[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-5248":3,"related-5248":109},{"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":25,"primary_topic":31,"secondary_topics":37,"classification":38,"search_phrases":81,"slug":84,"view_count":21,"doi":85,"paper":86,"created_at":108},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。",null,"Discover Artificial Intelligence","2026-10-17T00:00:00Z","论文",10,false,70,{"impact":17,"substance":18,"depth":19,"authority":17,"freshness":20,"relevant":21,"comment":22},12,20,17,9,1,"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。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","边缘计算","野生蔬菜","植物识别",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",[],{"status":39,"locked":14,"version":40,"method":41,"evidence":42},"classified","2026-10-22.2","rules",{"candidates":43,"agricultural_evidence":45},[44,53,61,69,76],{"code":32,"score":13,"supported":45,"title":46,"abstract":47,"tags":52},true,[],[48,49,50,51],"深度学习","机器学习","machine learning","deep learning",[27],{"code":54,"score":55,"supported":45,"title":56,"abstract":57,"tags":60},"I1",7,[],[58,59],"精准农业","precision agriculture",[26],{"code":62,"score":63,"supported":45,"title":64,"abstract":65,"tags":68},"A8",6,[],[66,67],"粮食安全","food security",[],{"code":70,"score":71,"supported":45,"title":72,"abstract":73,"tags":75},"B1",3,[],[74],"蔬菜",[],{"code":77,"score":21,"supported":14,"title":78,"abstract":79,"tags":80},"I5",[],[],[28],[82,83],"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":85,"openalex_id":87,"authors":88,"venue":10,"cited_by_count":100,"oa_url":6,"card":101,"direction":105,"ingested_from":107},"W7222842686",[89,91,94,97],{"name":90,"orcid":9},"Tania Sarkar",{"name":92,"orcid":93},"Pranav Kumar Singh","https:\u002F\u002Forcid.org\u002F0000-0001-8987-0229",{"name":95,"orcid":96},"Parag Bhuyan","https:\u002F\u002Forcid.org\u002F0009-0006-4430-1851",{"name":98,"orcid":99},"Anshuman Kalla","https:\u002F\u002Forcid.org\u002F0000-0002-3985-4578",0,{"tldr":102,"method":103,"finding":104,"direction":105,"opportunity":106},"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。","农业人工智能与决策模型","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。","openalex","2026-10-18T23:30:58.805321Z",{"total":63,"page":21,"page_size":63,"items":110},[111,196,248,313,414,483],{"id":112,"title":113,"url":114,"summary":115,"summary_zh":116,"content":9,"source_name":117,"source_url":114,"published_at":118,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":119,"score_detail":120,"sources":123,"tags":125,"primary_topic":127,"secondary_topics":133,"classification":135,"search_phrases":156,"slug":159,"view_count":21,"doi":160,"paper":161,"created_at":195},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","2026-10-16T00:00:00Z",69,{"impact":17,"substance":18,"depth":121,"authority":17,"freshness":20,"relevant":21,"comment":122},16,"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。",[124],{"name":117,"url":114},[26,27,28,48,126],"玉米病害",{"code":128,"slug":129,"name":130,"path":131,"parent_code":132},"A3","maize","玉米","\u002Ftopic\u002Ffield-crops\u002Fmaize","A",[134],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":136},{"candidates":137,"agricultural_evidence":45},[138,143,148,152],{"code":128,"score":139,"supported":45,"title":140,"abstract":141,"tags":142},14,[129],[130,129],[],{"code":32,"score":144,"supported":45,"title":145,"abstract":146,"tags":147},8,[],[48,51],[27,48],{"code":54,"score":55,"supported":45,"title":149,"abstract":150,"tags":151},[],[58,59],[26],{"code":77,"score":21,"supported":14,"title":153,"abstract":154,"tags":155},[],[],[28],[157,158],"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":160,"openalex_id":162,"authors":163,"venue":117,"cited_by_count":100,"oa_url":114,"card":189,"direction":194,"ingested_from":107},"W7222602850",[164,167,170,172,174,177,179,181,184,186],{"name":165,"orcid":166},"Awwab Mohammad","https:\u002F\u002Forcid.org\u002F0000-0002-1148-5678",{"name":168,"orcid":169},"Punith kumar","https:\u002F\u002Forcid.org\u002F0009-0005-5676-4194",{"name":171,"orcid":9},"Bhavani K",{"name":173,"orcid":9},"Sailee N. Panchbhai",{"name":175,"orcid":176},"Sagarkumar S. Badhiye","https:\u002F\u002Forcid.org\u002F0000-0002-0710-3761",{"name":178,"orcid":9},"Manoj Kumar S B",{"name":180,"orcid":9},"Dharamvir",{"name":182,"orcid":183},"Sumit Kumar Sar","https:\u002F\u002Forcid.org\u002F0000-0003-0384-9088",{"name":185,"orcid":9},"Rani Chhagan Dalvi",{"name":187,"orcid":188},"Yogesh Harishchandra Bhosale","https:\u002F\u002Forcid.org\u002F0000-0001-6901-1419",{"tldr":190,"method":191,"finding":192,"direction":105,"opportunity":193},"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。","农业遥感与作物表型","2026-10-17T23:30:28.248539Z",{"id":197,"title":198,"url":199,"summary":200,"summary_zh":9,"content":9,"source_name":201,"source_url":9,"published_at":202,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":119,"score_detail":203,"sources":206,"tags":208,"primary_topic":211,"secondary_topics":212,"classification":213,"search_phrases":235,"slug":238,"view_count":100,"doi":9,"paper":239,"created_at":247},4967,"SADR-VSS:一种用于轻量级农业目标检测的场景自适应动态路由视觉状态空间模块","https:\u002F\u002Fwww.ebiotrade.com\u002Fnewsf\u002F2026-10\u002F20261013084746521.htm","本文提出场景自适应动态路由视觉状态空间模块SADR-VSS,用于复杂田间条件下的轻量级农业目标检测。该方法引入场景自适应路由机制,动态协调局部卷积表示和长距离状态空间建模,从而在异质农业场景中实现更灵活的特征提取。大量实验表明,SADR-VSS实现了改善的检测性能,验证了其在嵌入式设备和农业自动化平台上的部署潜力。研究面向自动除草平台的高分辨率图像,在YOLOv11n基线基础上展示更集中的目标激活响应。","生物通 2026 年 10 月 13 日","2026-10-13T00:00:00Z",{"impact":204,"substance":18,"depth":19,"authority":144,"freshness":20,"relevant":21,"comment":205},15,"提出场景自适应动态路由视觉状态空间模块，在YOLOv11n基线上提升复杂田间轻量检测性能，方法新颖且面向嵌入式除草平台，具备较强专业参考价值。",[207],{"name":201,"url":199},[26,27,28,209,210],"农业目标检测","智能除草",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":214},{"candidates":215,"agricultural_evidence":45},[216,221,227,231],{"code":32,"score":17,"supported":45,"title":217,"abstract":219,"tags":220},[218],"目标检测",[218],[27],{"code":222,"score":71,"supported":45,"title":223,"abstract":224,"tags":226},"F4",[],[225],"除草",[],{"code":54,"score":21,"supported":14,"title":228,"abstract":229,"tags":230},[],[],[26],{"code":77,"score":21,"supported":14,"title":232,"abstract":233,"tags":234},[],[],[28],[236,237],"SADR-VSS 农业目标检测","YOLOv11n 自动除草","SADR-VSS农业目标检测-4967",{"doi":9,"openalex_id":9,"authors":240,"venue":9,"cited_by_count":100,"oa_url":9,"card":241,"direction":105,"ingested_from":246},[],{"tldr":242,"method":243,"finding":244,"direction":105,"opportunity":245},"提出场景自适应动态路由视觉状态空间模块SADR-VSS，用于复杂田间轻量级农业目标检测。","结合局部卷积与长距离状态空间建模，基于YOLOv11n在自动除草高分辨率图像上验","SADR-VSS提升检测性能，目标激活更集中，具备嵌入式农业平台部署潜力。","可探索动态路由机制在更多作物与杂草场景的泛化性，及与边缘计算硬件的协同优化。","agent","2026-10-15T00:06:08.643930Z",{"id":249,"title":250,"url":251,"summary":252,"summary_zh":253,"content":9,"source_name":254,"source_url":251,"published_at":202,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":119,"score_detail":255,"sources":259,"tags":261,"primary_topic":264,"secondary_topics":265,"classification":266,"search_phrases":294,"slug":297,"view_count":298,"doi":299,"paper":300,"created_at":312},4798,"Adaptability of Lightweight AI Models for Embedded Deployment: A Case Study of an Agricultural Monitoring Robot","https:\u002F\u002Fdoi.org\u002F10.54254\u002F2755-2721\u002F2026.ld37676","Many artificial intelligence programs require powerful computing hardware, whereas agricultural robots, drones, and smart cameras rely on small embedded devices with limited computing power, battery capacity, and heat dissipation. Lightweight models reduce parameters and computational costs while maintaining acceptable accuracy, enabling AI deployment on resource-constraint network devices. This paper reviews key lightweighting methods, including compact network architectures, model pruning, model quantization, and knowledge distillation. It compares common platforms such as Jetson, Raspberry Pi, and microcontrollers. Using an agricultural monitoring robot as an example, this study proposes a system combining a camera, a lightweight YOLO model, Jetson, and a microcontroller for real-time crop monitoring. Experiments are designed to evaluate accuracy, speed, power consumption, temperature, and battery life. Rather than pursuing maximum model complexity, this paper focuses on explaining how to select a model that is truly suitable for the actual device. For agricultural robots, effective deployment requires sufficient accuracy, real-time performance, and low energy consumption.","许多人工智能程序需要强大的计算硬件，而农业机器人、无人机和智能摄像头则依赖于计算能力、电池容量和散热能力均有限的小型嵌入式设备。轻量级模型在保持可接受精度的同时减少参数和计算成本，使人工智能能够部署在资源受限的网络设备上。本文综述了关键的轻量化方法，包括紧凑网络架构、模型剪枝、模型量化和知识蒸馏。本文比较了Jetson、树莓派和微控制器等常见平台。以农业监测机器人为例，本研究提出了一种结合摄像头、轻量级YOLO模型、Jetson和微控制器的系统，用于实时作物监测。实验旨在评估精度、速度、功耗、温度和电池寿命。本文并非追求最大化的模型复杂度，而是着重解释如何选择真正适合实际设备的模型。对于农业机器人而言，有效部署需要足够的精度、实时性能和低能耗。","Applied and Computational Engineering",{"impact":17,"substance":256,"depth":121,"authority":257,"freshness":13,"relevant":21,"comment":258},18,13,"系统梳理轻量化模型在农业嵌入式设备上的部署路径，并以监测机器人案例给出可复现方案，对智慧农业工程落地有参考价值。",[260],{"name":254,"url":251},[26,27,262,28,263],"农业机器人","作物监测",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":267},{"candidates":268,"agricultural_evidence":45},[269,275,281,285,290],{"code":32,"score":55,"supported":45,"title":270,"abstract":271,"tags":274},[],[272,273],"artificial intelligence","YOLO",[27],{"code":276,"score":277,"supported":45,"title":278,"abstract":279,"tags":280},"F6",4,[],[262],[262],{"code":54,"score":21,"supported":14,"title":282,"abstract":283,"tags":284},[],[],[26],{"code":286,"score":21,"supported":14,"title":287,"abstract":288,"tags":289},"I3",[],[],[263],{"code":77,"score":21,"supported":14,"title":291,"abstract":292,"tags":293},[],[],[28],[295,296],"农业监测机器人 轻量YOLO Jetson","嵌入式AI 模型轻量化","农业监测机器人轻量YOLOJetson-4798",5,"10.54254\u002F2755-2721\u002F2026.ld37676",{"doi":299,"openalex_id":301,"authors":302,"venue":254,"cited_by_count":100,"oa_url":305,"card":306,"direction":310,"ingested_from":107},"W7221561538",[303],{"name":304,"orcid":9},"Jingen Zhou","https:\u002F\u002Face.ewapub.com\u002Farticle\u002Fview\u002F37676.pdf",{"tldr":307,"method":308,"finding":309,"direction":310,"opportunity":311},"综述轻量化AI方法，并以农业监测机器人为例，提出相机+轻量YOLO+Jetson+单片机的嵌入式部署","综述网络压缩、剪枝、量化、蒸馏，对比Jetson、树莓派、单片机，设计农业机器人","农业机器人部署需兼顾足够精度、实时性与低能耗，而非追求最大模型复杂度。","智慧农业 \u002F 农业物联网","可研究面向田间多变环境的轻量化模型自适应选择与能效-精度联合优化部署策略。","2026-10-13T23:30:08.379081Z",{"id":314,"title":315,"url":316,"summary":317,"summary_zh":318,"content":9,"source_name":319,"source_url":316,"published_at":320,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":321,"score_detail":322,"sources":325,"tags":327,"primary_topic":330,"secondary_topics":334,"classification":336,"search_phrases":376,"slug":379,"view_count":100,"doi":380,"paper":381,"created_at":413},4489,"Artificial Intelligence and Internet of Things in Smart Agriculture: A Bibliometric and Thematic Review of Data Infrastructures and Sustainability Implications","https:\u002F\u002Fdoi.org\u002F10.54175\u002Fhsustain5040036","Artificial intelligence (AI) is reshaping smart agriculture through prediction, automation, resource optimization, and data-driven decision-making. However, its effective and sustainable deployment depends on reliable Internet of Things (IoT) data infrastructures supporting sensing, connectivity, data acquisition, transmission, and distributed processing. This review maps research at the intersection of AI, IoT, and smart agriculture and examines its data-infrastructure requirements and sustainability implications. Drawing on 441 Scopus-indexed, peer-reviewed journal articles published between 2017 and 2025, the study combines bibliometric performance analysis, science mapping, and content-based thematic interpretation to identify publication trends, intellectual foundations, influential research fronts, emerging themes, and deployment challenges. The bibliometric analyses characterize AI–IoT research in smart agriculture, while IoT data infrastructure provides the principal analytical lens, and sustainability and responsible deployment are examined through interpretive synthesis. The findings reveal rapid publication growth and prominent themes involving connected sensing, predictive analytics, edge intelligence, remote sensing, smart irrigation, cybersecurity, blockchain, and edge–cloud processing. Persistent barriers include limited interoperability, inconsistent data quality, energy requirements, scalability constraints, cybersecurity and governance risks, affordability, and unequal adoption in resource-constrained contexts. The review concludes that sustainable AI-enabled agriculture requires reliable, secure, interoperable, energy-efficient, inclusive, and context-appropriate digital infrastructures.","人工智能（AI）正通过预测、自动化、资源优化和数据驱动决策重塑智慧农业。然而，其有效且可持续的部署依赖于可靠的物联网（IoT）数据基础设施，以支持感知、连接、数据采集、传输和分布式处理。本综述梳理了人工智能、物联网与智慧农业交叉领域的研究，并考察其数据基础设施需求及可持续性影响。基于2017年至2025年间发表的441篇Scopus索引同行评审期刊论文，本研究结合文献计量绩效分析、科学知识图谱和基于内容的主题解读，以识别发文趋势、知识基础、有影响力的研究前沿、新兴主题及部署挑战。文献计量分析刻画了智慧农业中人工智能—物联网研究的特征，物联网数据基础设施则作为主要分析视角，可持续性与负责任部署则通过解释性综合加以考察。研究发现发文量快速增长，突出主题涉及互联感知、预测分析、边缘智能、遥感、智能灌溉、网络安全、区块链及边云处理。持续存在的障碍包括互操作性有限、数据质量不一致、能源需求、可扩展性约束、网络安全与治理风险、可负担性以及在资源受限情境中的不均衡采用。本综述得出结论：可持续的人工智能赋能农业需要可靠、安全、可互操作、节能、包容且情境适宜的数字基础设施。","Highlights of Sustainability","2026-10-08T00:00:00Z",79,{"impact":256,"substance":323,"depth":256,"authority":257,"freshness":144,"relevant":21,"comment":324},22,"基于441篇文献的AI-IoT智慧农业文献计量综述，系统梳理数据基础设施与可持续部署瓶颈，学术参考价值较高。",[326],{"name":319,"url":316},[26,27,328,28,329],"农业物联网","数据基础设施",{"code":77,"slug":331,"name":332,"path":333,"parent_code":36},"agricultural-iot","物联网传感与边缘计算","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-iot",[335],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":337},{"candidates":338,"agricultural_evidence":45},[339,347,352,359,363,370],{"code":77,"score":340,"supported":45,"title":341,"abstract":343,"tags":346},19,[342],"internet of things",[344,342,345],"物联网","IoT",[328,28],{"code":54,"score":204,"supported":45,"title":348,"abstract":350,"tags":351},[349],"smart agriculture",[26,349],[26],{"code":353,"score":139,"supported":45,"title":354,"abstract":356,"tags":358},"I7",[355],"bibliometric",[357,355],"文献计量",[],{"code":32,"score":17,"supported":45,"title":360,"abstract":361,"tags":362},[272],[272],[27],{"code":364,"score":63,"supported":45,"title":365,"abstract":366,"tags":369},"H3",[],[367,368],"灌溉","irrigation",[],{"code":286,"score":63,"supported":45,"title":371,"abstract":372,"tags":375},[],[373,374],"遥感","remote sensing",[],[377,378],"AI IoT 智慧农业 文献计量","农业物联网 数据基础设施","AIIoT智慧农业文献计量-4489","10.54175\u002Fhsustain5040036",{"doi":380,"openalex_id":382,"authors":383,"venue":319,"cited_by_count":100,"oa_url":407,"card":408,"direction":310,"ingested_from":107},"W7220924310",[384,387,390,392,395,398,401,404],{"name":385,"orcid":386},"Altyeb Ali Abaker Omer","https:\u002F\u002Forcid.org\u002F0000-0001-9420-9910",{"name":388,"orcid":389},"Yajie Dong","https:\u002F\u002Forcid.org\u002F0009-0001-2843-6135",{"name":391,"orcid":9},"Ibrahim Issa Mohamed Issa",{"name":393,"orcid":394},"Yousif Yahia Ahmed Abuker","https:\u002F\u002Forcid.org\u002F0009-0002-8111-9283",{"name":396,"orcid":397},"Mohamed Ibrahim Abdallh Babeker","https:\u002F\u002Forcid.org\u002F0009-0008-0904-9501",{"name":399,"orcid":400},"Alfadil Aboud Alfadil Hassan","https:\u002F\u002Forcid.org\u002F0009-0005-0656-1903",{"name":402,"orcid":403},"Zhiguo Shan","https:\u002F\u002Forcid.org\u002F0000-0002-6165-8258",{"name":405,"orcid":406},"Yinxue Shi","https:\u002F\u002Forcid.org\u002F0009-0002-1465-8666","https:\u002F\u002Fwww.hos.pub\u002Farticles\u002Fhsustain5040036\u002Fpdf",{"tldr":409,"method":410,"finding":411,"direction":310,"opportunity":412},"综述2017-2025年441篇文献，梳理AI与IoT在智慧农业中的数据基础设施与可持续性。","Scopus文献计量、科学映射与主题内容分析，以IoT数据基础设施为分析视角。","研究快速增长，但互操作性、数据质量、能耗、安全与公平采用仍是主要障碍。","可针对资源受限小农户场景，研究低能耗、可互操作且包容的农业IoT数据基础设施与治理机制。","2026-10-09T23:30:07.811940Z",{"id":415,"title":416,"url":417,"summary":418,"summary_zh":419,"content":9,"source_name":420,"source_url":417,"published_at":421,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":422,"score_detail":423,"sources":425,"tags":427,"primary_topic":429,"secondary_topics":430,"classification":432,"search_phrases":462,"slug":465,"view_count":21,"doi":466,"paper":467,"created_at":482},4420,"AI-Enabled Sustainable Precision Farming Using Raspberry Pi and Coral Edge TPU with Cloud-Based Model Training","https:\u002F\u002Fdoi.org\u002F10.22214\u002Fijraset.2026.85019","Precision Agriculture requires intelligent, adaptable and efficient technology that is capable of making decisions in agriculture at the right time, based on the condition of the plants and the environment. This paper proposes the development of an AI-based sustainable precision farming system based on computer vision, cloud based model training, Raspberry Pi, Coral Edge TPU and the Internet of Things (IoT) sensing. The proposed architecture's sensing layer, edge processing layer, cloud intelligence layer, and application layer enables a complete data processing pipeline from the field to real time decision support. Crop photos are collected for AI condition classification and agricultural conditions such as soil moisture, temperature, humidity and light intensity are collected by built-in sensors. After the above preprocessing, normalisation, image resizing and augmentation, the dataset is divided into training, validation and test sets. The trained deep learning models in a cloud environment are then quantized and converted to be optimized for the edge, following this step. Following this step, the trained deep learning models are quantized and converted for optimization on edge. The optimized model achieves an exemplary accuracy of 94.82%, precision of 94.47%, recall of 94.05% and F1-score of 94.26%. Deploying with the Coral Edge TPU reduces inference latency to approximately 38ms compared to Raspberry Pi-only processing, increases processing throughput to 26.3 pictures per second and reduces CPU usage. The edge-assisted architecture reduces the need for constant connection to the cloud, giving local decision making a leg up. Illustrative sustainability study estimates that condition based monitoring can save 22% of the irrigation water used every day. The findings indicated that the introduction of the edge AI and cloud intelligence in precision agricultural systems that are responsive, scalable, and resource-efficient is technically possible.","精准农业需要智能、自适应且高效的技术，能够根据植物和环境状况在恰当时机做出农业决策。本文提出开发一种基于人工智能的可持续精准农业系统，该系统依托计算机视觉、基于云端的模型训练、树莓派（Raspberry Pi）、Coral边缘TPU（Edge TPU）以及物联网（IoT）传感技术。所提出的架构包含感知层、边缘处理层、云智能层和应用层，实现了从田间到实时决策支持的完整数据处理流水线。系统采集作物照片用于AI状态分类，并通过内置传感器采集土壤湿度、温度、空气湿度和光照强度等农业环境条件。经过上述预处理、归一化、图像缩放和数据增强后，数据集被划分为训练集、验证集和测试集。随后，在云环境中训练好的深度学习模型经过量化和转换，针对边缘设备进行优化。优化后的模型达到了94.82%的准确率、94.47%的精确率、94.05%的召回率和94.26%的F1分数，表现优异。与仅使用树莓派处理相比，部署Coral边缘TPU将推理延迟降低至约38毫秒，将处理吞吐量提升至每秒26.3张图片，并降低了CPU占用率。该边缘辅助架构减少了对云端持续连接的需求，提升了本地决策能力。一项示例性可持续性研究估计，基于状态的监测可节省22%的每日灌溉用水量。研究结果表明，在精准农业系统中引入边缘AI和云智能，构建响应迅速、可扩展且资源高效的农业系统，在技术上是可行的。","International Journal for Research in Applied Science and Engineering Technology","2026-10-07T00:00:00Z",55,{"impact":144,"substance":256,"depth":204,"authority":63,"freshness":144,"relevant":21,"comment":424},"技术路线完整、指标具体，但属单篇学术论文，产业影响有限，可作为智慧农业技术参考而非每日精选头条。",[426],{"name":420,"url":417},[26,27,28,344,428],"精准灌溉",{"code":77,"slug":331,"name":332,"path":333,"parent_code":36},[431],{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},{"status":39,"locked":14,"version":40,"method":41,"evidence":433},{"candidates":434,"agricultural_evidence":45},[435,440,447,451,455],{"code":77,"score":436,"supported":45,"title":437,"abstract":438,"tags":439},11,[],[344,342,345],[344,28],{"code":32,"score":13,"supported":45,"title":441,"abstract":442,"tags":446},[],[48,443,51,444,445],"计算机视觉","computer vision","decision support",[27],{"code":364,"score":55,"supported":45,"title":448,"abstract":449,"tags":450},[],[367,368],[428],{"code":54,"score":55,"supported":45,"title":452,"abstract":453,"tags":454},[],[58,59],[26],{"code":456,"score":63,"supported":45,"title":457,"abstract":458,"tags":461},"H2",[],[459,460],"土壤","soil",[],[463,464],"Raspberry Pi Coral Edge TPU 精准农业","边缘AI 作物分类 灌溉节水","RaspberryPiCoralEdgeTPU精准农业-4420","10.22214\u002Fijraset.2026.85019",{"doi":466,"openalex_id":468,"authors":469,"venue":420,"cited_by_count":100,"oa_url":417,"card":477,"direction":310,"ingested_from":107},"W7220855887",[470,473,475],{"name":471,"orcid":472},"Prakash Kanade","https:\u002F\u002Forcid.org\u002F0000-0001-6296-9368",{"name":474,"orcid":9},"Shetty Chirag",{"name":476,"orcid":9},"Sunay Kanade",{"tldr":478,"method":479,"finding":480,"direction":310,"opportunity":481},"提出基于树莓派与Coral Edge TPU的边缘AI精准农业系统，实现作物状态分类与实时决策。","计算机视觉、云端模型训练与量化、边缘TPU部署、IoT多传感器融合。","模型准确率94.82%，推理延迟约38ms，条件监测可节水22%。","可探索多作物泛化、边缘模型自适应更新及水肥药协同优化，并量化长期可持续效益。","2026-10-08T23:30:09.663393Z",{"id":484,"title":485,"url":486,"summary":487,"summary_zh":488,"content":9,"source_name":489,"source_url":486,"published_at":490,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":491,"sources":493,"tags":495,"primary_topic":498,"secondary_topics":499,"classification":500,"search_phrases":515,"slug":518,"view_count":63,"doi":519,"paper":520,"created_at":531},4009,"Plant disease classification using lightweight deep learning architectures","https:\u002F\u002Fdoi.org\u002F10.1177\u002F18758967261494075","Detecting early-stage pathogens of plant diseases is a challenging task due to the low pathogen density and the subtlety or absence of visible symptoms. If not identified at an early stage, plant diseases can progress rapidly, making them significantly harder to control. Therefore, real-time and in-situ monitoring of plants is essential for tracking diseases and enabling early intervention. Within the scope of smart agriculture applications, crop health can be assessed and productivity can be maintained through mobile devices. In this study, the performance of lightweight neural network architectures on various plant disease datasets was compared, targeting devices with limited memory resources such as mobile devices and embedded systems, which we consider potential candidates for edge deployment based on the measured accuracy-efficiency trade-offs. The architectures evaluated include SqueezeNet, MobileViT, EdgeNeXt, GhostNet, EfficientNet, and LeViT. The plant datasets used in the experiments were Plant Disease, Cassava, and Turmeric. Each model was evaluated using Accuracy, F1-Score, Precision, and Recall metrics. Among the three datasets, the best performance was achieved on the Turmeric dataset using the GhostNet architecture, with scores of 0.9978 (Accuracy), 0.9976 (F1-Score), 0.9976 (Precision), and 0.9976 (Recall), respectively.","检测植物病害的早期病原体是一项具有挑战性的任务，因为病原体密度低，且可见症状细微或缺失。若未能在早期识别，植物病害会迅速进展，从而使其控制难度显著增加。因此，对植物进行实时原位监测对于追踪病害并实现早期干预至关重要。在智慧农业应用范围内，可通过移动设备评估作物健康并维持生产力。本研究比较了轻量级神经网络架构在不同植物病害数据集上的性能，目标针对内存资源受限的设备，如移动设备和嵌入式系统；基于所测得的精度-效率权衡，我们认为这些设备是边缘部署的潜在候选。所评估的架构包括SqueezeNet、MobileViT、EdgeNeXt、GhostNet、EfficientNet和LeViT。实验中使用的植物数据集为Plant Disease、Cassava和Turmeric。每个模型均使用准确率、F1分数、精确率和召回率指标进行评估。在三个数据集中，使用GhostNet架构在Turmeric数据集上取得了最佳性能，其得分分别为0.9978（准确率）、0.9976（F1分数）、0.9976（精确率）和0.9976（召回率）。","Journal of Intelligent & Fuzzy Systems","2026-10-01T00:00:00Z",{"impact":17,"substance":18,"depth":121,"authority":257,"freshness":20,"relevant":21,"comment":492},"系统比较六种轻量网络在三种作物病害数据集上的精度效率权衡，对边缘端部署有参考价值，但属常规模型对比研究，公共影响有限。",[494],{"name":489,"url":486},[26,27,28,496,497],"植物病害识别","轻量模型",{"code":32,"slug":33,"name":34,"path":35,"parent_code":36},[],{"status":39,"locked":14,"version":40,"method":41,"evidence":501},{"candidates":502,"agricultural_evidence":45},[503,507,511],{"code":32,"score":13,"supported":45,"title":504,"abstract":505,"tags":506},[51],[],[27,496],{"code":54,"score":55,"supported":45,"title":508,"abstract":509,"tags":510},[],[26,349],[26],{"code":77,"score":21,"supported":14,"title":512,"abstract":513,"tags":514},[],[],[28],[516,517],"GhostNet 姜黄病害识别","轻量神经网络 植物病害分类","GhostNet姜黄病害识别-4009","10.1177\u002F18758967261494075",{"doi":519,"openalex_id":521,"authors":522,"venue":489,"cited_by_count":100,"oa_url":9,"card":526,"direction":310,"ingested_from":107},"W7215069222",[523],{"name":524,"orcid":525},"Buket Toptaş","https:\u002F\u002Forcid.org\u002F0000-0003-2556-8199",{"tldr":527,"method":528,"finding":529,"direction":105,"opportunity":530},"比较六种轻量神经网络在三种植物病害数据集上的分类性能，面向边缘设备部署。","使用SqueezeNet、MobileViT、EdgeNeXt、GhostNet","GhostNet在Turmeric数据集上表现最佳，准确率达0.9978，适合资源受限设备。","可探索轻量模型在真实田间边缘设备上的实时病害检测与多作物泛化能力。","2026-10-02T23:30:11.674439Z"]