[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2934":3,"related-2934":86},{"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":27,"primary_topic":32,"secondary_topics":38,"classification":39,"search_phrases":66,"slug":69,"view_count":61,"doi":70,"paper":71,"created_at":85},2934,"A CNN-Based Approach for Leaf Disease Prediction in Smart Agriculture","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22825329","Plants play a crucial role in sustaining life by serving as a primary source of energy and mitigating global warming. However, they are increasingly vulnerable to diseases such as bacterial spot, late blight, and Septoria leaf spot, which significantly impact crop yield and agricultural productivity. Early and accurate detection of these diseases is essential for effective disease management and improved agricultural outcomes. This project aims to develop a deep learning-based approach for detecting plant leaf diseases using Convolutional Neural Networks (CNN). By leveraging benchmark datasets, the proposed CNN model demonstrates superior performance compared to traditional machine learning techniques, achieving an accuracy of 92%, precision of 89%, F1-score of 93%, and recall of 92.47%. The results highlight the effectiveness of CNN in automating disease identification, enabling timely intervention, and promoting sustainable agricultural practices.","植物在维持生命方面发挥着至关重要的作用，既是主要的能量来源，又能缓解全球变暖。然而，植物日益受到细菌性斑点病、晚疫病和壳针孢叶斑病等病害的威胁，严重影响作物产量和农业生产率。早期准确地检测这些病害对于有效防控病害和改善农业成果至关重要。本项目旨在开发一种基于深度学习的方法，利用卷积神经网络（CNN）检测植物叶片病害。通过利用基准数据集，所提出的CNN模型展现出优于传统机器学习技术的性能，达到了92%的准确率、89%的精确率、93%的F1分数和92.47%的召回率。结果表明，CNN在自动化病害识别方面具有显著效果，能够实现及时干预并促进可持续农业实践。",null,"Zenodo (CERN European Organization for Nuclear Research)","2026-09-18T00:00:00Z","论文",25,false,65,{"impact":17,"substance":18,"depth":19,"authority":17,"freshness":20,"relevant":21,"comment":22},12,18,14,9,1,"基于CNN的叶片病害识别研究，方法常规、数据集为公开基准，准确率92%属中等水平，对智慧农业植保场景有一定参考价值但缺乏突破性。",[24,25],{"name":10,"url":6},{"name":10,"url":26},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22825330",[28,29,30,31],"智慧农业","农业人工智能","深度学习","植物病害识别",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":40,"locked":14,"version":41,"method":42,"evidence":43},"classified","2026-10-22.2","rules",{"candidates":44,"agricultural_evidence":46},[45,53,59],{"code":33,"score":17,"supported":46,"title":47,"abstract":48,"tags":52},true,[],[30,49,50,51],"机器学习","machine learning","deep learning",[29,31,30],{"code":54,"score":20,"supported":46,"title":55,"abstract":57,"tags":58},"I1",[56],"smart agriculture",[],[28],{"code":60,"score":61,"supported":46,"title":62,"abstract":63,"tags":65},"H8",3,[],[64],"可持续农业",[],[67,68],"CNN 植物叶片病害 识别","卷积神经网络 作物病害 检测","CNN植物叶片病害识别-2934","10.5281\u002Fzenodo.22825329",{"doi":70,"openalex_id":72,"authors":73,"venue":10,"cited_by_count":76,"oa_url":6,"card":77,"direction":83,"ingested_from":84},"W7213587327",[74],{"name":75,"orcid":9},"B.Yashmal Sai, K.Karthik, K.Neeraj, G. Mahabub Subhani",0,{"tldr":78,"method":79,"finding":80,"direction":81,"opportunity":82},"用CNN对植物叶片病害进行自动识别，在基准数据集上取得92%准确率。","基于卷积神经网络，使用植物叶片病害基准数据集训练与评估。","CNN优于传统机器学习方法，准确率92%、F1值93%，可支持及时干预。","农业人工智能与决策模型","可探索轻量化CNN在田间移动端实时检测，并结合多病害与早期症状识别。","智慧农业 \u002F 农业物联网","openalex","2026-09-19T23:30:11.855376Z",{"total":87,"page":21,"page_size":87,"items":88},6,[89,144,206,268,322,377],{"id":90,"title":91,"url":92,"summary":93,"summary_zh":94,"content":9,"source_name":95,"source_url":92,"published_at":96,"category":12,"cover_url":9,"hotness":97,"is_selected":14,"score":98,"score_detail":99,"sources":103,"tags":105,"primary_topic":107,"secondary_topics":108,"classification":109,"search_phrases":122,"slug":125,"view_count":126,"doi":127,"paper":128,"created_at":143},3769,"Fine-Tuned Hybrid Deep Learning Framework for Plant Disease Classification Using MobileNetV2 and EfficientNetB0 Feature Fusion","https:\u002F\u002Fdoi.org\u002F10.47116\u002Fapjcri.2026.09.25","Plant diseases can substantially affect crop productivity and contribute to agricultural losses, creating a need for accurate and automated disease identification methods.Deep learning has become an effective approach for image-based plant disease recognition; however, relying on a single CNN architecture may limit the diversity of visual representations available for classification.This study presents a fine-tuned hybrid framework that combines MobileNetV2 and EfficientNetB0 through feature-level fusion for plant disease classification.The two backbone networks provide complementary representations, with MobileNetV2 offering a lightweight feature extraction capability and EfficientNetB0 providing richer visual representations.ImageNet-pretrained weights were employed, followed by selective fine-tuning to adapt the learned representations to the target plant disease dataset.Experiments were performed using the PlantVillage dataset containing 38 plant disease classes, with image preprocessing, augmentation, transfer learning, and fine-tuning incorporated into the experimental procedure.The proposed fine-tuned hybrid model achieved a validation accuracy of 98.90%, compared with 93.57% for MobileNetV2, 95.86% for EfficientNetB0, and 97.94% for the hybrid model without fine-tuning.The model also obtained high Precision, Recall, and F1-score values across the evaluated disease categories.Overall, the results indicate that combining complementary feature representations with selective fine-tuning can improve classification performance on the PlantVillage dataset and provide a promising basis for practical plant disease diagnosis in smart agriculture applications.","植物病害会显著影响作物生产力并造成农业损失，因此需要准确且自动化的病害识别方法。深度学习已成为基于图像的植物病害识别的有效方法；然而，依赖单一CNN架构可能会限制可用于分类的视觉表征的多样性。本研究提出了一种经过微调的混合框架，通过特征级融合将MobileNetV2和EfficientNetB0相结合，用于植物病害分类。这两个骨干网络提供了互补的表征，其中MobileNetV2具有轻量级特征提取能力，EfficientNetB0则提供更丰富的视觉表征。研究采用了ImageNet预训练权重，并随后进行选择性微调，以使学习到的表征适应目标植物病害数据集。实验使用包含38个植物病害类别的PlantVillage数据集进行，实验流程中纳入了图像预处理、数据增强、迁移学习和微调。所提出的微调混合模型达到了98.90%的验证准确率，而MobileNetV2为93.57%，EfficientNetB0为95.86%，未微调的混合模型为97.94%。该模型在评估的病害类别中还取得了较高的精确率、召回率和F1分数。总体而言，结果表明，将互补的特征表征与选择性微调相结合，可以提高在PlantVillage数据集上的分类性能，并为智慧农业应用中的实际植物病害诊断提供了有前景的基础。","Asia-pacific Journal of Convergent Research Interchange","2026-09-28T00:00:00Z",10,67,{"impact":17,"substance":100,"depth":101,"authority":97,"freshness":20,"relevant":21,"comment":102},20,16,"方法有实质创新且验证精度高，但属实验室数据集研究，产业落地影响有限，可作为技术前沿参考。",[104],{"name":95,"url":92},[28,29,30,31,106],"作物病害防治",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":110},{"candidates":111,"agricultural_evidence":46},[112,117],{"code":33,"score":113,"supported":46,"title":114,"abstract":115,"tags":116},17,[51],[30,51],[29,31,30],{"code":54,"score":118,"supported":46,"title":119,"abstract":120,"tags":121},7,[],[28,56],[28],[123,124],"MobileNetV2 EfficientNetB0 植物病害","PlantVillage 病害分类","MobileNetV2EfficientNetB0植物病害-3769",5,"10.47116\u002Fapjcri.2026.09.25",{"doi":127,"openalex_id":129,"authors":130,"venue":95,"cited_by_count":76,"oa_url":137,"card":138,"direction":83,"ingested_from":84},"W7214573881",[131,133,135],{"name":132,"orcid":9},"Ikromjon Tojiboev",{"name":134,"orcid":9},"Youn-Mo Soung",{"name":136,"orcid":9},"Gwang-Jun Kim","http:\u002F\u002Fapjcriweb.org\u002Fcontent\u002Fvol12no9\u002F25.pdf",{"tldr":139,"method":140,"finding":141,"direction":81,"opportunity":142},"融合MobileNetV2与EfficientNetB0特征并微调，实现植物病害高精度分类。","ImageNet预训练双骨干特征级融合+选择性微调，用PlantVillage ","微调混合模型验证准确率达98.90%，优于单模型与未微调混合模型。","可探索轻量化融合模型在田间复杂背景与移动端的实时病害识别部署。","2026-09-29T23:30:09.013020Z",{"id":145,"title":146,"url":147,"summary":148,"summary_zh":149,"content":9,"source_name":10,"source_url":147,"published_at":150,"category":12,"cover_url":9,"hotness":97,"is_selected":14,"score":151,"score_detail":152,"sources":156,"tags":158,"primary_topic":161,"secondary_topics":167,"classification":169,"search_phrases":186,"slug":189,"view_count":76,"doi":190,"paper":191,"created_at":205},5592,"Evaluation of Concept-Rank Collapse Audits for Computer Vision Agriculture Disease Classifiers Under Low-Label Regimes: An Interpretability Capacity Bound for Smallholder Fungicide Selectivity","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23545193","Concept-based interpretability methods for plant-disease classifiers are typically evaluated by whether their concept activations correlate with human-annotated labels, but this criterion is silent on a prior question: whether the classifier's internal representation retains enough concept-rank structure for any audit to be informative. the present analysis formalises that prior question as an interpretability capacity bound. A classifier is modelled as a concept-rank operator whose singular values govern how much concept-level signal survives the projection from pixel space to class logits, and a collapse audit is defined as the ratio of retained concept-rank energy to total concept energy. Under a low-label regime, where concept annotations are scarce and the audit must be estimated from few labelled examples, the bound predicts that audit reliability degrades as a function of the concept-rank spectrum and the label budget. The analysis is a theoretical and methodological contribution: it derives the bound, states the conditions under which a collapse audit is identifiable, and characterises the operating characteristics of the audit as a decision procedure under a declared variance structure (between-cluster SD = 6.0, residual SD = 4.5, intraclass correlation = 0.64). Power was estimated across 2000 design cells for cluster counts of 8, 16, 24 and 32 and effect sizes of 3, 5 and 8 percentage points; 52 clusters were required for 5 percentage points at 80% power. The bound reframes concept audits as capacity tests rather than fidelity tests, with consequences for how smallholder fungicide-selectivity decisions should be supported by interpretable disease classifiers.","面向植物病害分类器的基于概念的可解释性方法，通常以其概念激活是否与人工标注标签相关作为评价标准，但该标准对一个更先前的问题保持沉默：分类器的内部表征是否保留了足够的概念秩结构，从而使任何审计具有信息量。本分析将该先前问题形式化为一个可解释性容量上界。分类器被建模为概念秩算子，其奇异值支配着从像素空间到类别logits的投影中概念级信号得以保留的程度，并将坍缩审计定义为保留的概念秩能量与总概念能量之比。在低标签情形下，概念标注稀缺且审计必须由少量标注样本估计，该上界预测审计可靠性会随概念秩谱和标签预算的函数而退化。本分析是一项理论和方法论贡献：推导出该上界，陈述坍缩审计可识别的条件，并在声明的方差结构（簇间SD = 6.0，残差SD = 4.5，组内相关系数 = 0.64）下刻画审计作为决策程序的操作特征。在2000个设计单元中，针对簇数为8、16、24和32以及效应量为3、5和8个百分点的情形估计了功效；在80%功效下达到5个百分点需要52个簇。该上界将概念审计重新框定为容量检验而非保真度检验，并对可解释病害分类器应如何支持小农杀菌剂选择性决策具有启示意义。","2026-10-21T00:00:00Z",69,{"impact":153,"substance":154,"depth":18,"authority":17,"freshness":97,"relevant":21,"comment":155},8,21,"理论方法论文，提出可解释性容量上界并给出审计功效分析，对智慧农业病害识别可信度有参考价值，但属小众方法学研究、缺乏田间实证，暂不宜进入每日精选。",[157],{"name":10,"url":147},[28,29,159,31,160],"小农户","可解释性",{"code":162,"slug":163,"name":164,"path":165,"parent_code":166},"G2","farm-services","社会化服务与规模经营","\u002Ftopic\u002Frural-services\u002Ffarm-services","G",[168],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":170},{"candidates":171,"agricultural_evidence":46},[172,177,182],{"code":162,"score":17,"supported":46,"title":173,"abstract":175,"tags":176},[174],"smallholder",[174],[159],{"code":33,"score":97,"supported":46,"title":178,"abstract":180,"tags":181},[179],"computer vision",[],[29,31],{"code":54,"score":21,"supported":14,"title":183,"abstract":184,"tags":185},[],[],[28],[187,188],"农业人工智能 植物病害识别 可解释性 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可解释性智慧农业-5592","10.5281\u002Fzenodo.23545193",{"doi":190,"openalex_id":192,"authors":193,"venue":10,"cited_by_count":76,"oa_url":147,"card":200,"direction":81,"ingested_from":84},"W7223137323",[194,196,198],{"name":195,"orcid":9},"Akshay Ramgoolam",{"name":197,"orcid":9},"Priya Bundhoo Appadoo",{"name":199,"orcid":9},"Jean-Noël LEspérance",{"tldr":201,"method":202,"finding":203,"direction":81,"opportunity":204},"提出可解释性容量上界，评估低标签下概念秩崩溃审计的可靠性。","将分类器建模为概念秩算子，推导容量上界并做2000格功效模拟。","审计可靠性随概念秩谱与标签预算下降；5个百分点效应需52个聚类达80%功效。","可将容量上界用于小农户杀菌剂选择性决策的可解释模型审计与标签预算设计。","2026-10-22T11:21:10.425290Z",{"id":207,"title":208,"url":209,"summary":210,"summary_zh":211,"content":9,"source_name":212,"source_url":209,"published_at":213,"category":12,"cover_url":9,"hotness":97,"is_selected":14,"score":214,"score_detail":215,"sources":217,"tags":219,"primary_topic":222,"secondary_topics":228,"classification":230,"search_phrases":248,"slug":251,"view_count":76,"doi":252,"paper":253,"created_at":267},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":17,"substance":18,"depth":101,"authority":97,"freshness":153,"relevant":21,"comment":216},"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。",[218],{"name":212,"url":209},[28,29,30,220,221],"番茄病害","图像识别",{"code":223,"slug":224,"name":225,"path":226,"parent_code":227},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[229],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":231},{"candidates":232,"agricultural_evidence":46},[233,240,244],{"code":223,"score":234,"supported":46,"title":235,"abstract":237,"tags":239},15,[236],"tomato",[238,236],"番茄",[220],{"code":33,"score":20,"supported":46,"title":241,"abstract":242,"tags":243},[],[30,51],[29,221,30],{"code":54,"score":118,"supported":46,"title":245,"abstract":246,"tags":247},[],[28,56],[28],[249,250],"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":252,"openalex_id":254,"authors":255,"venue":212,"cited_by_count":76,"oa_url":261,"card":262,"direction":83,"ingested_from":84},"W7222977034",[256,258],{"name":257,"orcid":9},"Mrs. Vijetalaxmi A Hegde",{"name":259,"orcid":260},"Abhay Ramakant Kasetwar","https:\u002F\u002Forcid.org\u002F0000-0002-5800-8764","https:\u002F\u002Factainnovations.com\u002Findex.php\u002Fpub\u002Farticle\u002Fdownload\u002F1918\u002F981",{"tldr":263,"method":264,"finding":265,"direction":81,"opportunity":266},"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":269,"title":270,"url":271,"summary":272,"summary_zh":273,"content":9,"source_name":274,"source_url":271,"published_at":213,"category":12,"cover_url":9,"hotness":97,"is_selected":14,"score":275,"score_detail":276,"sources":278,"tags":280,"primary_topic":283,"secondary_topics":284,"classification":285,"search_phrases":307,"slug":310,"view_count":76,"doi":311,"paper":312,"created_at":321},5385,"A Comprehensive Review of Deep Learning and Computer Vision Techniques for Fruit Quality Assessment and Classification","https:\u002F\u002Fdoi.org\u002F10.25258\u002Fijddt.16.75s.151","Fruit image analysis has become an essential research area in precision agriculture, enabling automated fruit classification, quality grading, maturity estimation, disease diagnosis, yield prediction, and intelligent harvesting through advances in computer vision and artificial intelligence (AI).Recent progress in imaging technologies, large-scale benchmark datasets, and deep learning has substantially improved the accuracy, robustness, and scalability of automated fruit analysis systems.This survey presents a comprehensive and systematic review of image processing and AI techniques for fruit image analysis.It covers the complete image analysis pipeline, including image acquisition, preprocessing, enhancement, color space transformation, segmentation, feature extraction, and handcrafted texture descriptors.Furthermore, conventional machine learning algorithms are reviewed alongside state-of-the-art deep learning architectures, including Convolutional Neural Networks (CNNs), Vision Transformers (ViTs), and Vision Mamba models, for applications such as fruit recognition, quality assessment, disease detection, ripeness estimation, and object detection.Publicly available benchmark datasets, evaluation metrics, and performance comparison strategies are also summarized to facilitate objective assessment of existing approaches.In addition, the survey discusses key research challenges, including illumination variations, occlusion, complex orchard environments, limited annotated datasets, computational complexity, and domain adaptation, while highlighting emerging research trends such as self-supervised learning, multimodal learning, explainable AI, lightweight deep networks, foundation models, and edge intelligence for real-time deployment.By providing a unified review of methodologies, datasets, evaluation protocols, challenges, and future research directions, this survey offers a comprehensive reference for researchers and practitioners developing intelligent and scalable fruit image analysis systems for precision agriculture.","水果图像分析已成为精准农业中的一个重要研究领域，借助计算机视觉和人工智能（AI）的进步，实现了果实自动分类、品质分级、成熟度估计、病害诊断、产量预测和智能采收。成像技术、大规模基准数据集和深度学习的最新进展显著提升了自动化水果分析系统的准确性、鲁棒性和可扩展性。本综述对用于水果图像分析的图像处理和AI技术进行了全面而系统的回顾。内容涵盖完整的图像分析流程，包括图像采集、预处理、增强、颜色空间变换、分割、特征提取和手工纹理描述符。此外，综述了传统机器学习算法以及最先进的深度学习架构，包括卷积神经网络（CNN）、视觉Transformer（ViT）和视觉Mamba模型，用于果实识别、品质评估、病害检测、成熟度估计和目标检测等应用。同时总结了公开可用的基准数据集、评价指标和性能比较策略，以便对现有方法进行客观评估。此外，本综述讨论了关键研究挑战，包括光照变化、遮挡、复杂果园环境、标注数据集有限、计算复杂度和域适应，并重点介绍了新兴研究趋势，如自监督学习、多模态学习、可解释AI、轻量级深度网络、基础模型和面向实时部署的边缘智能。通过提供方法、数据集、评价协议、挑战和未来研究方向的统一综述，本综述为开发面向精准农业的智能且可扩展的水果图像分析系统的研究人员和实践者提供了全面的参考。","International Journal of Drug Delivery Technology",56,{"impact":153,"substance":18,"depth":101,"authority":87,"freshness":153,"relevant":21,"comment":277},"系统性综述覆盖CNN、ViT、Vision Mamba等前沿方法，信息量足，但期刊权威性一般且偏学术综述，公共价值有限，适合主题聚合而非每日精选头条。",[279],{"name":274,"url":271},[28,29,281,30,282],"计算机视觉","水果品质检测",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":286},{"candidates":287,"agricultural_evidence":46},[288,295,301],{"code":33,"score":289,"supported":46,"title":290,"abstract":291,"tags":294},28,[51,179],[292,30,49,281,50,51,293,179],"目标检测","artificial intelligence",[29,30,281],{"code":54,"score":118,"supported":46,"title":296,"abstract":297,"tags":300},[],[298,299],"精准农业","precision agriculture",[28],{"code":302,"score":61,"supported":46,"title":303,"abstract":304,"tags":306},"B2",[],[305],"orchard",[],[308,309],"水果品质 计算机视觉 深度学习","农业人工智能 水果品质检测 计算机视觉 智慧农业","水果品质计算机视觉深度学习-5385","10.25258\u002Fijddt.16.75s.151",{"doi":311,"openalex_id":313,"authors":314,"venue":274,"cited_by_count":76,"oa_url":271,"card":315,"direction":83,"ingested_from":84},"W7222892831",[],{"tldr":316,"method":317,"finding":318,"direction":319,"opportunity":320},"系统综述深度学习与计算机视觉在水果品质评估与分级中的全流程方法。","综述图像采集到分割、特征提取及CNN、ViT、Vision Mamba等模型与公","深度学习显著提升水果分析精度与鲁棒性，但光照、遮挡和小样本仍是主要瓶颈。","农业遥感与作物表型","可探索自监督与轻量化模型在复杂果园遮挡、小样本场景下的边缘实时部署。","2026-10-20T23:30:10.066042Z",{"id":323,"title":324,"url":325,"summary":326,"summary_zh":327,"content":9,"source_name":328,"source_url":325,"published_at":329,"category":12,"cover_url":9,"hotness":97,"is_selected":14,"score":330,"score_detail":331,"sources":334,"tags":336,"primary_topic":339,"secondary_topics":340,"classification":341,"search_phrases":357,"slug":360,"view_count":76,"doi":361,"paper":362,"created_at":376},5192,"A Comparative Study of Client-Level Stabilization Techniques in Federated Learning for Robust Plant Disease Recognition","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fs26206566","The successful integration of artificial intelligence (AI) algorithms in precision agriculture provided farmers with the means to identify potential issues, such as early disease detection or pest infestations, by making crop-related predictions. The new technological developments in this field improve the functioning of traditional agriculture by reducing the dependence on specialized human expertise and facilitating greater access to diagnostic procedures. However, most studies conducted in this area rely on centralized training of AI models, which leads to increased costs and raised privacy-related concerns. Federated learning (FL) offers a compelling framework for collaboratively training machine learning (ML) models on distributed datasets without centralizing the data owned by each participant. FL offers significant advantages in the preservation of data privacy, facilitates the collaborative exploitation of geographically distributed data sources, and reduces the risks associated with centralized collection. In this paper, we investigate the current limitations and performance boundaries of existing Federated and privacy-preserving learning in distributed sensing systems for plant disease detection, in scenarios that closely resemble real-world conditions. Our analysis specifically examined how FL aggregation algorithms, such as FedAvg, FedAvgM and FedProx, work in a custom multi-client experimental setup where data is partitioned so that each participant observes only those symptom patterns associated with specific environmental and climatic conditions. We propose further partial aggregation of the local model, an approach where we send only the model backbone to the central server, while the classification head of each participant remains strictly on the client side. The construction of environmentally heterogeneity is combined with a globally representative stabilizer node designed to preserve knowledge across disease classes that may be absent from certain clients.","人工智能（AI）算法在精准农业中的成功集成，为农民提供了通过作物相关预测来识别潜在问题（如早期病害检测或虫害侵染）的手段。该领域的新技术发展通过减少对专业人类知识的依赖并促进更广泛的诊断程序获取，改善了传统农业的运作方式。然而，该领域的大多数研究依赖于AI模型的集中式训练，这导致成本增加并引发隐私相关担忧。联邦学习（FL）提供了一个引人注目的框架，可在分布式数据集上协作训练机器学习（ML）模型，而无需集中化各参与者拥有的数据。联邦学习在保护数据隐私方面具有显著优势，促进了地理上分布的数据源的协作利用，并降低了与集中收集相关的风险。本文研究了在高度接近真实条件的场景中，现有联邦学习与隐私保护学习在用于植物病害检测的分布式感知系统中的当前局限性与性能边界。我们的分析特别考察了联邦学习聚合算法（如FedAvg、FedAvgM和FedProx）在自定义多客户端实验设置中的工作方式，其中数据被划分，使得每个参与者仅观察到与特定环境和气候条件相关的症状模式。我们提出对本地模型进行进一步的部分聚合，即仅将模型骨干发送至中央服务器，而每个参与者的分类头严格保留在客户端侧。环境异质性的构建与一个全局代表性的稳定器节点相结合，该节点旨在保留某些客户端可能缺失的跨病害类别的知识。","Sensors","2026-10-16T00:00:00Z",78,{"impact":18,"substance":154,"depth":113,"authority":332,"freshness":20,"relevant":21,"comment":333},13,"该研究针对植物病害识别中的联邦学习客户端稳定化方法提出部分聚合与稳定节点方案，方法新颖、实验贴近真实场景，对智慧农业隐私计算有参考价值，值得进入每日精选。",[335],{"name":328,"url":325},[28,29,337,31,338],"联邦学习","数据隐私",{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},[],{"status":40,"locked":14,"version":41,"method":42,"evidence":342},{"candidates":343,"agricultural_evidence":46},[344,348,352],{"code":33,"score":17,"supported":46,"title":345,"abstract":346,"tags":347},[],[49,50,293],[29,31,337],{"code":54,"score":118,"supported":46,"title":349,"abstract":350,"tags":351},[],[298,299],[28],{"code":353,"score":21,"supported":14,"title":354,"abstract":355,"tags":356},"I6",[],[],[338],[358,359],"联邦学习 植物病害识别","FedProx 作物病害检测","联邦学习植物病害识别-5192","10.3390\u002Fs26206566",{"doi":361,"openalex_id":363,"authors":364,"venue":328,"cited_by_count":76,"oa_url":325,"card":371,"direction":81,"ingested_from":84},"W7222586734",[365,368],{"name":366,"orcid":367},"Aurora-Felicia Cristea","https:\u002F\u002Forcid.org\u002F0009-0003-9718-065X",{"name":369,"orcid":370},"Ciprian Dobre","https:\u002F\u002Forcid.org\u002F0000-0003-4638-7725",{"tldr":372,"method":373,"finding":374,"direction":81,"opportunity":375},"比较联邦学习客户端级稳定化技术，提升植物病害识别的鲁棒性。","FedAvg\u002FFedAvgM\u002FFedProx聚合，仅上传骨干网络、分类头留本地，","部分聚合加稳定节点可缓解环境异质性与类别缺失带来的性能退化。","可探索面向非独立同分布农业数据的个性化联邦学习与通信效率优化。","2026-10-17T23:30:45.845684Z",{"id":378,"title":379,"url":380,"summary":381,"summary_zh":382,"content":9,"source_name":383,"source_url":380,"published_at":329,"category":12,"cover_url":9,"hotness":97,"is_selected":14,"score":151,"score_detail":384,"sources":386,"tags":388,"primary_topic":391,"secondary_topics":397,"classification":399,"search_phrases":419,"slug":422,"view_count":21,"doi":423,"paper":424,"created_at":457},5164,"Lightweight Hybrid CNN-Transformer Network for Robust Maize Leaf Disease Detection and Edge Deployment","https:\u002F\u002Fdoi.org\u002F10.22266\u002Fijies2026.1130.50","Early and accurate detection of maize leaf diseases is essential for improving crop productivity and supporting precision agriculture.However, deep learning models trained on controlled leaf-image datasets often experience performance degradation under real-world agricultural conditions because of illumination variation, background clutter, occlusion, leaf orientation, and imaging noise.To address these challenges, this study develops a lightweight deep learning framework for robust maize leaf disease classification and edge-oriented deployment.The framework employs MobileNetV3-Small for efficient extraction of disease-discriminative visual features and investigates lightweight feature-learning strategies for improving classification under challenging field conditions.Experiments were conducted using PlantVillage-Maize and Field-Maize datasets comprising 6,188 images from four categories: Maize Leaf Blight (MLB), Common Rust, Healthy, and Leaf Spot.The image-only MobileNetV3-Small model achieved 97.8% accuracy and a 97.4% F1-score on the controlled PlantVillage-Maize dataset, while its performance decreased to 86.1% accuracy and an 83.9% F1-score on Field-Maize, highlighting the domain gap between controlled and real-field imagery.Robustness was further evaluated under Gaussian noise, illumination variation, and partial occlusion, together with computational-efficiency and edge-deployment analyses.The findings demonstrate the importance of lightweight and robust visual feature learning for practical maize disease diagnosis under real-world agricultural imaging conditions.","早期准确检测玉米叶片病害对于提高作物生产力和支持精准农业至关重要。然而，在受控叶片图像数据集上训练的深度学习模型，在真实农业条件下往往会出现性能下降，原因包括光照变化、背景杂乱、遮挡、叶片朝向以及成像噪声。为应对这些挑战，本研究开发了一个轻量级深度学习框架，用于稳健的玉米叶片病害分类和面向边缘的部署。该框架采用MobileNetV3-Small高效提取具有病害判别力的视觉特征，并研究轻量级特征学习策略，以提升在复杂田间条件下的分类性能。实验使用PlantVillage-Maize和Field-Maize数据集进行，共包含来自四个类别的6，188张图像：玉米大斑病（Maize Leaf Blight，MLB）、普通锈病（Common Rust）、健康（Healthy）和叶斑病（Leaf Spot）。仅使用图像的MobileNetV3-Small模型在受控的PlantVillage-Maize数据集上达到了97.8%的准确率和97.4%的F1分数，而在Field-Maize上的性能下降至86.1%的准确率和83.9%的F1分数，凸显了受控图像与真实田间图像之间的域差距。研究进一步在高斯噪声、光照变化和部分遮挡条件下评估了稳健性，并进行了计算效率和边缘部署分析。研究结果表明，轻量级且稳健的视觉特征学习对于真实农业成像条件下的实际玉米病害诊断具有重要意义。","International journal of intelligent engineering and systems",{"impact":17,"substance":100,"depth":101,"authority":17,"freshness":20,"relevant":21,"comment":385},"该研究提出轻量级玉米叶病检测框架，并揭示受控数据集与田间数据之间的性能差距，方法扎实、结论有参考价值，但属细分技术论文，公共影响有限。",[387],{"name":383,"url":380},[28,29,389,30,390],"边缘计算","玉米病害",{"code":392,"slug":393,"name":394,"path":395,"parent_code":396},"A3","maize","玉米","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[398],{"code":33,"slug":34,"name":35,"path":36,"parent_code":37},{"status":40,"locked":14,"version":41,"method":42,"evidence":400},{"candidates":401,"agricultural_evidence":46},[402,406,410,414],{"code":392,"score":19,"supported":46,"title":403,"abstract":404,"tags":405},[393],[394,393],[],{"code":33,"score":153,"supported":46,"title":407,"abstract":408,"tags":409},[],[30,51],[29,30],{"code":54,"score":118,"supported":46,"title":411,"abstract":412,"tags":413},[],[298,299],[28],{"code":415,"score":21,"supported":14,"title":416,"abstract":417,"tags":418},"I5",[],[],[389],[420,421],"MobileNetV3 玉米叶部病害","玉米叶片病害 边缘部署","MobileNetV3玉米叶部病害-5164","10.22266\u002Fijies2026.1130.50",{"doi":423,"openalex_id":425,"authors":426,"venue":383,"cited_by_count":76,"oa_url":380,"card":452,"direction":319,"ingested_from":84},"W7222602850",[427,430,433,435,437,440,442,444,447,449],{"name":428,"orcid":429},"Awwab Mohammad","https:\u002F\u002Forcid.org\u002F0000-0002-1148-5678",{"name":431,"orcid":432},"Punith kumar","https:\u002F\u002Forcid.org\u002F0009-0005-5676-4194",{"name":434,"orcid":9},"Bhavani K",{"name":436,"orcid":9},"Sailee N. Panchbhai",{"name":438,"orcid":439},"Sagarkumar S. Badhiye","https:\u002F\u002Forcid.org\u002F0000-0002-0710-3761",{"name":441,"orcid":9},"Manoj Kumar S B",{"name":443,"orcid":9},"Dharamvir",{"name":445,"orcid":446},"Sumit Kumar Sar","https:\u002F\u002Forcid.org\u002F0000-0003-0384-9088",{"name":448,"orcid":9},"Rani Chhagan Dalvi",{"name":450,"orcid":451},"Yogesh Harishchandra Bhosale","https:\u002F\u002Forcid.org\u002F0000-0001-6901-1419",{"tldr":453,"method":454,"finding":455,"direction":81,"opportunity":456},"构建轻量MobileNetV3-Small框架实现玉米叶片病害分类并评估边缘部署。","MobileNetV3-Small，PlantVillage-Maize与Fie","受控数据准确率97.8%，田间降至86.1%，揭示明显域差距。","可研究跨域自适应与田间鲁棒特征学习，缩小受控与真实场景性能差距。","2026-10-17T23:30:28.248539Z"]