算法将手工纹理结构与深度学习（DL）特征相融合，然后结合高斯、双边和引导滤波器进行图像预处理，以在保留病害病变的同时最小化噪声。采用LAB颜色模型和对比度受限自适应直方图均衡化（CLAHE）来提高对比度。引入Otsu阈值分割以有效分离叶片片段与病害部分。使用局部二值模式（LBP）和灰度共生矩阵（GLCM）描述符获取细粒度特征，同时通过预训练的MobileNet-V2模型获取高层特征。特征融合后输入深度学习模型的全连接层进行训练和验证。结果表明，与现有模型相比，所提出的模型取得了更好的分类性能，使其成为智慧农业应用中实时番茄叶片病害检测的有效解决方案。","Acta Innovations","2026-10-18T00:00:00Z",64,{"impact":194,"substance":18,"depth":16,"authority":12,"freshness":229,"relevant":21,"comment":353},"提出融合手工纹理特征与MobileNet-V2的轻量番茄叶病检测方法，有一定方法新颖性，但属单篇论文、应用范围有限，未达每日精选门槛。",[355],{"name":349,"url":346},[26,27,357,358,359],"深度学习","番茄病害","图像识别",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[362],{"code":58,"slug":176,"name":177,"path":178,"parent_code":179},{"status":39,"locked":13,"version":40,"method":41,"evidence":364},{"candidates":365,"agricultural_evidence":46},[366,370,375],{"code":32,"score":96,"supported":46,"title":367,"abstract":368,"tags":369},[112],[48,112],[358],{"code":58,"score":20,"supported":46,"title":371,"abstract":372,"tags":374},[],[357,373],"deep learning",[27,359,357],{"code":64,"score":109,"supported":46,"title":376,"abstract":377,"tags":378},[],[26,117],[26],[380,381],"MobileNet-V2 番茄叶片病害","番茄叶病 深度学习 检测","MobileNet-V2番茄叶片病害-5387","10.62441\u002Factainnovations.vi.1918",{"doi":383,"openalex_id":385,"authors":386,"venue":349,"cited_by_count":74,"oa_url":392,"card":393,"direction":155,"ingested_from":156},"W7222977034",[387,389],{"name":388,"orcid":8},"Mrs. Vijetalaxmi A Hegde",{"name":390,"orcid":391},"Abhay Ramakant Kasetwar","https:\u002F\u002Forcid.org\u002F0000-0002-5800-8764","https:\u002F\u002Factainnovations.com\u002Findex.php\u002Fpub\u002Farticle\u002Fdownload\u002F1918\u002F981",{"tldr":394,"method":395,"finding":396,"direction":79,"opportunity":397},"提出轻量注意力多级混合MobileNet-V2框架，融合手工纹理与深度学习特征实现番茄叶片病害早期检","高斯\u002F双边\u002F引导滤波去噪，LAB+CLAHE增强，Otsu分割，LBP与GLCM","所提模型分类性能优于现有模型，可有效用于智慧农业实时番茄叶片病害检测。","可探索多作物跨域泛化、田间复杂光照下轻量模型部署与可解释性，及病害早期分级检测。","2026-10-20T23:30:10.424511Z",{"id":400,"title":401,"url":402,"summary":403,"summary_zh":404,"content":8,"source_name":405,"source_url":402,"published_at":406,"category":11,"cover_url":8,"hotness":12,"is_selected":13,"score":407,"score_detail":408,"sources":412,"tags":414,"primary_topic":418,"secondary_topics":422,"classification":429,"search_phrases":474,"slug":477,"view_count":74,"doi":8,"paper":478,"created_at":496},5313,"Real-Time IoT-Integrated Ensemble LSTM–Bi-LSTM Framework for Greenhouse Microclimate Forecasting","https:\u002F\u002Fwasrpublication.com\u002Findex.php\u002Findex\u002Farticle\u002Fview\u002F512","Accurate prediction of greenhouse microclimates is essential for optimizing crop growth and resource utilization in precision agriculture. The research presents an IoT-integrated ensemble deep learning framework for real-time greenhouse microclimate forecasting using Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks. Environmental variables, including temperature, light intensity, soil moisture, and humidity, were acquired through IoT sensor nodes deployed in a controlled greenhouse environment. A benchmark greenhouse dataset was first used for model development and hyperparameter optimization, while an original IoT-based dataset collected during cucumber, tomato, and pepper cultivation at the Federal University Wukari, Nigeria, was used for validation and real-world deployment. The data were preprocessed through noise filtering, missing value imputation, Z-score-based outlier removal, and Min–Max normalization. A weighted ensemble strategy was then applied to combine LSTM and Bi-LSTM predictions for improved robustness. Experimental results show that the Bi-LSTM model outperformed the LSTM model, achieving R² = 0.9981, MAE = 0.0088, RMSE = 0.0110, and MSE = 0.0001, compared to LSTM results of R² = 0.9956, MAE = 0.0133, RMSE = 0.0167, and MSE = 0.0003. Statistical validation using paired t-test, Wilcoxon signed-rank test, confidence intervals, and multi-run analysis confirmed that the performance improvement is statistically significant and robust. The proposed framework enables accurate real-time microclimate forecasting and intelligent environmental monitoring, providing a scalable solution for precision greenhouse management, improved crop productivity, optimized energy utilization, and efficient irrigation scheduling.","准确预测温室微气候对于精准农业中优化作物生长和资源利用至关重要。本研究提出了一种集成物联网的集成深度学习框架，利用长短期记忆网络（LSTM）和双向长短期记忆网络（Bi-LSTM）进行实时温室微气候预测。温度、光照强度、土壤湿度和湿度等环境变量通过部署在受控温室环境中的物联网传感器节点采集。研究首先使用基准温室数据集进行模型开发和超参数优化，随后使用在尼日利亚武卡里联邦大学黄瓜、番茄和辣椒种植期间采集的原始物联网数据集进行验证和实际部署。数据经过噪声滤波、缺失值插补、基于Z分数的异常值去除和最小—最大归一化预处理。然后采用加权集成策略融合LSTM和Bi-LSTM的预测结果以提高鲁棒性。实验结果表明，Bi-LSTM模型优于LSTM模型，其R² = 0.9981、MAE = 0.0088、RMSE = 0.0110、MSE = 0.0001，而LSTM的结果为R² = 0.9956、MAE = 0.0133、RMSE = 0.0167、MSE = 0.0003。采用配对t检验、Wilcoxon符号秩检验、置信区间和多轮运行分析进行的统计验证证实，性能提升具有统计显著性和鲁棒性。所提出的框架能够实现准确的实时微气候预测和智能环境监测，为精准温室管理、提高作物生产力、优化能源利用和高效灌溉调度提供了可扩展的解决方案。","World Journal of Multidisciplinary Studies","2026-10-16T00:00:00Z",67,{"impact":194,"substance":409,"depth":410,"authority":20,"freshness":229,"relevant":21,"comment":411},21,17,"方法扎实、验证充分，但属单点应用研究，公共影响有限，适合作为技术前沿条目而非头条精选。",[413],{"name":405,"url":402},[26,27,415,416,417],"农业物联网","温室环境","小气候预测",{"code":314,"slug":419,"name":420,"path":421,"parent_code":36},"protected-horticulture","设施园艺与植物工厂","\u002Ftopic\u002Fhorticulture\u002Fprotected-horticulture",[423,428],{"code":424,"slug":425,"name":426,"path":427,"parent_code":179},"I5","agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":13,"version":40,"method":41,"evidence":430},{"candidates":431,"agricultural_evidence":46},[432,438,443,450,456,460,467],{"code":424,"score":96,"supported":46,"title":433,"abstract":435,"tags":437},[434],"IoT",[436,434],"物联网",[415],{"code":314,"score":19,"supported":46,"title":439,"abstract":441,"tags":442},[440],"greenhouse",[317,440],[],{"code":32,"score":20,"supported":46,"title":444,"abstract":445,"tags":449},[],[48,446,447,112,448],"辣椒","黄瓜","cucumber",[],{"code":64,"score":109,"supported":46,"title":451,"abstract":452,"tags":455},[],[453,454],"精准农业","precision agriculture",[26],{"code":58,"score":109,"supported":46,"title":457,"abstract":458,"tags":459},[],[357,373],[27],{"code":461,"score":84,"supported":46,"title":462,"abstract":463,"tags":466},"H2",[],[464,465],"土壤","soil",[],{"code":468,"score":84,"supported":46,"title":469,"abstract":470,"tags":473},"H3",[],[471,472],"灌溉","irrigation",[],[475,476],"温室 小气候 LSTM 预测","尼日利亚 温室 IoT 黄瓜 番茄","温室小气候LSTM预测-5313",{"doi":8,"openalex_id":479,"authors":480,"venue":405,"cited_by_count":74,"oa_url":8,"card":491,"direction":155,"ingested_from":156},"W7222909837",[481,483,485,487,489],{"name":482,"orcid":8},"Siman Emmanuel*",{"name":484,"orcid":8},"Edward Onyebueke Agu",{"name":486,"orcid":8},"Musa Gani",{"name":488,"orcid":8},"Oladunjoye John Abiodun",{"name":490,"orcid":8},"Anagu Emmanuel John",{"tldr":492,"method":493,"finding":494,"direction":155,"opportunity":495},"提出物联网集成LSTM与Bi-LSTM加权集成框架，实时预测温室微气候。","IoT传感器采集温光湿数据，经预处理后用LSTM-Bi-LSTM加权集成建模。","Bi-LSTM优于LSTM，R²达0.9981，统计检验证实性能提升显著稳健。","可探索边缘端轻量化部署与多作物跨温室迁移学习，提升实时预测泛化性。","2026-10-19T23:30:13.295236Z"]