[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2683":3,"related-2683":71},{"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":18,"tags":20,"primary_topic":9,"secondary_topics":24,"classification":25,"search_phrases":47,"slug":50,"view_count":51,"doi":52,"paper":53,"created_at":70},2683,"Efficient Monocular Depth Estimation on Embedded Systems with Neural Cellular Automata","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs42979-026-05327-4","Real-time monocular depth estimation is an essential task for autonomous drone navigation, yet existing models require hundreds of billions of floating-point operations per in-ference, rendering them impractical for deployment on resource-constrained embedded systems. On the MidAir aerial imagery dataset, a mean absolute error of 5.05 m is obtained with mea-sured CPU inference latency of 3.66 ms and 40,832 parameters—2.9–6.1× faster and 5.4–16.3× fewer parameters than com-parable lightweight convolutional neural network (CNN) base-lines (FastDepth, MiniDepth, RT-MonoDepth-S, MiDaS-Lite). A depth-augmented semantic segmentation variant performs simultaneous depth estimation and semantic segmentation in a single forward pass with approximately 59,000 parameters, enabling holistic computer vision for autonomous flight. Diverse image and video processing tasks are supported by the same design, providing a practical foundation for efficient real-time computer vision in edge computing applications.","实时单目深度估计是自主无人机导航的一项关键任务，然而现有模型每次推理需要数千亿次浮点运算，使其难以部署在资源受限的嵌入式系统上。在MidAir航空影像数据集上，该方法的平均绝对误差为5.05 m，实测CPU推理延迟为3.66 ms，参数量为40,832——相比同类轻量级卷积神经网络（CNN）基线（FastDepth、MiniDepth、RT-MonoDepth-S、MiDaS-Lite），推理速度快2.9–6.1倍，参数量少5.4–16.3倍。一种深度增强语义分割变体可在单次前向传播中同时完成深度估计与语义分割，参数量约为59,000，为自主飞行提供了整体计算机视觉能力。同一设计支持多种图像与视频处理任务，为边缘计算应用中高效的实时计算机视觉提供了实用基础。",null,"SN Computer Science","2026-09-15T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"面向嵌入式系统的单目深度估计方法论文，属通用计算机视觉与无人机导航技术，未涉及三农或农业信息化应用场景，相关性不足。",[19],{"name":10,"url":6},[21,22,23],"无人机","农业人工智能","边缘计算",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":29},"needs_review","2026-10-22.2","rules",{"candidates":30,"agricultural_evidence":14,"reason":46},[31,40],{"code":32,"score":33,"supported":34,"title":35,"abstract":36,"tags":39},"I2",7,true,[],[37,38],"计算机视觉","computer vision",[22],{"code":41,"score":33,"supported":34,"title":42,"abstract":43,"tags":45},"I5",[],[23,44],"edge computing",[23],"农业相关性需要复核",[48,49],"农业人工智能 边缘计算 无人机","农业人工智能 边缘计算","农业人工智能边缘计算无人机-2683",1,"10.1007\u002Fs42979-026-05327-4",{"doi":52,"openalex_id":54,"authors":55,"venue":10,"cited_by_count":15,"oa_url":61,"card":62,"direction":68,"ingested_from":69},"W7213322770",[56,58],{"name":57,"orcid":9},"Kurt Nunn",{"name":59,"orcid":60},"Tooraj Nikoubin","https:\u002F\u002Forcid.org\u002F0000-0003-1724-3503","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs42979-026-05327-4.pdf",{"tldr":63,"method":64,"finding":65,"direction":66,"opportunity":67},"提出基于神经细胞自动机的轻量单目深度估计模型，在嵌入式系统上实现实时推理。","神经细胞自动机，MidAir航拍数据集，CPU推理，参数量仅4万。","深度估计MAE 5.05米，推理3.66毫秒，比轻量CNN快2.9-6.1倍且参数少5.4-16.3","农业遥感与作物表型","可探索该轻量模型在无人机农业场景（如作物高度估计、避障）的迁移与精度-效率平衡。","农业人工智能与决策模型","openalex","2026-09-16T23:30:52.892539Z",{"total":72,"page":51,"page_size":72,"items":73},6,[74,138,222,295,371,451],{"id":75,"title":76,"url":77,"summary":78,"summary_zh":9,"content":9,"source_name":79,"source_url":9,"published_at":80,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":81,"score_detail":82,"sources":89,"tags":91,"primary_topic":95,"secondary_topics":101,"classification":102,"search_phrases":125,"slug":128,"view_count":15,"doi":9,"paper":129,"created_at":137},5533,"基于低成本遥操作机械臂模仿学习的草莓果柄定点采摘","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.22765","该研究构建视觉运动模仿学习流程，统一感知、运动规划与接触操作，从人工遥操作演示训练基于ResNet-50骨干的动作分块Transformer策略，并在Jetson AGX Orin边缘平台以15赫兹自主部署。策略在130条演示、十万梯度步内损失由2.84降至0.091，数据集与模型权重已开源。预印本，已被IROS农业机器人研讨会接收。","arXiv 预印本 2026-10-16","2026-10-16T00:00:00Z",68,{"impact":83,"substance":84,"depth":85,"authority":86,"freshness":87,"relevant":51,"comment":88},16,21,18,9,4,"方法新颖、数据与开源材料扎实，但属预印本且已过一周，适合作为细分技术进展收录而非头条精选。",[90],{"name":79,"url":77},[22,92,23,93,94],"农业机器人","模仿学习","草莓采摘",{"code":96,"slug":97,"name":98,"path":99,"parent_code":100},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[],{"status":103,"locked":14,"version":27,"method":28,"evidence":104},"classified",{"candidates":105,"agricultural_evidence":34},[106,112,117,121],{"code":96,"score":107,"supported":34,"title":108,"abstract":110,"tags":111},8,[109],"草莓",[],[],{"code":113,"score":87,"supported":34,"title":114,"abstract":115,"tags":116},"F6",[],[92],[92],{"code":32,"score":51,"supported":14,"title":118,"abstract":119,"tags":120},[],[],[22],{"code":41,"score":51,"supported":14,"title":122,"abstract":123,"tags":124},[],[],[23],[126,127],"草莓果柄 定点采摘 机械臂","Jetson AGX Orin 采摘 模仿学习","草莓果柄定点采摘机械臂-5533",{"doi":9,"openalex_id":9,"authors":130,"venue":9,"cited_by_count":15,"oa_url":9,"card":131,"direction":68,"ingested_from":136},[],{"tldr":132,"method":133,"finding":134,"direction":68,"opportunity":135},"用低成本遥操作机械臂采集演示，模仿学习实现草莓果柄定点采摘。","ResNet-50骨干的动作分块Transformer策略，Jetson边缘部署","130条演示训练后损失降至0.091，策略可15赫兹自主采摘。","可探索小样本跨品种泛化与失败恢复，降低演示采集成本。","agent","2026-10-22T00:07:09.891422Z",{"id":139,"title":140,"url":141,"summary":142,"summary_zh":143,"content":9,"source_name":144,"source_url":141,"published_at":145,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":146,"score_detail":147,"sources":151,"tags":153,"primary_topic":9,"secondary_topics":157,"classification":158,"search_phrases":192,"slug":195,"view_count":15,"doi":196,"paper":197,"created_at":221},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":85,"substance":148,"depth":85,"authority":149,"freshness":86,"relevant":51,"comment":150},22,14,"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。",[152],{"name":144,"url":141},[154,22,23,155,156],"智慧农业","盐胁迫监测","药用植物",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":159},{"candidates":160,"agricultural_evidence":34,"reason":191},[161,167,174,180,187],{"code":162,"score":33,"supported":34,"title":163,"abstract":164,"tags":166},"B6",[],[156,165],"medicinal plant",[156],{"code":168,"score":33,"supported":34,"title":169,"abstract":170,"tags":173},"I1",[],[171,172],"精准农业","precision agriculture",[154],{"code":32,"score":33,"supported":34,"title":175,"abstract":176,"tags":179},[],[177,178],"机器学习","machine learning",[22],{"code":181,"score":182,"supported":34,"title":183,"abstract":184,"tags":186},"H6",3,[],[185],"农业生态",[],{"code":41,"score":51,"supported":14,"title":188,"abstract":189,"tags":190},[],[],[23],"多个产业证据相当，需要确认主归属",[193,194],"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":196,"openalex_id":198,"authors":199,"venue":144,"cited_by_count":15,"oa_url":141,"card":215,"direction":68,"ingested_from":69},"W7222914402",[200,203,206,209,212],{"name":201,"orcid":202},"Ahmad Ali","https:\u002F\u002Forcid.org\u002F0000-0001-5530-7374",{"name":204,"orcid":205},"Vinie Lee Silva-Alvarado","https:\u002F\u002Forcid.org\u002F0009-0000-5857-3248",{"name":207,"orcid":208},"Arman Heydari","https:\u002F\u002Forcid.org\u002F0009-0002-4705-0729",{"name":210,"orcid":211},"Sandra Sendra","https:\u002F\u002Forcid.org\u002F0000-0001-9556-9088",{"name":213,"orcid":214},"Jaime Lloret","https:\u002F\u002Forcid.org\u002F0000-0002-0862-0533",{"tldr":216,"method":217,"finding":218,"direction":219,"opportunity":220},"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","智慧农业 \u002F 农业物联网","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。","2026-10-20T23:30:35.809539Z",{"id":223,"title":224,"url":225,"summary":226,"summary_zh":227,"content":9,"source_name":228,"source_url":225,"published_at":229,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":230,"score_detail":231,"sources":235,"tags":237,"primary_topic":240,"secondary_topics":245,"classification":246,"search_phrases":269,"slug":272,"view_count":15,"doi":273,"paper":274,"created_at":294},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":85,"substance":84,"depth":232,"authority":233,"freshness":107,"relevant":51,"comment":234},17,12,"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。",[236],{"name":228,"url":225},[154,22,23,238,239],"作物病害识别","苹果病害",{"code":241,"slug":242,"name":243,"path":244,"parent_code":100},"B2","fruit","果树","\u002Ftopic\u002Fhorticulture\u002Ffruit",[],{"status":103,"locked":14,"version":27,"method":28,"evidence":247},{"candidates":248,"agricultural_evidence":34},[249,255,259,263],{"code":241,"score":85,"supported":34,"title":250,"abstract":252,"tags":254},[251],"apple",[243,253,251],"苹果",[239],{"code":168,"score":33,"supported":34,"title":256,"abstract":257,"tags":258},[],[171,172],[154],{"code":41,"score":33,"supported":34,"title":260,"abstract":261,"tags":262},[],[23,44],[23],{"code":32,"score":264,"supported":34,"title":265,"abstract":266,"tags":268},5,[],[267],"artificial intelligence",[238,22],[270,271],"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":273,"openalex_id":275,"authors":276,"venue":228,"cited_by_count":15,"oa_url":225,"card":289,"direction":68,"ingested_from":69},"W7222964752",[277,280,283,286],{"name":278,"orcid":279},"Milan Grujev","https:\u002F\u002Forcid.org\u002F0009-0002-3211-6844",{"name":281,"orcid":282},"Dragan H. Stojanovic","https:\u002F\u002Forcid.org\u002F0000-0003-4893-3814",{"name":284,"orcid":285},"Miloš Ilić","https:\u002F\u002Forcid.org\u002F0000-0002-9696-2874",{"name":287,"orcid":288},"Aleksandar Milosavljević","https:\u002F\u002Forcid.org\u002F0000-0003-3057-7727",{"tldr":290,"method":291,"finding":292,"direction":219,"opportunity":293},"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",{"id":296,"title":297,"url":298,"summary":299,"summary_zh":300,"content":9,"source_name":301,"source_url":298,"published_at":302,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":303,"score_detail":304,"sources":307,"tags":309,"primary_topic":312,"secondary_topics":317,"classification":318,"search_phrases":346,"slug":349,"view_count":51,"doi":350,"paper":351,"created_at":370},5248,"An entropy-guided dynamic lightweight network for identification of wild edible vegetables of BTR","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs44163-026-02528-x","Wild edible vegetables of Bodoland Territorial Region (BTR) are the species of plants that grow naturally and are commonly consumed as food by the indigenous communities. These plants are important sources of nutritional and therapeutic properties and are essential for food security and socio-economic development of rural communities. Therefore, sustainable conservation and utilization of these unique plant resources are of great significance. Developing an efficient and accurate automatic identification system is an essential conservation strategy for them. Current plant identification methods are mainly based on classical machine learning (ML) methods and deep convolutional neural network (CNN) architectures for recognition and classification. These methods are effective for images taken under controlled or pristine conditions, but the performance is often far from ideal in the complex and natural environments of forest and grassland, where wild edible plants are found. This paper proposes an entropy-guided dynamic lightweight deep learning architecture for automatic detection of wild edible vegetables in BTR. The proposed model employs adaptive computation with Dynamic Kernel Selection (DKS), Region-wise Adaptive Feature Routing (RAFR), Ultra-Light Context Encoding (ULCE), and Entropy-Guided Global Pooling (EGGP) to capture multi-scale plant characteristics efficiently and reduce redundant computations. The novelty of our proposed framework lies in its coordinated integration of these modules that is designed to reduce computational overhead without compromising with performance. Experimental results show that the proposed model achieves excellent classification accuracy of 90.69% with significantly reduced parameter complexity and floating-point operations (FLOPs), which is well-suited for real-time precision agriculture and low-resource edge deployment applications.","博多兰领土区域（BTR）的野生食用蔬菜是自然生长并被土著社区普遍作为食物食用的植物物种。这些植物是营养和治疗特性的重要来源，对农村社区的粮食安全和社会经济发展至关重要。因此，对这些独特植物资源的可持续保护和利用具有重要意义。开发高效准确的自动识别系统是保护这些植物资源的重要策略。当前的植物识别方法主要基于经典机器学习（ML）方法和深度卷积神经网络（CNN）架构进行识别和分类。这些方法对于在受控或原始条件下拍摄的图像是有效的，但在野生食用植物所处的森林和草地复杂自然环境中，其性能往往远不理想。本文提出了一种熵引导的动态轻量级深度学习架构，用于自动检测BTR中的野生食用蔬菜。所提出的模型采用动态核选择（DKS）、区域自适应特征路由（RAFR）、超轻量上下文编码（ULCE）和熵引导全局池化（EGGP）的自适应计算，以高效捕捉多尺度植物特征并减少冗余计算。我们所提出框架的新颖性在于这些模块的协同集成，旨在在不影响性能的情况下降低计算开销。实验结果表明，所提出的模型达到了90.69%的优异分类准确率，同时显著降低了参数复杂度和浮点运算量（FLOPs），非常适合实时精准农业和低资源边缘部署应用。","Discover Artificial Intelligence","2026-10-17T00:00:00Z",70,{"impact":233,"substance":305,"depth":232,"authority":233,"freshness":86,"relevant":51,"comment":306},20,"提出熵引导动态轻量网络用于野生食用蔬菜识别，准确率90.69%且参数与算力显著降低，方法有新意、结论可靠，但属细分应用研究，公共影响有限。",[308],{"name":301,"url":298},[154,22,23,310,311],"野生蔬菜","植物识别",{"code":32,"slug":313,"name":314,"path":315,"parent_code":316},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":103,"locked":14,"version":27,"method":28,"evidence":319},{"candidates":320,"agricultural_evidence":34},[321,327,331,338,342],{"code":32,"score":13,"supported":34,"title":322,"abstract":323,"tags":326},[],[324,177,178,325],"深度学习","deep learning",[22],{"code":168,"score":33,"supported":34,"title":328,"abstract":329,"tags":330},[],[171,172],[154],{"code":332,"score":72,"supported":34,"title":333,"abstract":334,"tags":337},"A8",[],[335,336],"粮食安全","food security",[],{"code":96,"score":182,"supported":34,"title":339,"abstract":340,"tags":341},[],[98],[],{"code":41,"score":51,"supported":14,"title":343,"abstract":344,"tags":345},[],[],[23],[347,348],"BTR 野生食用蔬菜 识别","熵引导 轻量网络 植物识别","BTR野生食用蔬菜识别-5248","10.1007\u002Fs44163-026-02528-x",{"doi":350,"openalex_id":352,"authors":353,"venue":301,"cited_by_count":15,"oa_url":298,"card":365,"direction":68,"ingested_from":69},"W7222842686",[354,356,359,362],{"name":355,"orcid":9},"Tania Sarkar",{"name":357,"orcid":358},"Pranav Kumar Singh","https:\u002F\u002Forcid.org\u002F0000-0001-8987-0229",{"name":360,"orcid":361},"Parag Bhuyan","https:\u002F\u002Forcid.org\u002F0009-0006-4430-1851",{"name":363,"orcid":364},"Anshuman Kalla","https:\u002F\u002Forcid.org\u002F0000-0002-3985-4578",{"tldr":366,"method":367,"finding":368,"direction":68,"opportunity":369},"提出熵引导动态轻量网络，用于识别BTR野生食用蔬菜。","动态核选择、区域自适应特征路由、超轻上下文编码与熵引导池化。","分类准确率达90.69%，参数量和FLOPs显著降低，适合边缘部署。","可探索复杂自然场景下轻量模型在低资源边缘设备的实时植物识别与保护应用。","2026-10-18T23:30:58.805321Z",{"id":372,"title":373,"url":374,"summary":375,"summary_zh":376,"content":9,"source_name":377,"source_url":374,"published_at":80,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":378,"score_detail":379,"sources":381,"tags":383,"primary_topic":385,"secondary_topics":391,"classification":393,"search_phrases":412,"slug":415,"view_count":51,"doi":416,"paper":417,"created_at":450},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",69,{"impact":233,"substance":305,"depth":83,"authority":233,"freshness":86,"relevant":51,"comment":380},"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。",[382],{"name":377,"url":374},[154,22,23,324,384],"玉米病害",{"code":386,"slug":387,"name":388,"path":389,"parent_code":390},"A3","maize","玉米","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[392],{"code":32,"slug":313,"name":314,"path":315,"parent_code":316},{"status":103,"locked":14,"version":27,"method":28,"evidence":394},{"candidates":395,"agricultural_evidence":34},[396,400,404,408],{"code":386,"score":149,"supported":34,"title":397,"abstract":398,"tags":399},[387],[388,387],[],{"code":32,"score":107,"supported":34,"title":401,"abstract":402,"tags":403},[],[324,325],[22,324],{"code":168,"score":33,"supported":34,"title":405,"abstract":406,"tags":407},[],[171,172],[154],{"code":41,"score":51,"supported":14,"title":409,"abstract":410,"tags":411},[],[],[23],[413,414],"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":416,"openalex_id":418,"authors":419,"venue":377,"cited_by_count":15,"oa_url":374,"card":445,"direction":66,"ingested_from":69},"W7222602850",[420,423,426,428,430,433,435,437,440,442],{"name":421,"orcid":422},"Awwab Mohammad","https:\u002F\u002Forcid.org\u002F0000-0002-1148-5678",{"name":424,"orcid":425},"Punith kumar","https:\u002F\u002Forcid.org\u002F0009-0005-5676-4194",{"name":427,"orcid":9},"Bhavani K",{"name":429,"orcid":9},"Sailee N. Panchbhai",{"name":431,"orcid":432},"Sagarkumar S. Badhiye","https:\u002F\u002Forcid.org\u002F0000-0002-0710-3761",{"name":434,"orcid":9},"Manoj Kumar S B",{"name":436,"orcid":9},"Dharamvir",{"name":438,"orcid":439},"Sumit Kumar Sar","https:\u002F\u002Forcid.org\u002F0000-0003-0384-9088",{"name":441,"orcid":9},"Rani Chhagan Dalvi",{"name":443,"orcid":444},"Yogesh Harishchandra Bhosale","https:\u002F\u002Forcid.org\u002F0000-0001-6901-1419",{"tldr":446,"method":447,"finding":448,"direction":68,"opportunity":449},"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",{"id":452,"title":453,"url":454,"summary":455,"summary_zh":9,"content":9,"source_name":456,"source_url":9,"published_at":457,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":458,"score_detail":459,"sources":462,"tags":464,"primary_topic":467,"secondary_topics":468,"classification":469,"search_phrases":489,"slug":492,"view_count":15,"doi":9,"paper":493,"created_at":500},5130,"DefoliationCAM:面向葡萄藤食叶严重度实时评估的边缘AI系统 [预印本]","https:\u002F\u002Farxiv.org\u002Fabs\u002F2610.20879","Fuchen Li等提出DefoliationCAM(D-CAM),一种太阳能供电的边缘AI系统,用于估算葡萄藤树冠食叶程度并通过LoRa将结果传输至Web仪表盘。流水线使用YOLOX-Nano在4K图像中定位葡萄藤主干,并使用基于MobileNet的轻量级通道注意力分类器对320×320像素的斑块进行分类。29,674个田间采集斑块被标注为背景或四种损伤等级之一;合并中度和重度类别将类别不平衡比从约40:1降至8.8:1。合成增强使macro-F1从0.768提升至0.838。分类器以更少的参数量(1.08M vs 23.52M)在macro-F1上优于ResNet-50。利用TensorRT FP16在NVIDIA Jetson Orin Nano上每张4K图像处理时间约1.5秒,完整运行周期57-60秒。两台设备为期五周的田间部署验证了自主太阳能运行、LoRa通信和远程食叶监测的可行性。","arXiv 2610.20879 2026 年 10 月 14 日","2026-10-14T00:00:00Z",75,{"impact":83,"substance":148,"depth":85,"authority":460,"freshness":107,"relevant":51,"comment":461},11,"预印本提出太阳能边缘AI系统，实现葡萄藤食叶严重度实时评估与LoRa远程监测，方法新颖、数据规模大、田间验证充分，具智慧农业应用价值。",[463],{"name":456,"url":454},[154,22,23,465,466],"葡萄藤","病害评估",{"code":241,"slug":242,"name":243,"path":244,"parent_code":100},[],{"status":103,"locked":14,"version":27,"method":28,"evidence":470},{"candidates":471,"agricultural_evidence":34},[472,477,481,485],{"code":241,"score":460,"supported":34,"title":473,"abstract":475,"tags":476},[474],"葡萄",[474],[],{"code":168,"score":51,"supported":14,"title":478,"abstract":479,"tags":480},[],[],[154],{"code":32,"score":51,"supported":14,"title":482,"abstract":483,"tags":484},[],[],[22],{"code":41,"score":51,"supported":14,"title":486,"abstract":487,"tags":488},[],[],[23],[490,491],"DefoliationCAM 葡萄藤 食叶","Jetson Orin Nano 边缘AI 葡萄","DefoliationCAM葡萄藤食叶-5130",{"doi":9,"openalex_id":9,"authors":494,"venue":9,"cited_by_count":15,"oa_url":9,"card":495,"direction":219,"ingested_from":136},[],{"tldr":496,"method":497,"finding":498,"direction":219,"opportunity":499},"提出太阳能边缘AI系统DefoliationCAM，实时评估葡萄藤食叶严重度并远程传输。","YOLOX-Nano定位主干，MobileNet通道注意力分类，TensorRT","轻量分类器macro-F1达0.838，优于ResNet-50，田间部署验证可行。","可探索多作物迁移、损伤等级细化及边缘模型自适应更新以提升泛化性。","2026-10-17T00:13:44.932340Z"]