[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-237":3,"related-237":48},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"primary_topic":8,"secondary_topics":33,"classification":34,"search_phrases":42,"slug":45,"view_count":46,"doi":8,"paper":8,"created_at":47},237,"大尺寸水果内部品质无损检测及智能分选装备荣获美国匹兹堡国际发明展金奖——广东省农科院设施所徐赛团队","https:\u002F\u002Fwww.gdaas.cn\u002Fkxyjn\u002Fkyjz\u002Fcontent\u002Fpost_1334163.html","第2026届美国匹兹堡国际发明展(INPEX)在美国宾夕法尼亚州匹兹堡市圆满落幕。由广东省农业科学院设施所徐赛研究员、陆华忠教授、梁鑫实验师牵头研发的大尺寸水果内部品质无损检测技术及智能分选装备发明成果,从全球众多参展项目中脱颖而出获得金奖,是继第51届瑞士日内瓦国际发明展(IEIG)银奖后的又一荣誉。该研究聚焦柚子、菠萝等华南优势大尺寸水果内部品质无损检测领域难点,基于可见\u002F近红外光谱、机器视觉、称重传感等多源信息智能传感技术,自主研发实现大尺寸水果糖度、含水率、可食率、内部缺陷等关键品质指标的快速、无损、精准检测与智能化分级,有效解决了大尺寸水果难以准确无损智能分选的产业痛点,为岭南特色水果采后商品化处理提供科技支撑。",null,"近日，全球公认三大发明展之一的第2026届美国匹兹堡国际发明展（INPEX）在美国宾夕法尼亚州匹兹堡市圆满落幕。由我院设施所徐赛研究员、陆华忠教授、梁鑫实验师牵头研发的“大尺寸水果内部品质无损检测技术及智能分选装备（Nondestructive Detection Technology and Intelligent Sorting Equipment for Internal Quality of Large-sized Fruits）”发明成果，从全球众多参展项目中脱颖而出，获得金奖，是继第51届瑞士日内瓦国际发明展（IEIG）银奖的又一荣誉，标志着我院设施所在水果品质无损检测与智能分选技术领域的创新能力获得国际认可。\n\n该研究聚焦柚子、菠萝等华南优势大尺寸水果内部品质无损检测的领域难点，基于可见\u002F近红外光谱、机器视觉、称重传感等多源信息智能传感技术，自主研发实现了大尺寸水果糖度、含水率、可食率、内部缺陷等关键品质指标的快速、无损、精准检测与智能化分级，有效解决了大尺寸水果难以准确无损智能分选的产业痛点，为岭南特色水果采后商品化处理提供了有力的科技支撑。","广东省农业科学院 2026-08-03","2026-08-03T00:00:00Z","报道",10,false,72,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},20,18,14,12,8,1,"省级农科院团队获国际发明展金奖，聚焦大尺寸水果无损检测与智能分选，技术有突破性，但影响范围偏省级，信息增量中等。",[25],{"name":10,"url":6},[27,28,29,30,31,32],"广东省农科院","无损检测","智能分选","匹兹堡发明展","金奖","设施所",[],{"status":35,"locked":14,"version":36,"method":37,"evidence":38},"unclassified","2026-10-22.2","rules",{"candidates":39,"agricultural_evidence":40,"reason":41},[],true,"缺少足够的主题证据",[43,44],"匹兹堡发明展 广东省农科院 无损检测 智能分选","匹兹堡发明展 广东省农科院","匹兹堡发明展广东省农科院无损检测智能分选-237",7,"2026-08-05T23:53:01.279095Z",{"total":49,"page":22,"page_size":49,"items":50},6,[51,77,200,274,365,422],{"id":52,"title":53,"url":54,"summary":55,"summary_zh":8,"content":56,"source_name":57,"source_url":8,"published_at":58,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":59,"score_detail":60,"sources":64,"tags":66,"primary_topic":8,"secondary_topics":68,"classification":69,"search_phrases":72,"slug":75,"view_count":49,"doi":8,"paper":8,"created_at":76},459,"广东农科院'大尺寸水果内部品质无损检测技术'获美国匹兹堡国际发明展金奖——徐赛团队填补行业空白","https:\u002F\u002Fwww.nfnews.com\u002Fcontent\u002FY3MpX0eky1.html","第2026届美国匹兹堡国际发明展(INPEX)在美国宾夕法尼亚州匹兹堡市圆满落幕,广东省农业科学院设施农业研究所研发的'大尺寸水果内部品质无损检测技术及智能分选装备'发明成果获金奖。柚子、菠萝等华南特色水果果形大、果皮厚,内部品质难以通过肉眼判断。徐赛研究员、陆华忠教授、梁鑫实验师牵头研发,基于可见\u002F近红外光谱、机器视觉、称重传感等多源信息智能传感技术,实现了一系列创新突破,成功解决了大尺寸水果透射光谱信号弱的行业共性难题,自主研发形成了流水线式与便携式无损检测与智能分选装备,可实现糖度、含水率、可食率、内部缺陷等关键品质指标的快速、无损、精准检测与智能化分级。","近日，第2026届美国匹兹堡国际发明展（INPEX）在美国宾夕法尼亚州匹兹堡市圆满落幕。广东省农业科学院设施农业研究所（以下简称“设施所”）研发的“大尺寸水果内部品质无损检测技术及智能分选装备（Nondestructive Detection Technology and Intelligent Sorting Equipment for Internal Quality of Large-sized Fruits）”发明成果，从全球众多参展项目中脱颖而出，获得金奖。\n\n美国匹兹堡国际发明展创办于1986年，与瑞士日内瓦国际发明展、德国纽伦堡国际发明展并称全球公认的三大发明展，此次获奖成果由设施所研究员徐赛、院教授陆华忠、设施所实验师梁鑫牵头研发。\n\n据徐赛介绍，柚子、菠萝等华南特色水果果形大、果皮厚，内部品质难以通过肉眼判断。长期以来，大尺寸水果的内部关键品质指标缺乏快速精准的无损检测手段，采后分选主要依赖人工经验，效率低、误判率高，严重制约了华南特色水果的商品化发展。\n\n“面对这一产业难题，我们团队经过多年技术攻关。”徐赛说，基于可见\u002F近红外光谱、机器视觉、称重传感等多源信息智能传感技术，实现了一系列创新突破，成功解决了大尺寸水果透射光谱信号弱的行业共性难题，自主研发形成了流水线式与便携式无损检测与智能分选装备，可实现糖度、含水率、可食率、内部缺陷等关键品质指标的快速、无损、精准检测与智能化分级。\n\n此次获奖标志着设施所在水果品质无损检测与智能分选技术领域的创新能力已跻身国际前沿。该成果已在中国、美国等地取得发明专利、软著等知识产权，牵头制定并发布多项标准，为行业标准化发展提供了重要技术规范。\n\n目前，该技术成果形成的装备已在广东梅州、湛江等主产区示范推广，有效推动了产业向品质精准分级销售转型升级。\n\n“此次荣获国际金奖，是设施所多年来坚持自主创新、聚焦产业需求的重要成果体现。”设施所所长张长远表示，下一步，设施所将继续围绕设施农业智能化、精准化发展方向，加强关键核心技术攻关，加速科技成果转化应用，为广东乡村振兴、建设农业强省贡献更多科技力量。","南方日报 2026-08-08","2026-08-08T00:00:00Z",71,{"impact":61,"substance":18,"depth":19,"authority":62,"freshness":49,"relevant":22,"comment":63},22,11,"省级农业科研机构在国际发明展获奖，技术填补行业空白并已示范推广，具有产业价值，但报道偏通稿，深度一般。",[65],{"name":57,"url":54},[27,28,29,67],"国际金奖",[],{"status":35,"locked":14,"version":36,"method":37,"evidence":70},{"candidates":71,"agricultural_evidence":40,"reason":41},[],[73,74],"广东省农科院 国际金奖 无损检测 智能分选","广东省农科院 国际金奖","广东省农科院国际金奖无损检测智能分选-459","2026-08-12T23:57:23.006317Z",{"id":78,"title":79,"url":80,"summary":81,"summary_zh":82,"content":8,"source_name":83,"source_url":80,"published_at":84,"category":85,"cover_url":8,"hotness":13,"is_selected":14,"score":86,"score_detail":87,"sources":91,"tags":93,"primary_topic":98,"secondary_topics":104,"classification":110,"search_phrases":170,"slug":173,"view_count":174,"doi":175,"paper":176,"created_at":199},5582,"AI-Based RGB Imaging and 14-Channel Multispectral Food Quality Scanner","https:\u002F\u002Fdoi.org\u002F10.22214\u002Fijraset.2026.85255","Food-quality assessment plays an important role in food safety, agricultural processing, storage, and supply-chain management. Conventional inspection methods depend on visual judgement or laboratory-based testing, which may require considerable time, specialised equipment, and manual effort. Recent developments in computer vision, multispectral sensing, and artificial intelligence (AI) provide opportunities for automated, non-destructive food-quality assessment. This paper reviews the application of RGB imaging, multispectral sensing, machine learning, and deep learning for fruit-ripeness estimation, surfacedefect detection, grain classification, and food-authenticity assessment. The reviewed literature demonstrates that RGB imaging can extract visible features such as colour, shape, and texture, whereas multispectral sensing provides wavelength-dependent information associated with food characteristics. Published studies have reported promising results in tomato-ripeness classification, apple-defect detection, rice-grain analysis, and honey-adulteration screening. Based on these findings, a compact food-quality scanner integrating an RGB camera, a 14-channel multispectral sensor, controlled illumination, and an embedded processing unit is proposed. The review discusses sensor integration, data preprocessing, feature fusion, classification methods, evaluation metrics, and implementation challenges. It also identifies the need for broader datasets, standardised illumination, independent validation, and resource-efficient AI models to improve the reliability of portable food-inspection systems.","食品质量评估在食品安全、农产品加工、储运和供应链管理中发挥着重要作用。传统检测方法依赖人工目视判断或实验室检测，往往需要较长时间、专用设备和人工投入。近年来，计算机视觉、多光谱传感和人工智能（AI）的发展为自动化、无损食品质量评估提供了新的机遇。本文综述了RGB成像、多光谱传感、机器学习和深度学习在果实成熟度估计、表面缺陷检测、谷物分类和食品真实性评估中的应用。所综述的文献表明，RGB成像能够提取颜色、形状和纹理等可见特征，而多光谱传感则可提供与食品特性相关的波长依赖信息。已发表研究在番茄成熟度分类、苹果缺陷检测、稻米籽粒分析和蜂蜜掺假筛查等方面取得了良好结果。基于上述研究结果，本文提出一种集成了RGB相机、14通道多光谱传感器、受控照明和嵌入式处理单元的紧凑型食品质量扫描仪。综述讨论了传感器集成、数据预处理、特征融合、分类方法、评价指标和实现挑战，并指出需要更广泛的数据集、标准化照明、独立验证和资源高效的AI模型，以提高便携式食品检测系统的可靠性。","International Journal for Research in Applied Science and Engineering Technology","2026-10-21T00:00:00Z","论文",65,{"impact":20,"substance":18,"depth":88,"authority":89,"freshness":13,"relevant":22,"comment":90},16,9,"综述性论文，提出集成RGB与14通道多光谱的便携食品质量扫描仪方案，方法框架清晰但缺乏自有实验数据，属细分领域技术进展，可作参考但非重大突破。",[92],{"name":83,"url":80},[94,95,28,96,97],"智慧农业","农业人工智能","多光谱成像","食品质量检测",{"code":99,"slug":100,"name":101,"path":102,"parent_code":103},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing","I",[105],{"code":106,"slug":107,"name":108,"path":109,"parent_code":103},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai",{"status":111,"locked":14,"version":36,"method":37,"evidence":112},"classified",{"candidates":113,"agricultural_evidence":40},[114,119,130,137,144,151,158,165],{"code":99,"score":20,"supported":40,"title":115,"abstract":117,"tags":118},[116],"multispectral",[116],[96],{"code":106,"score":13,"supported":40,"title":120,"abstract":121,"tags":129},[],[122,123,124,125,126,127,128],"深度学习","机器学习","计算机视觉","machine learning","deep learning","artificial intelligence","computer vision",[95],{"code":131,"score":46,"supported":40,"title":132,"abstract":133,"tags":136},"E4",[],[134,135],"食品安全","food safety",[28],{"code":138,"score":49,"supported":40,"title":139,"abstract":140,"tags":143},"A1",[],[141,142],"稻米","rice",[],{"code":145,"score":49,"supported":40,"title":146,"abstract":147,"tags":150},"B1",[],[148,149],"番茄","tomato",[],{"code":152,"score":49,"supported":40,"title":153,"abstract":154,"tags":157},"B2",[],[155,156],"苹果","apple",[],{"code":159,"score":160,"supported":40,"title":161,"abstract":162,"tags":164},"E1",3,[],[163],"农产品加工",[],{"code":166,"score":22,"supported":14,"title":167,"abstract":168,"tags":169},"I1",[],[],[94],[171,172],"RGB成像 多光谱 食品质量","14通道 多光谱 扫描仪","RGB成像多光谱食品质量-5582",0,"10.22214\u002Fijraset.2026.85255",{"doi":175,"openalex_id":177,"authors":178,"venue":83,"cited_by_count":174,"oa_url":80,"card":191,"direction":197,"ingested_from":198},"W7223139905",[179,181,183,185,187,189],{"name":180,"orcid":8},"Eshwari Take",{"name":182,"orcid":8},"Avanish Raut",{"name":184,"orcid":8},"Vedant Joshi",{"name":186,"orcid":8},"Shravani Akolkar",{"name":188,"orcid":8},"R. M. Gharat",{"name":190,"orcid":8},"Shruti Dive",{"tldr":192,"method":193,"finding":194,"direction":195,"opportunity":196},"综述RGB与多光谱成像结合AI的食品品质无损检测，并提出一款集成14通道多光谱传感器的紧凑型扫描仪方","综述RGB成像、多光谱传感与机器学习\u002F深度学习在食品检测中的应用，并提出传感器集","RGB与多光谱融合在番茄成熟度、苹果缺陷、稻米分类和蜂蜜掺假检测中表现良好。","农业人工智能与决策模型","可研究多源光谱特征融合与轻量化模型，构建标准化数据集和便携设备独立验证体系。","数字乡村与农业信息化","openalex","2026-10-22T11:20:48.684398Z",{"id":201,"title":202,"url":203,"summary":204,"summary_zh":205,"content":8,"source_name":206,"source_url":203,"published_at":207,"category":85,"cover_url":8,"hotness":208,"is_selected":14,"score":209,"score_detail":210,"sources":214,"tags":218,"primary_topic":222,"secondary_topics":228,"classification":229,"search_phrases":257,"slug":260,"view_count":174,"doi":261,"paper":262,"created_at":273},5398,"Correlation Analysis of Banana Leaf Colour and Texture Features with Chemically Determined Nutrient Concentrations","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23470857","Correlation Analysis of Banana Leaf Colour and Texture Features with Chemically Determined Nutrient Concentrations examines the relationship between measurable colour and texture characteristics of banana leaves and their chemically determined nutrient concentrations. The study uses digital image processing to extract leaf features, including RGB colour values, colour intensity, texture patterns, and related statistical parameters. These image-based measurements are compared with laboratory-based nutrient analysis to identify significant correlations between optical features and nutrient levels. The research aims to determine whether leaf colour and texture can serve as reliable indicators of plant nutritional status. This approach may support the development of non-destructive, cost-effective, and efficient techniques for monitoring banana plant health. The findings can contribute to precision agriculture, improved nutrient management, and the advancement of image-based methods for crop assessment and agricultural research.","香蕉叶片颜色和纹理特征与化学测定养分浓度的相关性分析探讨了香蕉叶片可测量的颜色和纹理特征与其化学测定养分浓度之间的关系。该研究利用数字图像处理提取叶片特征，包括RGB颜色值、颜色强度、纹理模式及相关统计参数。将这些基于图像的测量结果与实验室养分分析进行比较，以识别光学特征与养分水平之间的显著相关性。该研究旨在确定叶片颜色和纹理能否作为植物营养状况的可靠指标。该方法可能有助于开发无损、经济高效且高效的香蕉植株健康监测技术。研究结果可为精准农业、改进养分管理以及推进基于图像的作物评估和农业研究方法作出贡献。","International Journal of Emerging Technologies and Innovative Research","2026-10-19T00:00:00Z",25,50,{"impact":21,"substance":88,"depth":211,"authority":212,"freshness":89,"relevant":22,"comment":213},13,4,"该研究探索用叶片颜色与纹理图像无损判断香蕉营养状况，思路有价值，但期刊权威性低、样本规模未明，暂不宜进入每日精选。",[215,216],{"name":206,"url":203},{"name":206,"url":217},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23471101",[94,28,219,220,221],"图像识别","香蕉","营养诊断",{"code":223,"slug":224,"name":225,"path":226,"parent_code":227},"F3","fertilizers","肥料与水肥一体化","\u002Ftopic\u002Finputs-equipment\u002Ffertilizers","F",[],{"status":111,"locked":14,"version":36,"method":37,"evidence":230},{"candidates":231,"agricultural_evidence":40},[232,238,243,249,253],{"code":166,"score":46,"supported":40,"title":233,"abstract":234,"tags":237},[],[235,236],"精准农业","precision agriculture",[94],{"code":223,"score":160,"supported":40,"title":239,"abstract":240,"tags":242},[],[241],"养分管理",[],{"code":244,"score":160,"supported":40,"title":245,"abstract":246,"tags":248},"I7",[],[247],"研究方法",[],{"code":152,"score":22,"supported":14,"title":250,"abstract":251,"tags":252},[],[],[220],{"code":106,"score":22,"supported":14,"title":254,"abstract":255,"tags":256},[],[],[219],[258,259],"香蕉叶片 营养浓度 图像特征","图像识别 无损检测 智慧农业 营养诊断","香蕉叶片营养浓度图像特征-5398","10.5281\u002Fzenodo.23470857",{"doi":261,"openalex_id":263,"authors":264,"venue":206,"cited_by_count":174,"oa_url":203,"card":267,"direction":197,"ingested_from":198},"W7222963764",[265],{"name":266,"orcid":8},"Anantjit Publication",{"tldr":268,"method":269,"finding":270,"direction":271,"opportunity":272},"分析香蕉叶片颜色与纹理特征同化学测定养分浓度的相关性。","数字图像处理提取RGB、颜色强度与纹理参数，与实验室养分分析对比。","叶片光学特征与养分水平存在显著相关，可作营养状态指标。","农业遥感与作物表型","可扩展到多作物、多生育期及高光谱纹理融合的养分无损诊断模型构建。","2026-10-20T23:30:23.713550Z",{"id":275,"title":276,"url":277,"summary":278,"summary_zh":279,"content":8,"source_name":280,"source_url":277,"published_at":281,"category":85,"cover_url":8,"hotness":13,"is_selected":14,"score":282,"score_detail":283,"sources":285,"tags":287,"primary_topic":291,"secondary_topics":292,"classification":293,"search_phrases":317,"slug":320,"view_count":174,"doi":321,"paper":322,"created_at":364},4892,"RGB-Derived Haralick Edge-Texture Features Discriminate Mung Bean Responses to Mineral and Biofertilizer Regimes","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagronomy16202026","Low-cost RGB imaging can accelerate crop phenotyping, but its ability to capture plant responses to fertilizer regimes through edge-based texture descriptors remains insufficiently tested. Mung bean [Vigna radiata (L.) R. Wilczek] was grown in a randomized complete block design with six fertilizer regimes and four replicates. Side-view RGB images acquired under controlled conditions were segmented, converted to grayscale, transformed into Canny edge maps, and summarized using six gray-level co-occurrence matrix (GLCM) features. Agronomic variables were evaluated: plant height, stem diameter, nodule weight, fresh weight, pod weight, shoot dry matter, grain yield per plot, the chlorophyll index, root length, and root volume. Contrast, energy, homogeneity, entropy, and variance differed across regimes, whereas the GLCM correlation did not. Mineral fertilization resulted in the highest values of stem diameter, nodule mass, fresh biomass, shoot dry matter, and the chlorophyll index. Baker’s Gamma coefficient (0.9369) and the cophenetic correlation (0.9498) showed high similarity between the hierarchical structures, indicating that the texture descriptors preserved a treatment organization highly similar to that observed for the agronomic variables. The Haralick features calculated from controlled RGB-derived edge maps revealed fertilizer-associated differences in the mung bean canopy structure. This method is promising for nondestructive screening, but replicate-level predictive validation, full reporting of image-processing parameters, and external testing are needed before agronomic traits can be estimated from images.","低成本RGB成像可加速作物表型分析，但其通过基于边缘的纹理描述符捕捉植物对施肥制度响应的能力仍缺乏充分验证。绿豆[Vigna radiata (L.) R. Wilczek]采用随机完全区组设计种植，设6个施肥处理，4次重复。在受控条件下获取的侧视RGB图像经分割、转换为灰度图、转化为Canny边缘图，并利用6个灰度共生矩阵(GLCM)特征进行汇总。评估的农艺指标包括：株高、茎粗、根瘤重、鲜重、荚重、地上部干物质、每小区籽粒产量、叶绿素指数、根长和根体积。对比度、能量、同质性、熵和方差在不同施肥处理间存在差异，而GLCM相关性则无显著差异。矿质施肥处理下茎粗、根瘤质量、鲜生物量、地上部干物质和叶绿素指数均最高。Baker's Gamma系数(0.9369)和共表型相关系数(0.9498)表明层次结构之间高度相似，说明纹理描述符所保留的处理组织结构与农艺变量所观察到的结构高度一致。由受控RGB衍生边缘图计算的Haralick特征揭示了绿豆冠层结构中与施肥相关的差异。该方法在无损筛选中具有前景，但在能够从图像估算农艺性状之前，仍需进行重复水平的预测验证、图像处理参数的完整报告以及外部测试。","Agronomy","2026-10-13T00:00:00Z",66,{"impact":21,"substance":17,"depth":88,"authority":211,"freshness":89,"relevant":22,"comment":284},"低成本RGB边缘纹理特征用于绿豆施肥响应的无损表型筛选，方法新颖但尚需重复级预测验证，属细分领域方法学进展。",[286],{"name":280,"url":277},[94,288,28,289,290],"绿豆","作物表型","RGB成像",{"code":223,"slug":224,"name":225,"path":226,"parent_code":227},[],{"status":111,"locked":14,"version":36,"method":37,"evidence":294},{"candidates":295,"agricultural_evidence":40},[296,303,308,313],{"code":223,"score":89,"supported":40,"title":297,"abstract":298,"tags":302},[],[299,300,301],"施肥","fertilizer","fertilization",[],{"code":99,"score":46,"supported":40,"title":304,"abstract":305,"tags":307},[],[289,306],"crop phenotyping",[289],{"code":309,"score":22,"supported":14,"title":310,"abstract":311,"tags":312},"A5",[],[],[288],{"code":166,"score":22,"supported":14,"title":314,"abstract":315,"tags":316},[],[],[94],[318,319],"绿豆 施肥 表型","RGB图像 纹理特征 作物","绿豆施肥表型-4892","10.3390\u002Fagronomy16202026",{"doi":321,"openalex_id":323,"authors":324,"venue":280,"cited_by_count":174,"oa_url":277,"card":359,"direction":271,"ingested_from":198},"W7221615335",[325,328,331,334,337,340,343,346,349,352,354,356],{"name":326,"orcid":327},"Eder Pereira Neves","https:\u002F\u002Forcid.org\u002F0000-0001-9645-7061",{"name":329,"orcid":330},"Jorge González Aguilera","https:\u002F\u002Forcid.org\u002F0000-0002-7308-0967",{"name":332,"orcid":333},"Werverth Costa Martins","https:\u002F\u002Forcid.org\u002F0000-0002-2813-4276",{"name":335,"orcid":336},"Roseline da Silva Coêlho","https:\u002F\u002Forcid.org\u002F0000-0002-4412-7471",{"name":338,"orcid":339},"Fábio Steiner","https:\u002F\u002Forcid.org\u002F0000-0001-9091-1737",{"name":341,"orcid":342},"Marco Aparecido Queiroz Duarte","https:\u002F\u002Forcid.org\u002F0000-0003-2494-448X",{"name":344,"orcid":345},"Alan Mário Zuffo","https:\u002F\u002Forcid.org\u002F0000-0001-9704-5325",{"name":347,"orcid":348},"César Augusto Masgo Soto","https:\u002F\u002Forcid.org\u002F0000-0003-0720-0833",{"name":350,"orcid":351},"Carlos Genaro Morales Aranibar","https:\u002F\u002Forcid.org\u002F0000-0002-4184-2365",{"name":353,"orcid":8},"María Paulina Aliaga Martínez",{"name":355,"orcid":8},"Nataniel Linares-Gutiérrez",{"name":357,"orcid":358},"Luis Fortunato Morales Aranibar","https:\u002F\u002Forcid.org\u002F0000-0002-9421-9833",{"tldr":360,"method":361,"finding":362,"direction":271,"opportunity":363},"用RGB图像Canny边缘图的Haralick纹理特征区分绿豆对不同施肥处理的响应。","侧视RGB图像分割、灰度化、Canny边缘检测与GLCM六特征，结合农艺性状聚类","对比度、能量、同质性、熵和方差随施肥制度显著差异，纹理与农艺变量层次结构高度相似。","可探索边缘纹理特征与具体农艺性状的定量预测模型，并开展重复级验证与跨品种外部测试。","2026-10-14T23:30:20.148045Z",{"id":366,"title":367,"url":368,"summary":369,"summary_zh":370,"content":8,"source_name":371,"source_url":368,"published_at":372,"category":85,"cover_url":8,"hotness":13,"is_selected":14,"score":373,"score_detail":374,"sources":377,"tags":379,"primary_topic":8,"secondary_topics":381,"classification":382,"search_phrases":400,"slug":403,"view_count":404,"doi":405,"paper":406,"created_at":421},4448,"Machine Learning for Ripeness Classification of Nendra Bale Banana: A Classical Approach Using SVM, kNN, and Random Forest","https:\u002F\u002Fdoi.org\u002F10.64388\u002Firev10i4-1723730","acceptance, and overall shelf life. Nendra Bale (Nendran), a dual-purpose, starch-rich Indian banana cultivar widely used for both table consumption and cooking, exhibits a ripening pattern that is markedly more texture-driven than colour-driven, distinguishing it from commercially dominant, colour-dominant cultivars. This study introduces an image-based framework for classifying the ripening stage of Nendra Bale bananas using classical machine learning. A first-hand dataset of 80 raw images across four ripening stages (Green, Mid-ripe, All-Yellow, Overripe) was collected under everyday mobile-camera conditions and augmented to 5,391 images to support more robust model training. Three classical classifiers (Support Vector Machine, k-Nearest Neighbours, Random Forest) were evaluated on Histogram of Oriented Gradients (HOG) features under both raw and augmented conditions. On the raw dataset, kNN gave the highest accuracy (76.47%), ahead of SVM and Random Forest (70.59% each); once the dataset was augmented, SVM became the strongest and most consistent model (81.60%), ahead of kNN (78.62%) and Random Forest (74.53%). A probabilistic stage-to-shelf-life mapping is proposed to convert predictions into an expected remaining life in days. The study offers a low-cost, non-destructive, deployable approach for quality assessment and post-harvest decision support for a texture-dominant, dual-purpose Indian banana cultivar.","接受度以及整体货架期。Nendra Bale（Nendran）是一种兼具鲜食与烹饪用途、富含淀粉的印度香蕉品种，其成熟模式明显更多由质地驱动而非颜色驱动，这使其区别于商业上占主导地位、以颜色为主导的品种。本研究提出了一种基于图像的框架，利用经典机器学习对Nendra Bale香蕉的成熟阶段进行分类。研究在日常手机拍摄条件下收集了涵盖四个成熟阶段（青绿、半熟、全黄、过熟）的80张原始图像一手数据集，并扩充至5,391张图像以支持更稳健的模型训练。在原始和扩充条件下，基于方向梯度直方图（HOG）特征对三种经典分类器（支持向量机、k近邻、随机森林）进行了评估。在原始数据集上，kNN取得了最高准确率（76.47%），高于SVM和随机森林（均为70.59%）；数据集扩充后，SVM成为最强且最一致的模型（81.60%），高于kNN（78.62%）和随机森林（74.53%）。研究提出了一种概率性的阶段至货架期映射方法，将预测结果转换为以天为单位的预期剩余寿命。本研究为一种质地主导、兼具双重用途的印度香蕉品种提供了一种低成本、非破坏性、可部署的品质评估与采后决策支持方法。","Iconic Research and Engineering Journals","2026-10-06T00:00:00Z",55,{"impact":21,"substance":18,"depth":375,"authority":49,"freshness":21,"relevant":22,"comment":376},15,"面向印度特色香蕉品种的经典机器学习成熟度分级研究，方法常规、数据规模有限，但无损检测与采后决策支持思路对农业信息化有参考价值。",[378],{"name":371,"url":368},[94,95,28,220,380],"采后分级",[],{"status":383,"locked":14,"version":36,"method":37,"evidence":384},"needs_review",{"candidates":385,"agricultural_evidence":14,"reason":399},[386,391,395],{"code":106,"score":18,"supported":40,"title":387,"abstract":388,"tags":390},[125],[123,125,389],"decision support",[95],{"code":152,"score":22,"supported":14,"title":392,"abstract":393,"tags":394},[],[],[220],{"code":166,"score":22,"supported":14,"title":396,"abstract":397,"tags":398},[],[],[94],"农业相关性需要复核",[401,402],"Nendra Bale 香蕉 成熟度 分类","香蕉 成熟度 机器学习 SVM","NendraBale香蕉成熟度分类-4448",2,"10.64388\u002Firev10i4-1723730",{"doi":405,"openalex_id":407,"authors":408,"venue":371,"cited_by_count":174,"oa_url":415,"card":416,"direction":195,"ingested_from":198},"W7220687470",[409,412],{"name":410,"orcid":411},"T. N. Manasa","https:\u002F\u002Forcid.org\u002F0009-0004-1163-2182",{"name":413,"orcid":414},"M Pushpalatha","https:\u002F\u002Forcid.org\u002F0000-0003-3637-9836","https:\u002F\u002Fwww.irejournals.com\u002Fformatedpaper\u002F1723730.pdf",{"tldr":417,"method":418,"finding":419,"direction":195,"opportunity":420},"用HOG特征和经典机器学习对Nendra Bale香蕉四个成熟阶段进行图像分类。","80张原始图像增强至5391张，提取HOG特征，比较SVM、kNN、随机森林。","增强后SVM最优达81.60%，并建立成熟阶段到货架期的概率映射。","可探索纹理主导型品种的深度学习与多模态融合，提升成熟度识别和货架期预测精度。","2026-10-08T23:30:52.769987Z",{"id":423,"title":424,"url":425,"summary":426,"summary_zh":427,"content":8,"source_name":428,"source_url":425,"published_at":429,"category":85,"cover_url":8,"hotness":13,"is_selected":14,"score":430,"score_detail":431,"sources":434,"tags":436,"primary_topic":8,"secondary_topics":439,"classification":440,"search_phrases":456,"slug":459,"view_count":46,"doi":460,"paper":461,"created_at":492},3133,"Dual-representation fusion of near-infrared spectra for simultaneous identification of fresh-cocoon sex and imprinted-dead cocoons during pupal metamorphosis","https:\u002F\u002Fdoi.org\u002F10.1016\u002Fj.compag.2026.112431","Automated identification of fresh-cocoon sex and imprinted-dead cocoons is essential for raw silk quality control and requires an efficient and reliable approach. Although near-infrared (NIR) spectroscopy shows potential, sex-identification performance across pupal metamorphosis remains insufficiently understood, and existing modeling approaches remain underdeveloped. This study developed a dual-representation weighted-fusion network for fresh-cocoon sex and imprinted-dead cocoon identification during pupal metamorphosis. The network comprises two ablation-optimized branches: a 1D-CNN incorporating dilated spatial attention, adaptive coordinate attention, and ConvNeXtV2 blocks for spectral-sequence feature extraction, and a 2D-CNN incorporating shuffle attention network, adaptive coordinate attention, and ResNet blocks for recurrence-plot-based structural feature extraction. The spectral-sequence and recurrence-plot branches capture complementary information that is integrated using an adaptive weighted-fusion strategy, with the optimized branch parameters used as pretrained weights for transfer learning. On the held-out test set, the dual-representation weighted-fusion network achieved the highest overall accuracy of 95.39%, outperforming the optimized 1D-CNN (93.55%) and 2D-CNN (94.59%), with an average per-sample network inference time of 0.921 ms. Sex-identification performance varied with pupal metamorphosis, showing generally lower and more variable accuracy during the early period, improved performance during the middle period, and some decline during the late period. The fusion network maintained high accuracy across the three periods and achieved its highest mean sex-identification accuracy of 97.22% during the middle period (days 5–7). Overall, the proposed dual-representation NIR framework provides a promising approach for non-destructive fresh-cocoon sex identification and imprinted-dead cocoon screening, while highlighting the pupal developmental period as an important consideration for practical sex sorting.","鲜茧性别与印痕死茧的自动化识别对生丝质量控制至关重要，需要一种高效可靠的方法。尽管近红外（NIR）光谱显示出潜力，但蛹期变态过程中的性别识别性能仍未得到充分理解，现有建模方法也尚不成熟。本研究开发了一种双表示加权融合网络，用于蛹期变态过程中鲜茧性别和印痕死茧的识别。该网络包含两个经消融优化的分支：一个一维CNN分支，融合了膨胀空间注意力、自适应坐标注意力和ConvNeXtV2模块，用于光谱序列特征提取；以及一个二维CNN分支，融合了混洗注意力网络、自适应坐标注意力和ResNet模块，用于基于递归图的结构特征提取。光谱序列分支和递归图分支捕获互补信息，通过自适应加权融合策略进行整合，并将优化后的分支参数用作迁移学习的预训练权重。在留出测试集上，双表示加权融合网络达到了95.39%的最高总体准确率，优于优化后的一维CNN（93.55%）和二维CNN（94.59%），平均单样本网络推理时间为0.921 ms。性别识别性能随蛹期变态而变化，早期准确率普遍较低且波动较大，中期性能提升，晚期有所下降。融合网络在三个时期均保持较高准确率，并在中期（第5–7天）达到了97.22%的最高平均性别识别准确率。总体而言，所提出的双表示近红外框架为非破坏性鲜茧性别识别和印痕死茧筛查提供了一种有前景的方法，同时凸显了蛹发育时期作为实际性别分选的重要考虑因素。","Computers and Electronics in Agriculture","2026-09-21T00:00:00Z",82,{"impact":18,"substance":61,"depth":432,"authority":19,"freshness":89,"relevant":22,"comment":433},19,"该研究提出双表征加权融合近红外光谱网络，实现鲜茧性别与印痕死茧的高精度无损识别，方法新颖、数据可靠，对蚕桑智能化分选具有实用价值。",[435],{"name":428,"url":425},[94,95,28,437,438],"蚕桑产业","近红外光谱",[],{"status":383,"locked":14,"version":36,"method":37,"evidence":441},{"candidates":442,"agricultural_evidence":14,"reason":399},[443,448,452],{"code":444,"score":22,"supported":14,"title":445,"abstract":446,"tags":447},"A6",[],[],[437],{"code":166,"score":22,"supported":14,"title":449,"abstract":450,"tags":451},[],[],[94],{"code":106,"score":22,"supported":14,"title":453,"abstract":454,"tags":455},[],[],[95],[457,458],"近红外光谱 蚕茧 雌雄鉴别","鲜茧 性别识别 无损检测","近红外光谱蚕茧雌雄鉴别-3133","10.1016\u002Fj.compag.2026.112431",{"doi":460,"openalex_id":462,"authors":463,"venue":428,"cited_by_count":174,"oa_url":425,"card":487,"direction":195,"ingested_from":198},"W7213904433",[464,467,469,471,473,475,477,480,482,485],{"name":465,"orcid":466},"Haibo He","https:\u002F\u002Forcid.org\u002F0000-0002-5247-9370",{"name":468,"orcid":8},"Bing Lu",{"name":470,"orcid":8},"Mingqing Zhong",{"name":472,"orcid":8},"Wantong Xie",{"name":474,"orcid":8},"Yong Chen",{"name":476,"orcid":8},"Zongmeng Yang",{"name":478,"orcid":479},"Hua Huang","https:\u002F\u002Forcid.org\u002F0000-0002-2817-2950",{"name":481,"orcid":8},"Xiaoling Tong",{"name":483,"orcid":484},"Tianfu Zhao","https:\u002F\u002Forcid.org\u002F0000-0001-8189-7638",{"name":486,"orcid":8},"Shiping Zhu",{"tldr":488,"method":489,"finding":490,"direction":195,"opportunity":491},"提出双表征加权融合近红外光谱网络，同时识别鲜茧性别与印痕死茧。","1D-CNN与2D-CNN双分支，结合注意力、递归图与迁移学习。","融合网络总体准确率95.39%，中期性别识别最高达97.22%。","可探索蛹期动态建模与轻量化边缘部署，提升实际分选鲁棒性。","2026-09-22T23:30:02.331612Z"]