[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4417":3,"related-4417":101},{"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":75,"slug":78,"view_count":79,"doi":80,"paper":81,"created_at":100},4417,"CuFormer U-Net: a transformer-enhanced multi-task network for cucumber leaf disease detection and segmentation","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffpls.2026.1975030","Cucumber foliar symptoms reduce functional leaf area and complicate greenhouse scouting. This study presents CuFormer U-Net, a Transformer-enhanced multi-task network for three-class image-level classification on the 3,754-image Kaggle benchmark (healthy, powdery mildew, and downy mildew) and binary visible-symptom segmentation on a separate 400-image greenhouse cohort (200 healthy and 200 affected leaves). The greenhouse annotations comprise 2,705 rectangles (1,741 color-abnormality and 964 tissue-damage instances); rectangle-seeded lesion masks were manually refined for the dense-prediction experiments. The reported fixed-split point estimates were 96.7% accuracy, 96.3% macro precision, 95.8% macro recall, and 96.0% macro F1 for classification, and 92.4% mean image-wise Dice, 83.1% macro IoU, 93.2% foreground precision, and 91.7% foreground recall for segmentation. The complete internal-validation ablation configuration reached 93.1% Dice and 87.3% IoU. The available experiment archive does not contain independent-seed reruns, per-image predictions for inferential testing, annotator-level masks, quantitative results for the separate 100-image greenhouse stress-test cohort, or reproducible hardware profiling. Accordingly, all between-model differences are interpreted descriptively, the external cohort is not presented as formal external validation, and robustness and deployment claims have been moderated. CuFormer U-Net provides a technically motivated basis for joint recognition and spatial characterization, but confirmatory multi-run and multi-site evaluation is required. boundary refinement, cucumber leaf disease, multi-task learning, plant disease, precision agriculture, semantic segmentation, vision transformer","黄瓜叶片症状会减少有效叶面积，并增加温室巡查的难度。本研究提出CuFormer U-Net，这是一种经Transformer增强的多任务网络，用于在包含3，754张图像的Kaggle基准数据集上进行三类图像级分类（健康、白粉病和霜霉病），并在一个独立的包含400张图像的温室队列（200张健康叶片和200张受影响叶片）上进行二值可见症状分割。温室标注包含2，705个矩形框（1，741个颜色异常实例和964个组织损伤实例）；用于密集预测实验的矩形框种子病灶掩膜经过人工精修。所报告的固定划分点估计结果为：分类任务准确率96.7%、宏平均精确率96.3%、宏平均召回率95.8%、宏平均F1值96.0%；分割任务平均图像级Dice系数92.4%、宏平均IoU 83.1%、前景精确率93.2%、前景召回率91.7%。完整的内部验证消融配置达到Dice 93.1%和IoU 87.3%。现有实验档案不包含独立随机种子重跑、用于推断性检验的逐图像预测、标注者级别掩膜、针对独立100张图像温室压力测试队列的定量结果，或可复现的硬件性能分析。因此，所有模型间差异均以描述性方式解释，外部队列不作为正式外部验证呈现，稳健性和部署相关主张也已作审慎表述。CuFormer U-Net为联合识别与空间表征提供了具有技术依据的基础，但仍需开展验证性多轮次和多站点评估。边界精修、黄瓜叶部病害、多任务学习、植物病害、精准农业、语义分割、视觉Transformer",null,"Frontiers in Plant Science","2026-10-07T00:00:00Z","论文",10,false,73,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},15,20,17,13,8,1,"方法新颖、数据与指标披露充分且自我限定严谨，但属单作物单场景研究，产业影响有限，适合作为技术类精选。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","植物病害识别","图像分割","黄瓜种植",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":47},[45,53,61,69],{"code":33,"score":46,"supported":47,"title":48,"abstract":50,"tags":52},14,true,[49],"cucumber",[51,49],"黄瓜",[],{"code":54,"score":55,"supported":47,"title":56,"abstract":57,"tags":60},"I1",7,[],[58,59],"精准农业","precision agriculture",[27],{"code":62,"score":63,"supported":47,"title":64,"abstract":65,"tags":68},"B7",6,[],[66,67],"温室","greenhouse",[],{"code":70,"score":71,"supported":14,"title":72,"abstract":73,"tags":74},"I2",3,[],[],[28,30,29],[76,77],"CuFormer U-Net 黄瓜叶部病害","黄瓜 霜霉病 白粉病 识别","CuFormerU-Net黄瓜叶部病害-4417",0,"10.3389\u002Ffpls.2026.1975030",{"doi":80,"openalex_id":82,"authors":83,"venue":10,"cited_by_count":79,"oa_url":91,"card":92,"direction":98,"ingested_from":99},"W7220838309",[84,87,89],{"name":85,"orcid":86},"Batyrkhan Omarov","https:\u002F\u002Forcid.org\u002F0000-0002-8341-7113",{"name":88,"orcid":9},"Sayat Ibrayev",{"name":90,"orcid":9},"Nurbibi Imanbayeva","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fplant-science\u002Farticles\u002F10.3389\u002Ffpls.2026.1975030\u002Fpdf",{"tldr":93,"method":94,"finding":95,"direction":96,"opportunity":97},"提出CuFormer U-Net多任务网络，同时实现黄瓜叶病分类与病斑分割。","Transformer增强U-Net，用Kaggle 3754图分类和400图温","分类准确率96.7%，分割Dice 92.4%，但缺独立重复与外部验证。","农业遥感与作物表型","需多轮多站点验证，并补全外部压力测试与可复现部署评估。","智慧农业 \u002F 农业物联网","openalex","2026-10-08T23:30:09.461430Z",{"total":63,"page":22,"page_size":63,"items":102},[103,167,231,294,385,439],{"id":104,"title":105,"url":106,"summary":107,"summary_zh":108,"content":9,"source_name":109,"source_url":106,"published_at":110,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":111,"score_detail":112,"sources":116,"tags":118,"primary_topic":121,"secondary_topics":122,"classification":123,"search_phrases":142,"slug":145,"view_count":137,"doi":146,"paper":147,"created_at":166},2962,"A Multi-Modal Generative Model for Tomato Disease Leaves Understanding","https:\u002F\u002Fdoi.org\u002F10.48550\u002Farxiv.2609.19555","Artificial intelligence for plant disease analysis has advanced from task-specific classifiers to multi-modal models capable of jointly interpreting visual and textual information. However, practical deployment in precision agriculture remains limited because most existing approaches treat disease understanding as isolated prediction tasks, failing to capture the complementary relationships among symptom recognition, severity assessment, and question-driven diagnostic reasoning. In tomato pathology, accurate interpretation of diseased leaves requires more than label prediction; it demands integrating visual symptoms with semantic context to support a comprehensive and explainable understanding. Here, we present SOLAR, a multimodal generative model that understands tomato disease spanning six question-answering tasks. SOLAR learns to align visual features with task-aware language representations by Fusion Expert module based on mixture-of-expert, enabling it to generate contextually relevant answers across diverse diagnostic tasks. By formulating tomato disease analysis as a generative Visual Question Answering (VQA) task, SOLAR provides a flexible framework that supports multi-task inference within a single model while improving performance and cross-task knowledge sharing. We evaluate SOLAR on $41,677$ images, including $216,209$ Question-Answering (QA) pairs to understand tomato leaf disease under both closed and open-ended QA settings. Experimental results show that SOLAR consistently outperforms state-of-the-art vision-only, vision-language, and task-specific models across all tasks, demonstrating superior accuracy, robustness, and multimodal reasoning. These findings highlight the potential of generative multimodal modeling as an effective direction for understanding of plant disease. The code for this study is available at https:\u002F\u002Fgithub.com\u002FEnalisUs\u002FSOLAR.","人工智能用于植物病害分析已从任务专用分类器发展到能够联合解读视觉与文本信息的多模态模型。然而，在精准农业中的实际部署仍然有限，因为大多数现有方法将病害理解视为孤立的预测任务，未能捕捉症状识别、严重程度评估与问题驱动诊断推理之间的互补关系。在番茄病理学中，对病叶的准确解读需要的不仅仅是标签预测；它要求将视觉症状与语义上下文相结合，以支持全面且可解释的理解。在此，我们提出SOLAR，一种多模态生成模型，能够理解番茄病害并涵盖六项问答任务。SOLAR通过基于专家混合的融合专家模块，学习将视觉特征与任务感知的语言表示对齐，使其能够在多样化的诊断任务中生成上下文相关的答案。通过将番茄病害分析表述为生成式视觉问答（VQA）任务，SOLAR提供了一个灵活的框架，支持在单一模型内进行多任务推理，同时提升性能并促进跨任务知识共享。我们在$41,677$张图像上评估SOLAR，其中包括$216,209$个问答（QA）对，以在封闭式和开放式问答设置下理解番茄叶片病害。实验结果表明，SOLAR在所有任务上均持续优于最先进的纯视觉、视觉语言和任务专用模型，展现出更优的准确性、鲁棒性和多模态推理能力。这些发现凸显了生成式多模态建模作为理解植物病害的有效方向的潜力。本研究的代码可在https:\u002F\u002Fgithub.com\u002FEnalisUs\u002FSOLAR获取。","arXiv (Cornell University)","2026-09-17T00:00:00Z",79,{"impact":113,"substance":114,"depth":113,"authority":20,"freshness":21,"relevant":22,"comment":115},18,22,"提出面向番茄病害的多模态生成式VQA模型SOLAR，在4万余张图像上验证多任务诊断性能，方法新颖、数据规模可观，对智慧植保有参考价值。",[117],{"name":109,"url":106},[27,28,119,29,120],"番茄病害","多模态模型",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":124},{"candidates":125,"agricultural_evidence":47},[126,132,136],{"code":33,"score":17,"supported":47,"title":127,"abstract":129,"tags":131},[128],"tomato",[130,128],"番茄",[119],{"code":54,"score":55,"supported":47,"title":133,"abstract":134,"tags":135},[],[58,59],[27],{"code":70,"score":137,"supported":47,"title":138,"abstract":139,"tags":141},5,[],[140],"artificial intelligence",[28,29],[143,144],"SOLAR 番茄病害 多模态模型","番茄叶片病害 视觉问答","SOLAR番茄病害多模态模型-2962","10.48550\u002Farxiv.2609.19555",{"doi":146,"openalex_id":148,"authors":149,"venue":109,"cited_by_count":79,"oa_url":106,"card":160,"direction":164,"ingested_from":99},"W7213586905",[150,153,155,157],{"name":151,"orcid":152},"Khang Nguyen Quoc","https:\u002F\u002Forcid.org\u002F0000-0003-4927-4822",{"name":154,"orcid":9},"Minh-Phuoc Tran",{"name":156,"orcid":9},"Gia-Han Truong",{"name":158,"orcid":159},"Luyl-Da Quach","https:\u002F\u002Forcid.org\u002F0000-0002-5661-4250",{"tldr":161,"method":162,"finding":163,"direction":164,"opportunity":165},"提出多模态生成模型SOLAR，统一理解番茄病害叶片的六类问答任务。","基于混合专家融合模块对齐视觉与任务感知语言，用4万余图像和21万问答对训练。","SOLAR在闭集和开放问答中均超越视觉、视觉语言及任务专用模型，展现更强推理能力。","农业人工智能与决策模型","可探索将生成式多模态VQA扩展到更多作物和田间实时场景，并融合传感器数据。","2026-09-19T23:30:55.245800Z",{"id":168,"title":169,"url":170,"summary":171,"summary_zh":9,"content":9,"source_name":172,"source_url":9,"published_at":173,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":174,"score_detail":175,"sources":177,"tags":179,"primary_topic":182,"secondary_topics":183,"classification":190,"search_phrases":217,"slug":220,"view_count":221,"doi":9,"paper":222,"created_at":230},2274,"ArXiv 2609.10469 AgroVisNet:轻量化卷积网络及萝卜-马铃薯-葫芦病害诊断基准","https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.10469","提出AgroVisNet紧凑型卷积网络及专家验证基准BD-PlantDX,包含孟加拉国Bogura和Nilphamari地区12类萝卜、土豆、葫芦共12432张田间图像。模型参数仅29万,测试精度99.52%,加权F1 99.52%,部署后量化0.46MB,CPU推理8.40ms\u002F张。","arXiv 2609.10469","2026-09-08T16:00:00Z",77,{"impact":113,"substance":114,"depth":113,"authority":20,"freshness":63,"relevant":22,"comment":176},"提出29万参数轻量卷积网络与万余张田间病害基准数据集，量化后仅0.46MB、CPU单张8.4ms，对低成本边缘部署的作物病害诊断有实用参考价值。",[178],{"name":172,"url":170},[27,28,180,29,181],"边缘计算","轻量化模型",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[184],{"code":185,"slug":186,"name":187,"path":188,"parent_code":189},"A5","tubers-grains","薯类与杂粮","\u002Ftopic\u002Ffield-crops\u002Ftubers-grains","A",{"status":40,"locked":14,"version":41,"method":42,"evidence":191},{"candidates":192,"agricultural_evidence":47},[193,199,204,208,212],{"code":33,"score":194,"supported":47,"title":195,"abstract":197,"tags":198},11,[196],"萝卜",[196],[],{"code":185,"score":21,"supported":47,"title":200,"abstract":202,"tags":203},[201],"马铃薯",[],[],{"code":70,"score":71,"supported":14,"title":205,"abstract":206,"tags":207},[],[],[28,29,181],{"code":54,"score":22,"supported":14,"title":209,"abstract":210,"tags":211},[],[],[27],{"code":213,"score":22,"supported":14,"title":214,"abstract":215,"tags":216},"I5",[],[],[180],[218,219],"农业人工智能 植物病害识别 轻量化模型 智慧农业","农业人工智能 植物病害识别","农业人工智能植物病害识别轻量化模型智慧农业-2274",2,{"doi":9,"openalex_id":9,"authors":223,"venue":9,"cited_by_count":79,"oa_url":9,"card":224,"direction":164,"ingested_from":229},[],{"tldr":225,"method":226,"finding":227,"direction":164,"opportunity":228},"提出轻量卷积网络AgroVisNet及萝卜、马铃薯、葫芦病害诊断基准BD-PlantDX。","构建12432张田间图像基准，设计29万参数紧凑CNN并量化部署。","测试精度99.52%，量化后仅0.46MB，CPU推理8.40ms\u002F张。","可探索跨地区跨作物泛化、田间复杂光照下的轻量模型鲁棒性与边缘部署。","agent","2026-09-13T00:04:05.295687Z",{"id":232,"title":233,"url":234,"summary":235,"summary_zh":236,"content":9,"source_name":237,"source_url":234,"published_at":238,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":239,"score_detail":240,"sources":244,"tags":246,"primary_topic":249,"secondary_topics":250,"classification":256,"search_phrases":274,"slug":277,"view_count":79,"doi":278,"paper":279,"created_at":293},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":241,"substance":113,"depth":242,"authority":13,"freshness":21,"relevant":22,"comment":243},12,16,"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。",[245],{"name":237,"url":234},[27,28,247,119,248],"深度学习","图像识别",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[251],{"code":70,"slug":252,"name":253,"path":254,"parent_code":255},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":40,"locked":14,"version":41,"method":42,"evidence":257},{"candidates":258,"agricultural_evidence":47},[259,263,269],{"code":33,"score":17,"supported":47,"title":260,"abstract":261,"tags":262},[128],[130,128],[119],{"code":70,"score":264,"supported":47,"title":265,"abstract":266,"tags":268},9,[],[247,267],"deep learning",[28,248,247],{"code":54,"score":55,"supported":47,"title":270,"abstract":271,"tags":273},[],[27,272],"smart agriculture",[27],[275,276],"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":278,"openalex_id":280,"authors":281,"venue":237,"cited_by_count":79,"oa_url":287,"card":288,"direction":98,"ingested_from":99},"W7222977034",[282,284],{"name":283,"orcid":9},"Mrs. Vijetalaxmi A Hegde",{"name":285,"orcid":286},"Abhay Ramakant Kasetwar","https:\u002F\u002Forcid.org\u002F0000-0002-5800-8764","https:\u002F\u002Factainnovations.com\u002Findex.php\u002Fpub\u002Farticle\u002Fdownload\u002F1918\u002F981",{"tldr":289,"method":290,"finding":291,"direction":164,"opportunity":292},"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":295,"title":296,"url":297,"summary":298,"summary_zh":299,"content":9,"source_name":300,"source_url":297,"published_at":301,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":302,"score_detail":303,"sources":306,"tags":308,"primary_topic":312,"secondary_topics":316,"classification":322,"search_phrases":362,"slug":365,"view_count":79,"doi":9,"paper":366,"created_at":384},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":241,"substance":304,"depth":19,"authority":264,"freshness":21,"relevant":22,"comment":305},21,"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。",[307],{"name":300,"url":297},[27,28,309,310,311],"农业物联网","温室环境","小气候预测",{"code":62,"slug":313,"name":314,"path":315,"parent_code":37},"protected-horticulture","设施园艺与植物工厂","\u002Ftopic\u002Fhorticulture\u002Fprotected-horticulture",[317,321],{"code":213,"slug":318,"name":319,"path":320,"parent_code":255},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":323},{"candidates":324,"agricultural_evidence":47},[325,331,335,340,344,348,355],{"code":213,"score":17,"supported":47,"title":326,"abstract":328,"tags":330},[327],"IoT",[329,327],"物联网",[309],{"code":62,"score":46,"supported":47,"title":332,"abstract":333,"tags":334},[67],[66,67],[],{"code":33,"score":264,"supported":47,"title":336,"abstract":337,"tags":339},[],[130,338,51,128,49],"辣椒",[],{"code":54,"score":55,"supported":47,"title":341,"abstract":342,"tags":343},[],[58,59],[27],{"code":70,"score":55,"supported":47,"title":345,"abstract":346,"tags":347},[],[247,267],[28],{"code":349,"score":63,"supported":47,"title":350,"abstract":351,"tags":354},"H2",[],[352,353],"土壤","soil",[],{"code":356,"score":63,"supported":47,"title":357,"abstract":358,"tags":361},"H3",[],[359,360],"灌溉","irrigation",[],[363,364],"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":9,"openalex_id":367,"authors":368,"venue":300,"cited_by_count":79,"oa_url":9,"card":379,"direction":98,"ingested_from":99},"W7222909837",[369,371,373,375,377],{"name":370,"orcid":9},"Siman Emmanuel*",{"name":372,"orcid":9},"Edward Onyebueke Agu",{"name":374,"orcid":9},"Musa Gani",{"name":376,"orcid":9},"Oladunjoye John Abiodun",{"name":378,"orcid":9},"Anagu Emmanuel John",{"tldr":380,"method":381,"finding":382,"direction":98,"opportunity":383},"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",{"id":386,"title":387,"url":388,"summary":389,"summary_zh":9,"content":9,"source_name":390,"source_url":9,"published_at":391,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":111,"score_detail":392,"sources":394,"tags":396,"primary_topic":399,"secondary_topics":400,"classification":401,"search_phrases":426,"slug":429,"view_count":221,"doi":430,"paper":431,"created_at":438},5301,"MambaSeed:基于Mamba的轻量级混合视觉网络用于番茄叶病识别(PLOS ONE)","https:\u002F\u002Fjournals.plos.org\u002Fplosone\u002Farticle?id=10.1371\u002Fjournal.pone.0359350","PLOS ONE于2026-10-15发表论文MambaSeed,由Wang X, Zhang H, Chen Y, Li Y, Qin Y, Lv Z等团队提出基于MambaVisionMixer的轻量级混合视觉网络,配套局部连续分支注入(LCBI)机制;在番茄、玉米、马铃薯数据集上识别准确率分别达98.97%、98.06%和95.87%,模型仅1.13M参数、0.240G MACs,在RTX 4090上延迟3.39ms\u002F图像,为资源受限农田环境提供紧凑、高效、鲁棒的病害识别方案。","PLOS ONE(2026-10-15)","2026-10-15T00:00:00Z",{"impact":113,"substance":114,"depth":113,"authority":20,"freshness":21,"relevant":22,"comment":393},"方法新颖、指标扎实的轻量级病害识别论文，对资源受限农田场景有实用价值，值得进入每日精选。",[395],{"name":390,"url":388},[27,28,130,397,398],"病害识别","轻量级模型",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":402},{"candidates":403,"agricultural_evidence":47},[404,408,414,418,422],{"code":33,"score":241,"supported":47,"title":405,"abstract":406,"tags":407},[130],[130],[130],{"code":409,"score":71,"supported":47,"title":410,"abstract":411,"tags":413},"A3",[],[412],"玉米",[],{"code":185,"score":71,"supported":47,"title":415,"abstract":416,"tags":417},[],[201],[],{"code":70,"score":221,"supported":14,"title":419,"abstract":420,"tags":421},[],[],[28,397],{"code":54,"score":22,"supported":14,"title":423,"abstract":424,"tags":425},[],[],[27],[427,428],"MambaSeed 番茄叶病","MambaVisionMixer 病害识别","MambaSeed番茄叶病-5301","10.1371\u002Fjournal.pone.0359350",{"doi":430,"openalex_id":9,"authors":432,"venue":9,"cited_by_count":79,"oa_url":9,"card":433,"direction":164,"ingested_from":229},[],{"tldr":434,"method":435,"finding":436,"direction":164,"opportunity":437},"提出轻量级混合视觉网络MambaSeed，实现番茄等作物叶病高效识别。","基于MambaVisionMixer与局部连续分支注入机制，在三种作物病害数据集","番茄、玉米、马铃薯识别准确率达98.97%、98.06%、95.87%，仅1.13M参数、3.39m","可探索该轻量模型在移动端与边缘设备的田间部署，及多作物跨域泛化与病害早期识别。","2026-10-19T00:07:48.589614Z",{"id":440,"title":441,"url":442,"summary":443,"summary_zh":444,"content":9,"source_name":445,"source_url":442,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":446,"score_detail":447,"sources":449,"tags":451,"primary_topic":453,"secondary_topics":454,"classification":456,"search_phrases":473,"slug":476,"view_count":22,"doi":477,"paper":478,"created_at":501},4494,"Tomato ripeness classification with weight-based and texture-adaptive pooling in CNNs","https:\u002F\u002Fdoi.org\u002F10.64960\u002Feasr.2026.266223","This research introduces a weight-based mixed pooling and adaptive fuzzy pooling mechanism based on feature map texture analysis for attention mechanism Squeeze-and-Excitation Networks (SE) and Convolutional Neural Networks (CNNs) in tomato ripeness classification. Traditional CNNs and SE networks rely on deterministic pooling strategies that can be suboptimal for capturing diverse visual features such as texture and color gradients in fruit. A novel fuzzy pooling system is proposed that dynamically adjusts the fusion ratio of min and max pooling based on real-time texture analysis of feature maps via a Laplacian filter. This mechanism was integrated into Darknet53, ResNet34, and ResNet101 architectures, both directly and within the SE attention block. The method was evaluated on a five-class tomato ripeness dataset using 10-fold cross-validation against traditional and fixed-weight pooling methods. The fuzzy and mixed pooling approach demonstrated superior performance on certain models which include ESEnet: Darknet53 + SE (Fuzzy pool) achieved an average F1 score across folds of 0.8429, outperforming Darknet53 + baseline SE (Average pool) at 0.8350; Extended Net: ResNet34 + Fuzzy pool achieved an average F1 score across folds of 0.8305, outperforming baseline ResNet34 at 0.8130 and ResNet101 + Fuzzy pool achieved an average F1 score across folds of 0.8284, outperforming baseline ResNet101 at 0.8267. This improvement was realized with minimal increase in computational overhead. Specifically, measurements of model parameters (M) and FLOPs (GMACs) showed only a slight increase across all architectures after integrating SEnet into the system, and zero increase after integrating the Laplacian filter and fuzzy logic. The study concludes that logic-based adaptive pooling is a robust strategy that improves feature representation in CNNs, achieving a balance between classification accuracy and computational cost. These findings offer practical value for developing more reliable automated harvesting systems and provide a generalizable enhancement for a wide range of computer vision classification tasks.","本研究提出了一种基于特征图纹理分析的权重混合池化与自适应模糊池化机制，用于番茄成熟度分类中的注意力机制挤压激励网络（Squeeze-and-Excitation Networks, SE）和卷积神经网络（Convolutional Neural Networks, CNNs）。传统的CNN和SE网络依赖确定性池化策略，在捕捉果实纹理和颜色梯度等多样化视觉特征时可能并非最优。本文提出了一种新颖的模糊池化系统，通过拉普拉斯滤波器对特征图进行实时纹理分析，动态调整最小池化和最大池化的融合比例。该机制被集成到Darknet53、ResNet34和ResNet101架构中，既可直接集成，也可嵌入SE注意力模块内。该方法在五类番茄成熟度数据集上采用10折交叉验证，与传统池化及固定权重池化方法进行了对比评估。模糊池化和混合池化方法在部分模型上表现出优越性能，包括：ESEnet：Darknet53 + SE（模糊池化）在各折上的平均F1得分为0.8429，优于Darknet53 + 基线SE（平均池化）的0.8350；扩展网络：ResNet34 + 模糊池化在各折上的平均F1得分为0.8305，优于基线ResNet34的0.8130；ResNet101 + 模糊池化在各折上的平均F1得分为0.8284，优于基线ResNet101的0.8267。这一改进仅带来了极小的计算开销增加。具体而言，模型参数量（M）和浮点运算次数（GMACs）的测量结果表明，将SEnet集成到系统后所有架构仅有轻微增加，而集成拉普拉斯滤波器和模糊逻辑后则无任何增加。研究结论认为，基于逻辑的自适应池化是一种鲁棒策略，能够改善CNN中的特征表示，在分类精度和计算成本之间实现平衡。这些发现为开发更可靠的自动化收获系统提供了实用价值，并为广泛的计算机视觉分类任务提供了一种可推广的增强方法。","Engineering and Applied Science Research",66,{"impact":21,"substance":18,"depth":19,"authority":241,"freshness":264,"relevant":22,"comment":448},"提出基于纹理自适应模糊池化的CNN改进方法，在番茄成熟度分类上取得小幅但稳定的F1提升且算力开销几乎不增，对自动采摘与农业视觉识别有参考价值，但属细分方法类论文，影响面有限。",[450],{"name":445,"url":442},[27,28,130,248,452],"自动采摘",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[455],{"code":70,"slug":252,"name":253,"path":254,"parent_code":255},{"status":40,"locked":14,"version":41,"method":42,"evidence":457},{"candidates":458,"agricultural_evidence":47},[459,463,469],{"code":33,"score":17,"supported":47,"title":460,"abstract":461,"tags":462},[128],[130,128],[130],{"code":70,"score":21,"supported":47,"title":464,"abstract":465,"tags":468},[],[466,467],"计算机视觉","computer vision",[28,248],{"code":54,"score":22,"supported":14,"title":470,"abstract":471,"tags":472},[],[],[27],[474,475],"番茄 成熟度 分类 卷积神经网络","Darknet53 ResNet 番茄 成熟度","番茄成熟度分类卷积神经网络-4494","10.64960\u002Feasr.2026.266223",{"doi":477,"openalex_id":479,"authors":480,"venue":445,"cited_by_count":79,"oa_url":495,"card":496,"direction":98,"ingested_from":99},"W7220840158",[481,483,485,487,490,492],{"name":482,"orcid":9},"Rut Yatigul",{"name":484,"orcid":9},"Wisanu Jitviriya",{"name":486,"orcid":9},"Eiji Hayashi",{"name":488,"orcid":489},"Aran Blattler","https:\u002F\u002Forcid.org\u002F0000-0002-8684-6239",{"name":491,"orcid":9},"Watcharin Tangsuksant",{"name":493,"orcid":494},"Teppakorn Sittiwanchai","https:\u002F\u002Forcid.org\u002F0000-0001-9653-8750","https:\u002F\u002Fph01.tci-thaijo.org\u002Findex.php\u002Feasr\u002Farticle\u002Fdownload\u002F266223\u002F176569",{"tldr":497,"method":498,"finding":499,"direction":164,"opportunity":500},"提出基于纹理自适应模糊池化机制，提升CNN番茄成熟度分类性能。","用Laplacian滤波分析特征图纹理，动态调整最大最小池化融合比，集成到Dar","模糊池化在多个模型上F1提升，且计算开销几乎不增加。","可探索自适应池化在其它果蔬成熟度或田间复杂光照下的泛化能力。","2026-10-09T23:30:09.993787Z"]