[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-3487":3,"related-3487":85},{"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":41,"slug":44,"view_count":45,"doi":46,"paper":47,"created_at":84},3487,"Enhanced YOLOv8-seg-SPDConv for accurate Schatzker classification of tibial plateau fractures","https:\u002F\u002Fdoi.org\u002F10.3389\u002Ffmed.2026.1843762","Background Tibial plateau fractures are typically caused by direct or indirect violent forces, often resulting in collapse fractures of the medial or lateral tibial plateau. Accurate diagnosis and classification of tibial plateau fractures are of significant importance for determining appropriate treatment plans. However, manual Schatzker classification is subject to considerable inter-observer variability, particularly among junior physicians and non-specialist clinicians, often resulting in suboptimal accuracy and prolonged decision-making time in high-throughput emergency settings. Objective This study aimed to develop and validate a lightweight YOLOv8n-seg-SPDConv model for the joint instance segmentation and Schatzker classification of tibial plateau fractures using thin-slice axial CT images from 552 unique patients. Specifically, by integrating the Space-to-Depth Convolution (SPDConv) module, we sought to preserve sub-2 mm cortical disruptions while reducing model complexity and suggesting potential for future deployment on resource-constrained platforms. Using a hold-out test set benchmarked against a senior orthopedic surgeon's consensus standard, we systematically evaluated the model's diagnostic performance, inference efficiency (226 FPS), and interpretability via Gradient-weighted Class Activation Mapping (Grad-CAM), with the ultimate goal of serving as a reliable real-time clinical adjunct that supports, rather than supplants, clinicians in emergency and perioperative decision-making. Methods From October 2017 to January 2026, a dataset comprising 552 axial CT slices from unique patients was collected. Each image was independently annotated into six clinically relevant categories according to the Schatzker classification. To prevent data leakage, dataset partitioning was strictly performed prior to augmentation using an 8:2 patient-wise split. The YOLOv8n-seg network was employed for joint segmentation and classification, with multiple preprocessing techniques applied to ensure data consistency and enhance model performance. Results The baseline YOLOv8n-seg achieved mAP50 values of 0.941, 0.956, 0.861, 0.818, 0.916, and 0.869 for Schatzker types I–VI, respectively. The improved YOLOv8n-seg-SPDConv yielded mAP50 of 0.928, 0.952, 0.929, 0.859, 0.925, and 0.893 for the six subtypes, with an overall mAP50 increasing from 0.893 to 0.914. Notably, the proposed model reduced parameters from 3.01 M to 2.64 M and FLOPs from 8.1 G to 7.3 G, while increasing inference speed from 188 to 226 FPS, meeting real-time requirements for edge deployment. Grad-CAM visualization confirmed that the model focused its attention on clinically meaningful regions, including fracture fissures and articular depressions, rather than background artifacts. Discussion This deep learning-based classification method provides efficient and reliable automated assessments to assist and augment manual evaluation by clinicians, with the potential to help reduce interobserver variability among junior physicians during emergency and perioperative decision-making. It shows promise as a tool that may help mitigate interobserver variability and support junior physicians in emergency and primary care settings. While marginal performance variations were observed in simple linear fractures, the model achieved substantial gains in complex, low-contrast subtypes. These findings highlight its value as a complementary clinical decision support tool, with the potential to support and streamline diagnostic workflows rather than replace expert judgment, ultimately contributing to improved patient outcomes.","背景 胫骨平台骨折通常由直接或间接暴力所致，常导致内侧或外侧胫骨平台塌陷骨折。胫骨平台骨折的准确诊断与分型对于确定合适的治疗方案具有重要意义。然而，人工Schatzker分型存在较大的观察者间差异，尤其在低年资医师和非专科临床医生中更为明显，常导致在高通量急诊环境下准确率欠佳且决策时间延长。目的 本研究旨在开发并验证一种轻量级YOLOv8n-seg-SPDConv模型，利用552例独特患者的薄层轴位CT图像，对胫骨平台骨折进行联合实例分割与Schatzker分型。具体而言，通过整合空间到深度卷积（SPDConv）模块，我们力求在保留亚2 mm皮质中断的同时降低模型复杂度，并为其未来在资源受限平台上的部署提供可能。使用以资深骨科外科医生共识标准为基准的留出测试集，我们系统评估了模型的诊断性能、推理效率（226 FPS）以及通过梯度加权类激活映射（Grad-CAM）实现的可解释性，最终目标是将其作为一种可靠的实时临床辅助工具，在急诊和围手术期决策中支持而非取代临床医生。方法 自2017年10月至2026年1月，收集了包含552例独特患者轴位CT切片的 dataset。每张图像均根据Schatzker分型独立标注为六个临床相关类别。为防止数据泄漏，数据集划分严格在增强之前进行，采用8：2的患者层面拆分。采用YOLOv8n-seg网络进行联合分割与分类，并应用多种预处理技术以确保数据一致性并提升模型性能。结果 基线YOLOv8n-seg对Schatzker I–VI型的mAP50分别为0.941、0.956、0.861、0.818、0.916和0.869。改进后的YOLOv8n-seg-SPDConv对六个亚型的mAP50分别为0.928、0.952、0.929、0.859、0.925和0.893，总体mAP50从0.893提升至0.914。值得注意的是，所提出的模型将参数量从3.01 M降至2.64 M，FLOPs从8.1 G降至7.3 G，同时增",null,"Frontiers in Medicine","2026-09-22T00:00:00Z","论文",10,false,0,{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":17},"属医学影像AI研究，与三农、农业信息化、智慧农业主题无关，不予入选。",[19],{"name":10,"url":6},[21,22,23],"深度学习","医学影像","骨折分型",[],{"status":26,"locked":14,"version":27,"method":28,"evidence":29},"needs_review","2026-10-22.2","rules",{"candidates":30,"agricultural_evidence":14,"reason":40},[31],{"code":32,"score":33,"supported":34,"title":35,"abstract":36,"tags":39},"I2",7,true,[],[37,38],"deep learning","decision support",[21],"农业相关性需要复核",[42,43],"YOLOv8-seg-SPDConv 胫骨平台骨折","Schatzker 分型 深度学习","YOLOv8-seg-SPDConv胫骨平台骨折-3487",3,"10.3389\u002Ffmed.2026.1843762",{"doi":46,"openalex_id":48,"authors":49,"venue":10,"cited_by_count":15,"oa_url":75,"card":76,"direction":82,"ingested_from":83},"W7213974124",[50,52,54,56,58,60,62,64,66,69,71,73],{"name":51,"orcid":9},"Haoteng Wang",{"name":53,"orcid":9},"Zhiheng Gao",{"name":55,"orcid":9},"Heting Xiao",{"name":57,"orcid":9},"Xuwei Ling",{"name":59,"orcid":9},"Haowen Lu",{"name":61,"orcid":9},"Yu Chen",{"name":63,"orcid":9},"Minbo Jian",{"name":65,"orcid":9},"Zheming Shen",{"name":67,"orcid":68},"Quan Zhou","https:\u002F\u002Forcid.org\u002F0000-0003-2376-7741",{"name":70,"orcid":9},"Peng Yang",{"name":72,"orcid":9},"Tao Liu",{"name":74,"orcid":9},"Yusen Qiao","https:\u002F\u002Fwww.frontiersin.org\u002Fjournals\u002Fmedicine\u002Farticles\u002F10.3389\u002Ffmed.2026.1843762\u002Fpdf",{"tldr":77,"method":78,"finding":79,"direction":80,"opportunity":81},"提出轻量YOLOv8n-seg-SPDConv模型，用CT图像实现胫骨平台骨折Schatzker分型","552例薄层轴位CT，YOLOv8n-seg加SPDConv模块，患者级8:2划","整体mAP50从0.893升至0.914，参数与FLOPs下降，推理达226 FPS。","农业人工智能与决策模型","该轻量分割-分类联合框架可迁移至农业图像细粒度分级任务，如作物病害或果实损伤分型。","农业遥感与作物表型","openalex","2026-09-25T23:30:22.979253Z",{"total":86,"page":87,"page_size":86,"items":88},6,1,[89,166,222,260,320,395],{"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":13,"is_selected":14,"score":97,"score_detail":98,"sources":104,"tags":106,"primary_topic":111,"secondary_topics":117,"classification":123,"search_phrases":145,"slug":148,"view_count":15,"doi":149,"paper":150,"created_at":165},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":99,"substance":100,"depth":101,"authority":13,"freshness":102,"relevant":87,"comment":103},12,18,16,8,"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。",[105],{"name":95,"url":92},[107,108,21,109,110],"智慧农业","农业人工智能","番茄病害","图像识别",{"code":112,"slug":113,"name":114,"path":115,"parent_code":116},"B1","vegetables","蔬菜","\u002Ftopic\u002Fhorticulture\u002Fvegetables","B",[118],{"code":32,"slug":119,"name":120,"path":121,"parent_code":122},"agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":124,"locked":14,"version":27,"method":28,"evidence":125},"classified",{"candidates":126,"agricultural_evidence":34},[127,134,139],{"code":112,"score":128,"supported":34,"title":129,"abstract":131,"tags":133},15,[130],"tomato",[132,130],"番茄",[109],{"code":32,"score":135,"supported":34,"title":136,"abstract":137,"tags":138},9,[],[21,37],[108,110,21],{"code":140,"score":33,"supported":34,"title":141,"abstract":142,"tags":144},"I1",[],[107,143],"smart agriculture",[107],[146,147],"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":149,"openalex_id":151,"authors":152,"venue":95,"cited_by_count":15,"oa_url":158,"card":159,"direction":164,"ingested_from":83},"W7222977034",[153,155],{"name":154,"orcid":9},"Mrs. Vijetalaxmi A Hegde",{"name":156,"orcid":157},"Abhay Ramakant Kasetwar","https:\u002F\u002Forcid.org\u002F0000-0002-5800-8764","https:\u002F\u002Factainnovations.com\u002Findex.php\u002Fpub\u002Farticle\u002Fdownload\u002F1918\u002F981",{"tldr":160,"method":161,"finding":162,"direction":80,"opportunity":163},"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。","智慧农业 \u002F 农业物联网","2026-10-20T23:30:10.424511Z",{"id":167,"title":168,"url":169,"summary":170,"summary_zh":171,"content":9,"source_name":172,"source_url":169,"published_at":96,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":173,"score_detail":174,"sources":176,"tags":178,"primary_topic":181,"secondary_topics":182,"classification":183,"search_phrases":208,"slug":211,"view_count":15,"doi":212,"paper":213,"created_at":221},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":102,"substance":100,"depth":101,"authority":86,"freshness":102,"relevant":87,"comment":175},"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。",[177],{"name":172,"url":169},[107,108,179,21,180],"计算机视觉","水果品质检测",{"code":32,"slug":119,"name":120,"path":121,"parent_code":122},[],{"status":124,"locked":14,"version":27,"method":28,"evidence":184},{"candidates":185,"agricultural_evidence":34},[186,196,202],{"code":32,"score":187,"supported":34,"title":188,"abstract":190,"tags":195},28,[37,189],"computer vision",[191,21,192,179,193,37,194,189],"目标检测","机器学习","machine learning","artificial intelligence",[108,21,179],{"code":140,"score":33,"supported":34,"title":197,"abstract":198,"tags":201},[],[199,200],"精准农业","precision agriculture",[107],{"code":203,"score":45,"supported":34,"title":204,"abstract":205,"tags":207},"B2",[],[206],"orchard",[],[209,210],"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":212,"openalex_id":214,"authors":215,"venue":172,"cited_by_count":15,"oa_url":169,"card":216,"direction":164,"ingested_from":83},"W7222892831",[],{"tldr":217,"method":218,"finding":219,"direction":82,"opportunity":220},"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。","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":223,"title":224,"url":225,"summary":226,"summary_zh":227,"content":9,"source_name":172,"source_url":225,"published_at":228,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":229,"sources":231,"tags":233,"primary_topic":9,"secondary_topics":234,"classification":235,"search_phrases":242,"slug":245,"view_count":15,"doi":246,"paper":247,"created_at":259},5242,"Enhanced Convolutional Neural Network Architecture with Attention-Guided Feature Refinement for Robust Image Classification","https:\u002F\u002Fdoi.org\u002F10.25258\u002Fijddt.16.88s.43","Image classification remains a foundational problem in computer vision, underpinning applications that range from medical diagnostics to autonomous navigation. Although deep convolutional neural networks (CNNs) have substantially advanced classification accuracy over the last decade, standard architectures such as VGG, ResNet, and plain CNNs often struggle to jointly optimize accuracy, parameter efficiency, and robustness to intra-class variation. This paper proposes an AttentionGuided Refinement Network (AGR-Net), a CNN architecture that integrates a lightweight channel-and-spatial attention module with residual feature refinement blocks to improve discriminative feature learning while maintaining a compact parameter footprint. The proposed model is evaluated on the CIFAR-10 benchmark dataset using a rigorous experimental protocol that includes data augmentation, learning-rate scheduling, and five-fold cross-validation. Comparative experiments against baseline architectures, including a plain CNN, VGG-16, ResNet-18, and MobileNetV2, demonstrate that AGR-Net achieves a top-1 accuracy of 94.6%, outperforming the strongest baseline by 1.8 percentage points while using 27% fewer parameters than ResNet-18. Ablation studies confirm that the attention module and refinement blocks each contribute measurably to the accuracy gain. The results indicate that attention-guided refinement offers a favorable trade-off between accuracy, efficiency, and robustness, making the proposed architecture suitable for deployment in resource-constrained and real-time image classification systems. The paper further discusses the advantages, practical applications, limitations, and future research directions of the proposed approach.","图像分类仍然是计算机视觉中的一个基础性问题，支撑着从医学诊断到自主导航等诸多应用。尽管深度卷积神经网络（CNN）在过去十年中大幅提升了分类准确率，但VGG、ResNet和普通CNN等标准架构往往难以在准确率、参数效率和对类内变化的鲁棒性之间实现联合优化。本文提出了一种注意力引导细化网络（AttentionGuided Refinement Network，AGR-Net），这是一种CNN架构，它将轻量级的通道与空间注意力模块与残差特征细化模块相结合，以改进判别性特征学习，同时保持紧凑的参数规模。所提出的模型在CIFAR-10基准数据集上使用严格的实验方案进行评估，该方案包括数据增强、学习率调度和五折交叉验证。与基线架构（包括普通CNN、VGG-16、ResNet-18和MobileNetV2）的对比实验表明，AGR-Net实现了94.6%的top-1准确率，比最强基线高出1.8个百分点，同时使用的参数比ResNet-18少27%。消融研究证实，注意力模块和细化模块各自对准确率提升都有可测量的贡献。结果表明，注意力引导细化在准确率、效率和鲁棒性之间提供了有利的权衡，使所提出的架构适合部署在资源受限和实时的图像分类系统中。本文进一步讨论了所提出方法的优势、实际应用、局限性和未来研究方向。","2026-10-17T00:00:00Z",{"impact":15,"substance":15,"depth":15,"authority":15,"freshness":15,"relevant":15,"comment":230},"该文为通用计算机视觉论文，未涉及农业场景，与三农及农业信息化无关，不宜入选。",[232],{"name":172,"url":225},[108,21,110],[],{"status":26,"locked":14,"version":27,"method":28,"evidence":236},{"candidates":237,"agricultural_evidence":14,"reason":40},[238],{"code":32,"score":135,"supported":34,"title":239,"abstract":240,"tags":241},[],[179,189],[108,110,21],[243,244],"农业人工智能 图像识别 深度学习","农业人工智能 图像识别","农业人工智能图像识别深度学习-5242","10.25258\u002Fijddt.16.88s.43",{"doi":246,"openalex_id":248,"authors":249,"venue":172,"cited_by_count":15,"oa_url":225,"card":254,"direction":164,"ingested_from":83},"W7222796569",[250,252],{"name":251,"orcid":9},"KRISHNA SANDEEP JONNALA",{"name":253,"orcid":9},"K VENKAT RAJU",{"tldr":255,"method":256,"finding":257,"direction":80,"opportunity":258},"提出注意力引导细化网络AGR-Net，在CIFAR-10上兼顾精度与参数效率。","轻量通道-空间注意力模块+残差特征细化块，五折交叉验证对比基线。","AGR-Net达94.6%准确率，超最强基线1.8个百分点且参数比ResNet-18少27%。","可将该轻量注意力架构迁移至作物病害识别等农业图像任务，验证田间复杂场景鲁棒性。","2026-10-18T23:30:13.674128Z",{"id":261,"title":262,"url":263,"summary":264,"summary_zh":265,"content":9,"source_name":266,"source_url":263,"published_at":228,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":267,"score_detail":268,"sources":271,"tags":273,"primary_topic":276,"secondary_topics":282,"classification":283,"search_phrases":300,"slug":303,"view_count":87,"doi":304,"paper":305,"created_at":319},5234,"A smart agriculture-oriented cross-attention multiscale CNN for sugarcane disease diagnosis","https:\u002F\u002Fdoi.org\u002F10.1080\u002F23080477.2026.2749739","Sugarcane leaf diseases can adversely affect crop health and yield, making timely disease identification important for smart agriculture. Manual inspection of leaf diseases is time-consuming and requires expert knowledge, particularly when large cultivation areas need to be monitored. To tackle this problem, this study proposes a Cross-Attention Multiscale Parallel Convolutional Neural Network for automatic classification of sugarcane leaf diseases. This framework comprises a Parallel Feature Extraction Stem, cross-attention mechanism, Dense Connection Blocks, and Inception Blocks to learn disease features at various spatial scales. The PFES extracts fine and broad disease patterns using parallel convolutional branches, while the cross-attention mechanism refines the extracted features by emphasizing disease-related information. The DCB supports feature propagation and reuse, and the IB further captures multi-scale feature representations. The proposed model was tested on two benchmark datasets of leaf diseases for sugarcane plants. The proposed framework obtained an accuracy (98.79%), precision (98.31%), recall (97.81%), specificity (98.60%), and F1-Score (98.05%). For assessing the classification accuracy and consistency of the framework, the comparative study, ablation studies, and five-fold cross-validation are carried out. The results show that CA-MPCNN provides accurate sugarcane leaf disease classification and can support automated disease diagnosis in smart agriculture applications.","甘蔗叶片病害会对作物健康与产量造成不利影响，因此及时识别病害对智慧农业具有重要意义。人工检查叶片病害耗时且需要专业知识，尤其是在需要监测大面积种植区域时。为解决该问题，本研究提出一种用于甘蔗叶片病害自动分类的交叉注意力多尺度并行卷积神经网络（Cross-Attention Multiscale Parallel Convolutional Neural Network）。该框架由并行特征提取主干（Parallel Feature Extraction Stem）、交叉注意力机制、密集连接块（Dense Connection Blocks）和Inception块组成，用于学习不同空间尺度上的病害特征。PFES通过并行卷积分支提取细粒度与广域病害模式，而交叉注意力机制通过强调病害相关信息对提取的特征进行细化。DCB支持特征传播与复用，IB进一步捕获多尺度特征表示。所提出的模型在两个甘蔗植株叶片病害基准数据集上进行了测试。该框架取得了准确率（98.79%）、精确率（98.31%）、召回率（97.81%）、特异性（98.60%）和F1分数（98.05%）。为评估该框架的分类准确性和一致性，开展了对比研究、消融研究和五折交叉验证。结果表明，CA-MPCNN能够实现准确的甘蔗叶片病害分类，并可支持智慧农业应用中的自动化病害诊断。","Smart Science",69,{"impact":99,"substance":269,"depth":101,"authority":99,"freshness":135,"relevant":87,"comment":270},20,"该研究提出一种面向甘蔗叶部病害自动分类的交叉注意力多尺度CNN，在两个基准数据集上准确率达98.79%，方法新颖、实验充分，但属于细分作物应用研究，产业影响有限，时效性强，值得进入每日精选。",[272],{"name":266,"url":263},[107,108,274,21,275],"甘蔗","病害诊断",{"code":277,"slug":278,"name":279,"path":280,"parent_code":281},"A6","cash-crops","棉麻糖与特色经作","\u002Ftopic\u002Ffield-crops\u002Fcash-crops","A",[],{"status":124,"locked":14,"version":27,"method":28,"evidence":284},{"candidates":285,"agricultural_evidence":34},[286,291,295],{"code":277,"score":128,"supported":34,"title":287,"abstract":289,"tags":290},[288],"sugarcane",[274,288],[274],{"code":140,"score":128,"supported":34,"title":292,"abstract":293,"tags":294},[143],[107,143],[107],{"code":32,"score":296,"supported":14,"title":297,"abstract":298,"tags":299},2,[],[],[108,21],[301,302],"甘蔗 叶部病害 智能诊断","CA-MPCNN 甘蔗 病害","甘蔗叶部病害智能诊断-5234","10.1080\u002F23080477.2026.2749739",{"doi":304,"openalex_id":306,"authors":307,"venue":266,"cited_by_count":15,"oa_url":9,"card":314,"direction":164,"ingested_from":83},"W7222832245",[308,310,312],{"name":309,"orcid":9},"Bala Subramanian Chokkalingam",{"name":311,"orcid":9},"Uvarani Meenrajan",{"name":313,"orcid":9},"Shanmugapriya Sankaran",{"tldr":315,"method":316,"finding":317,"direction":80,"opportunity":318},"提出交叉注意力多尺度并行CNN，实现甘蔗叶病自动分类。","并行卷积分支、交叉注意力、密集连接与Inception块，两个基准数据集验证。","模型准确率达98.79%，消融与五折交叉验证证明其有效稳定。","可探索田间复杂背景与轻量化部署，并扩展到多作物病害实时诊断。","2026-10-18T23:30:07.777036Z",{"id":321,"title":322,"url":323,"summary":324,"summary_zh":325,"content":9,"source_name":326,"source_url":323,"published_at":327,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":267,"score_detail":328,"sources":330,"tags":332,"primary_topic":335,"secondary_topics":340,"classification":342,"search_phrases":367,"slug":370,"view_count":87,"doi":371,"paper":372,"created_at":394},5165,"Proximal Remote Sensing of Oil Palm Basal Stem Rot Using Deep Learning Vision Algorithms and Ground-based Images","https:\u002F\u002Fdoi.org\u002F10.22266\u002Fijies2026.1130.31","Basal Stem Rot (BSR), caused by Ganoderma boninense, threatens oil palm productivity in Southeast Asia.This study develops and benchmarks a low-cost remote sensing framework for BSR severity diagnosis from smartphone-captured RGB trunk images, evaluating two pathways for future field deployment.The first pairs YOLO detection with a Random Forest classifier: YOLO26n gave the best accuracy-to-cost trade-off among three nanovariants for localizing BSR symptoms (mushroom, rot, white-button), and the end-to-end YOLO26n+RF pipeline achieved 0.83 accuracy and macro-F1 of 0.79 across Healthy, Mild, Moderate, and Severe classes.Rot was consistently the hardest symptom to localize, owing to its diffuse, boundary-ambiguous appearance.The second pathway trained four image classifiers (EfficientNet-B0, MobileNetV2, Swin-Tiny, and ConvNeXt-V2-Tiny) directly on severity labels, with ConvNeXt-V2-Tiny performing best (0.83 accuracy, 0.83 macro-F1).Both pathways performed well at severity extremes but struggled with Moderate, reflecting visual overlap between stages.SHAP analysis identified rot-area ratio and fruiting-body count as top predictors.These offline results show accurate BSR diagnosis is potentially achievable from smartphone imagery, laying groundwork for future on-device deployment.","由灵芝（Ganoderma boninense）引起的基茎腐病（Basal Stem Rot, BSR）威胁着东南亚油棕的生产力。本研究开发并基准测试了一个低成本遥感框架，用于从智能手机拍摄的RGB树干图像中诊断基茎腐病的严重程度，并评估了未来田间部署的两条技术路径。第一条路径将YOLO检测与随机森林分类器相结合：在三种纳米变体中，YOLO26n在定位基茎腐病症状（蘑菇、腐烂、白钮）方面实现了最佳的精度-成本权衡，端到端的YOLO26n+RF流程在健康、轻度、中度和重度四个类别上达到了0.83的准确率和0.79的宏F1值。腐烂始终是最难定位的症状，原因在于其弥散且边界模糊的外观。第二条路径直接在严重程度标签上训练了四个图像分类器（EfficientNet-B0、MobileNetV2、Swin-Tiny和ConvNeXt-V2-Tiny），其中ConvNeXt-V2-Tiny表现最佳（准确率0.83，宏F1值0.83）。两条路径在严重程度极端类别上表现良好，但在中度类别上表现欠佳，反映出各阶段之间存在视觉重叠。SHAP分析确定腐烂面积比和子实体数量为最重要的预测因子。这些离线结果表明，利用智能手机图像有望实现准确的基茎腐病诊断，为未来设备端部署奠定了基础。","International journal of intelligent engineering and systems","2026-10-16T00:00:00Z",{"impact":99,"substance":269,"depth":101,"authority":99,"freshness":135,"relevant":87,"comment":329},"该研究利用智能手机图像与深度学习实现油棕基腐病严重度诊断，方法新颖、结论可靠，但属细分作物研究，产业影响有限，适合作为技术类精选。",[331],{"name":326,"url":323},[107,333,21,334,275],"农业遥感","油棕",{"code":336,"slug":337,"name":338,"path":339,"parent_code":122},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",[341],{"code":32,"slug":119,"name":120,"path":121,"parent_code":122},{"status":124,"locked":14,"version":27,"method":28,"evidence":343},{"candidates":344,"agricultural_evidence":34},[345,351,356,363],{"code":336,"score":128,"supported":34,"title":346,"abstract":348,"tags":350},[347],"remote sensing",[349,347],"遥感",[333],{"code":32,"score":99,"supported":34,"title":352,"abstract":353,"tags":355},[37],[354],"YOLO",[21],{"code":357,"score":86,"supported":34,"title":358,"abstract":359,"tags":362},"B5",[],[360,361],"蘑菇","mushroom",[],{"code":140,"score":87,"supported":14,"title":364,"abstract":365,"tags":366},[],[],[107],[368,369],"油棕 基腐病 遥感","Ganoderma boninense 智能手机 检测","油棕基腐病遥感-5165","10.22266\u002Fijies2026.1130.31",{"doi":371,"openalex_id":373,"authors":374,"venue":326,"cited_by_count":15,"oa_url":323,"card":389,"direction":82,"ingested_from":83},"W7222626135",[375,378,381,383,386],{"name":376,"orcid":377},"Wan Siu Hong","https:\u002F\u002Forcid.org\u002F0000-0002-8254-4962",{"name":379,"orcid":380},"Jonathan Yong Chung Ee","https:\u002F\u002Forcid.org\u002F0000-0003-4079-8005",{"name":382,"orcid":9},"Jin Yuan Chan",{"name":384,"orcid":385},"Mohamad Izzuddin Anuar","https:\u002F\u002Forcid.org\u002F0000-0002-4929-5175",{"name":387,"orcid":388},"Mahmud Iwan Solihin","https:\u002F\u002Forcid.org\u002F0000-0002-5293-7466",{"tldr":390,"method":391,"finding":392,"direction":82,"opportunity":393},"用手机拍摄油棕树干图像，结合深度学习检测与分类，实现基腐病严重度诊断。","YOLO26n+随机森林与四种图像分类器，基于手机RGB图像，SHAP解释。","两条路径准确率均约0.83，中度病级最难区分，腐区比例与子实体数为关键预测因子。","可探索轻量化模型在手机端离线部署，并扩充多地区、多品种数据以提升中度病级辨识。","2026-10-17T23:30:28.307953Z",{"id":396,"title":397,"url":398,"summary":399,"summary_zh":400,"content":9,"source_name":326,"source_url":398,"published_at":327,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":267,"score_detail":401,"sources":403,"tags":405,"primary_topic":408,"secondary_topics":413,"classification":415,"search_phrases":436,"slug":439,"view_count":87,"doi":440,"paper":441,"created_at":474},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。",{"impact":99,"substance":269,"depth":101,"authority":99,"freshness":135,"relevant":87,"comment":402},"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。",[404],{"name":326,"url":398},[107,108,406,21,407],"边缘计算","玉米病害",{"code":409,"slug":410,"name":411,"path":412,"parent_code":281},"A3","maize","玉米","\u002Ftopic\u002Ffield-crops\u002Fmaize",[414],{"code":32,"slug":119,"name":120,"path":121,"parent_code":122},{"status":124,"locked":14,"version":27,"method":28,"evidence":416},{"candidates":417,"agricultural_evidence":34},[418,423,427,431],{"code":409,"score":419,"supported":34,"title":420,"abstract":421,"tags":422},14,[410],[411,410],[],{"code":32,"score":102,"supported":34,"title":424,"abstract":425,"tags":426},[],[21,37],[108,21],{"code":140,"score":33,"supported":34,"title":428,"abstract":429,"tags":430},[],[199,200],[107],{"code":432,"score":87,"supported":14,"title":433,"abstract":434,"tags":435},"I5",[],[],[406],[437,438],"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":440,"openalex_id":442,"authors":443,"venue":326,"cited_by_count":15,"oa_url":398,"card":469,"direction":82,"ingested_from":83},"W7222602850",[444,447,450,452,454,457,459,461,464,466],{"name":445,"orcid":446},"Awwab Mohammad","https:\u002F\u002Forcid.org\u002F0000-0002-1148-5678",{"name":448,"orcid":449},"Punith kumar","https:\u002F\u002Forcid.org\u002F0009-0005-5676-4194",{"name":451,"orcid":9},"Bhavani K",{"name":453,"orcid":9},"Sailee N. Panchbhai",{"name":455,"orcid":456},"Sagarkumar S. Badhiye","https:\u002F\u002Forcid.org\u002F0000-0002-0710-3761",{"name":458,"orcid":9},"Manoj Kumar S B",{"name":460,"orcid":9},"Dharamvir",{"name":462,"orcid":463},"Sumit Kumar Sar","https:\u002F\u002Forcid.org\u002F0000-0003-0384-9088",{"name":465,"orcid":9},"Rani Chhagan Dalvi",{"name":467,"orcid":468},"Yogesh Harishchandra Bhosale","https:\u002F\u002Forcid.org\u002F0000-0001-6901-1419",{"tldr":470,"method":471,"finding":472,"direction":80,"opportunity":473},"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"]