IEEE Transactions on AgriFood Electronics最新文献_第7页

Label-Free D-Mannitol Detection Using Vanadium Dioxide and TMDCs-Based Metallic Plasmonic Biosensor 基于二氧化钒和tmdcs的金属等离子体生物传感器的无标签d -甘露醇检测

IEEE Transactions on AgriFood Electronics Pub Date : 2026-03-01 Epub Date: 2025-11-03 DOI: 10.1109/TAFE.2025.3622866

Mogal Mahazira Tabassum;Yesudasu Vasimalla;Madhusudan Mishra;Santosh Kumar

{"title":"Label-Free D-Mannitol Detection Using Vanadium Dioxide and TMDCs-Based Metallic Plasmonic Biosensor","authors":"Mogal Mahazira Tabassum;Yesudasu Vasimalla;Madhusudan Mishra;Santosh Kumar","doi":"10.1109/TAFE.2025.3622866","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3622866","url":null,"abstract":"Identification of biomolecules such as D-mannitol is required for biotechnology, environmental monitoring, and medical diagnosis. This study presents a customized surface plasmon resonance (SPR) sensor that uses vanadium dioxide (<inline-formula><tex-math>$mathrm{V}{{mathrm{O}}_2}$</tex-math></inline-formula>) as an important material layer to improve detection performance. To improve its performance, the suggested sensor has a layered structure that is composed of transition metal dichalcogenides, Pilkington Optiwhite glass, and a silver (Ag) layer. D-mannitol detection sensitivity and uniqueness increase with <inline-formula><tex-math>$mathrm{V}{{mathrm{O}}_2}$</tex-math></inline-formula> and special optical and plasmonic characteristics. Our experiments show that the suggested sensor performs better than the conventional SPR sensor, with a high sensitivity of 300.41<inline-formula><tex-math>$^circ /text{RIU}$</tex-math></inline-formula>, figure of merit of 68.96 <inline-formula><tex-math>$text{RI}{{mathrm{U}}^{ - 1}}$</tex-math></inline-formula>, combined sensitive factor of 67.633, and a quality factor of 200.1248 <inline-formula><tex-math>$text{RI}{{mathrm{U}}^{ - 1}}$</tex-math></inline-formula>. Label-free, in real-time biosensing applications, the work displays the ability of <inline-formula><tex-math>$mathrm{V}{{mathrm{O}}_2}$</tex-math></inline-formula>, which provides a promising development in highly sensitive identification methods. In addition, a comparison exam shows the better performance of our sensors on current detection techniques. Finally, the construction methods that will help to make the suggested sensor experimentally.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"168-175"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512364","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

GDA-YOLO11: Amodal Instance Segmentation for Occlusion-Robust Robotic Fruit Harvesting GDA-YOLO11：面向闭塞鲁棒机器人水果收获的模态实例分割

IEEE Transactions on AgriFood Electronics Pub Date : 2026-03-01 Epub Date: 2026-03-18 DOI: 10.1109/TAFE.2026.3670352

Caner Beldek;Emre Sariyildiz;Son Lam Phung;Gursel Alici

{"title":"GDA-YOLO11: Amodal Instance Segmentation for Occlusion-Robust Robotic Fruit Harvesting","authors":"Caner Beldek;Emre Sariyildiz;Son Lam Phung;Gursel Alici","doi":"10.1109/TAFE.2026.3670352","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3670352","url":null,"abstract":"Occlusion remains a critical challenge in robotic fruit harvesting, as undetected or inaccurately localized fruits often results in substantial crop losses. To mitigate this issue, we propose a harvesting framework using a new amodal segmentation model, GDA-YOLO11, which incorporates architectural improvements and an updated asymmetric mask loss. The proposed model is trained on a modified version of a public citrus dataset and evaluated on both the base dataset and occlusion-sensitive subsets with varying occlusion levels. Within the framework, full fruit masks, including invisible regions, are inferred by GDA-YOLO11, and picking points are subsequently estimated using the Euclidean distance transform. These points are then projected into 3-D coordinates for robotic harvesting execution. Experiments were conducted using real citrus fruits in a controlled environment simulating occlusion scenarios. Notably, to the best of the authors’ knowledge, this study provides the first practical demonstration of amodal instance segmentation in robotic fruit harvesting. GDA-YOLO11 achieves a precision of 0.844, recall of 0.846, mAP@50 of 0.914, and mAP@50:95 of 0.636, outperforming YOLO11n by 5.1%, 1.3%, and 1.0% in precision, mAP@50, and mAP@50:95, respectively. The framework attains harvesting success rates of 92.59%, 85.18%, 48.14%, and 22.22% at zero to high occlusion levels, improving success by 3.5% under medium and high occlusion. These findings demonstrate that GDA-YOLO11 enhances occlusion-robust segmentation and streamlines perception-to-action integration, paving the way for more reliable autonomous systems in agriculture.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"409-417"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667651","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimized Path Planning for UGV Based on Sampling Maps 基于采样图的UGV路径优化规划

IEEE Transactions on AgriFood Electronics Pub Date : 2026-03-01 Epub Date: 2025-10-27 DOI: 10.1109/TAFE.2025.3615535

Gavriela Asiminari;Panagiotis Papazisis;Dimitrios Katikaridis;Dimitrios Kateris;Dionysis Bochtis

{"title":"Optimized Path Planning for UGV Based on Sampling Maps","authors":"Gavriela Asiminari;Panagiotis Papazisis;Dimitrios Katikaridis;Dimitrios Kateris;Dionysis Bochtis","doi":"10.1109/TAFE.2025.3615535","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3615535","url":null,"abstract":"This work proposes an optimized path-planning approach for soil sampling using an autonomous uncrewed ground vehicle (UGV) in precision agriculture. The field is divided into homogeneous management zones based on electrical conductivity (ECa) measurements, with sampling points strategically distributed within each zone. A path-planning algorithm minimizes the travel distance for the UGV while ensuring thorough data collection. The methodology combines geospatial analysis, inverse distance weighting interpolation, and clustering to assign accurate ECa values to grid points and classify zones. The novelty of this study lies not in the development of new algorithms but in the integration of established methods into a unified framework, implemented on a UGV and validated under real field conditions. The Greedy algorithm is applied to solve the <italic>travelling salesman problem to optimize the UGV’s route, ensuring efficient sampling. The sampling plan is uploaded to an Android application for manual guidance or to the UGV for autonomous operation. Equipped with sensors for measuring soil pH and compaction, the vehicle follows the predefined path, and data are stored for analysis. Experimental validation shows that the system reduces operational costs and improves soil health assessment, demonstrating the potential of autonomous robotic platforms in precision agriculture.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"15-21"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509759","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sustainable Water Management in an Evolving Tomato Cultivation Testbed 不断发展的番茄栽培试验田的可持续水资源管理

IEEE Transactions on AgriFood Electronics Pub Date : 2026-03-01 Epub Date: 2025-11-14 DOI: 10.1109/TAFE.2025.3625603

Giulia Oddi;Laura Belli;Luca Davoli;Luca Preite;Martina Galaverni;Margherita Rodolfi;Giuseppe Vignali;Tommaso Ganino;Gianluigi Ferrari

{"title":"Sustainable Water Management in an Evolving Tomato Cultivation Testbed","authors":"Giulia Oddi;Laura Belli;Luca Davoli;Luca Preite;Martina Galaverni;Margherita Rodolfi;Giuseppe Vignali;Tommaso Ganino;Gianluigi Ferrari","doi":"10.1109/TAFE.2025.3625603","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3625603","url":null,"abstract":"Nowadays traditional agricultural irrigation practices present significant challenges for both sustainability and productivity, resulting in excessive water consumption—70% of the world’s water consumption is dedicated to agricultural irrigation—and inefficient resource management. The adoption of innovative solutions and technologies to support smart agriculture applications allows to overcome these problems and improve the productivity in terms of crop yield, fruits quality, efficiency, resource management, and waste reduction. Guided by these goals, this work examines the activities carried out within the NextGenerationEU-funded AGRITECH project in an evolving tomato cultivation testbed. The evaluation has been conducted for two consecutive years, namely, 2023 and 2024, with the deployment of Internet of Things devices and the support of the <italic>Agriware cloud platform. In particular, the automated irrigation system deployed during the second year of experimentation allowed for more precise and efficient irrigation scheduling with respect to that of the first year (manually managed). In fact, <inline-formula><tex-math>$mathbf{0.13}$</tex-math></inline-formula> m<inline-formula><tex-math>$^{mathbf{3}}$</tex-math></inline-formula> of water per square mater have been saved, while the water use efficiency improved by 22.2%, considering the global yield, thanks to the revised automated system. The experimental results demonstrate the feasibility of <italic>on-field automated irrigation processes, allowing to reduce the water consumption, increasing the accuracy, and improving the efficiency, if compared to manually managed irrigations. Overall, the experimental findings clearly highlight that a fully automated decision support system could enhance agricultural practices by enabling more precise resource management and by reducing water waste and farmers’ workload.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"56-67"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11247915","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148510153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Phosphorus Stress Detection in Plants Using Harmonically Modulated Chlorophyll Fluorescence 利用调和调制叶绿素荧光检测植物磷胁迫

IEEE Transactions on AgriFood Electronics Pub Date : 2026-03-01 Epub Date: 2025-11-04 DOI: 10.1109/TAFE.2025.3615847

Faisal Sani Bala;Michael D. O’Toole;Bruce Grieve;Stephen Rolfe;Mustafa Yasin

{"title":"Phosphorus Stress Detection in Plants Using Harmonically Modulated Chlorophyll Fluorescence","authors":"Faisal Sani Bala;Michael D. O’Toole;Bruce Grieve;Stephen Rolfe;Mustafa Yasin","doi":"10.1109/TAFE.2025.3615847","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3615847","url":null,"abstract":"This study explores a novel application of harmonically modulated chlorophyll fluorescence imaging for detecting phosphorus nutrient stress in plants. This approach may provide advantages over contemporary methods, appearing less susceptible to spurious light sources, requiring lower computational demand than hyperspectral imaging, and enabling faster results compared to the rapid light-induced fluorescence method, which requires extended dark adaptation. A sinusoidally modulated fluorescence imaging system was developed to capture fluorescence signals from wheat plants under varying phosphorus conditions. Signals were processed using wavelet scattering, wavelet packet, and fast Fourier transforms, then classified via support vector machine. Results indicate that the method can distinguish between phosphorus-sufficient (100%), phosphorus-deficient (50%), and phosphorus-deprived (0%) plants, achieving up to 98% accuracy in binary classifications under the tested condition between high and low phosphorus levels, and 79% –98% accuracy for intermediate comparisons (high versus medium, medium versus low). Wavelet packet transform consistently delivered the highest performance (<inline-formula><tex-math>$>$</tex-math></inline-formula>96% accuracy across all pairs) with minimal variability. The study establishes harmonically modulated chlorophyll fluorescence as a promising tool for rapid, noninvasive nutrient stress detection, advancing precision agriculture practices.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"176-184"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Semantic-Search: A Knowledge-Driven Classification Method for Accurate Identification of Plant Diseases 语义搜索：一种知识驱动的植物病害准确识别分类方法

IEEE Transactions on AgriFood Electronics Pub Date : 2026-03-01 Epub Date: 2025-10-23 DOI: 10.1109/TAFE.2025.3619095

Kiran K. Kethineni;Saraju P. Mohanty;Elias Kougianos

{"title":"Semantic-Search: A Knowledge-Driven Classification Method for Accurate Identification of Plant Diseases","authors":"Kiran K. Kethineni;Saraju P. Mohanty;Elias Kougianos","doi":"10.1109/TAFE.2025.3619095","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3619095","url":null,"abstract":"As the global population is increasing and agricultural resources are diminishing, effective management of plant diseases become critical. Convolutional neural network-based models have been widely adopted in agriculture cyber–physical systems due to their high accuracy. However, these models require large, labeled datasets for training, limiting their practicality in plant disease detection where data are heterogeneous, scarce, and subjected to continual evolution. To address these challenges, we propose semantic-search, a knowledge-driven system that interprets plant diseases based on high-level semantic features, such as visual patterns, colors, and crop type, rather than relying solely on low-level image features. The system classifies diseases by querying a structured knowledge base using these semantics. “Semantic search” here refers to classification based on semantic feature extraction and knowledge base querying. It enables greater adaptability, interpretability, and robustness to intraclass variability caused by differing environmental conditions. The system can incorporate new disease classes through simple knowledge base updates, eliminating the need for retraining. This facilitates efficient scaling to evolving set of diseases. We validated the proposed approach on a dataset of 11 000 images encompassing 21 diseases across 11 plant species, achieving an accuracy of 90%, thereby demonstrating its effectiveness, scalability.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"4-14"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148514956","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Stress-Minimized Oral Temperature Measurement in Pigs Using Custom-Developed Water-Supply Device 使用定制的供水装置测量猪的最小压力口腔温度

IEEE Transactions on AgriFood Electronics Pub Date : 2026-03-01 Epub Date: 2025-12-24 DOI: 10.1109/TAFE.2025.3637826

Geunho Lee;Teruyuki Yamane;Tasuku Koga;Tota Kuga;Atsushi Takahashi;Yusuke Iki

{"title":"Stress-Minimized Oral Temperature Measurement in Pigs Using Custom-Developed Water-Supply Device","authors":"Geunho Lee;Teruyuki Yamane;Tasuku Koga;Tota Kuga;Atsushi Takahashi;Yusuke Iki","doi":"10.1109/TAFE.2025.3637826","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3637826","url":null,"abstract":"Existing methods for monitoring pig health primarily include visual inspection by pig farmers and the measurement of body temperature, typically via rectal or vaginal insertion. However, the continuous monitoring of rectal or vaginal temperatures poses challenges owing to hygiene concerns and the stress it imposes on pigs. This article presents a novel water-supply device that enables automatic stress-free oral temperature measurements during voluntary drinking. By capturing oral temperature during water intake, the device supports continuous monitoring without causing discomfort to the pigs. For accuracy, a measurement-and-counting algorithm is implemented to identify valid temperature data and prevent interference between oral and water temperatures. After integrating the algorithm into the device, its effectiveness for water delivery and accurate oral temperature measurements is evaluated. Experiments conducted on a farm confirmed the reliability of the device for measuring oral temperatures in pigs. Furthermore, these results demonstrate that oral temperature, as determined by the application of the algorithm, has the potential to serve as a reliable surrogate for core body temperature. The device using this algorithm and its extensive results are presented in detail.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"270-278"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667695","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DDAN-RGAL: A Dual-Domain Adaptive Network With Reality-Gap Aware Learning for Field-Deployable Plant Disease Detection DDAN-RGAL：一种具有现实差距感知学习的双域自适应网络，用于现场可部署植物病害检测

IEEE Transactions on AgriFood Electronics Pub Date : 2026-03-01 Epub Date: 2026-03-27 DOI: 10.1109/TAFE.2026.3667568

Syed Asif Ahmad Qadri;Nen Fu Huang;Yu-Hsiang Huang;Pin-Cheng Chan

{"title":"DDAN-RGAL: A Dual-Domain Adaptive Network With Reality-Gap Aware Learning for Field-Deployable Plant Disease Detection","authors":"Syed Asif Ahmad Qadri;Nen Fu Huang;Yu-Hsiang Huang;Pin-Cheng Chan","doi":"10.1109/TAFE.2026.3667568","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3667568","url":null,"abstract":"Deep learning models achieve over 95% accuracy for plant disease detection in laboratory settings but suffer severe performance drops exceeding 30% when deployed under real agricultural conditions. This article presents dual-domain adaptive network with reality-gap aware learning (DDAN-RGAL), a unified framework that explicitly bridges this laboratory-to-field gap through three synergistic modules. The first, domain-invariant feature disentanglement, separates disease-intrinsic patterns from environmental artifacts using adversarial and mutual-information constraints. The second, cross-domain prototype learning with uncertainty, learns hierarchical laboratory and field disease prototypes while providing calibrated confidence through evidential deep learning. The third, reality-gap aware meta-classification, dynamically adapts expert classifiers based on domain characteristics inferred from each input. Experiments on PlantVillage, PlantDoc, and a real-world paddy field dataset collected using a field-deployed speed-dome camera and Raspberry Pi-based edge system demonstrate that DDAN-RGAL achieves 98.7% laboratory accuracy and 94.8% field accuracy, reducing the reality gap from 27.9% to 3.9%, a more than seven-fold improvement over existing methods. The framework provides highly reliable uncertainty estimates (expected calibration error: 0.042), inference (21.6 ms on GPU; 285 ms on Raspberry Pi 4), and strong data efficiency (85.3% accuracy with only 10% of the training data). These results establish DDAN-RGAL as a practical and field-ready solution for precision agriculture, enabling robust deployment of laboratory-trained models in real-world farming environments where both accuracy and reliability are essential.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"418-435"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Food Based Nano Conductive Pastes With Algae Biocatalyst for Microbial Fuel Cell Electrodes Screen-Printed on Edible Substrates 用于微生物燃料电池电极的含有藻类生物催化剂的食品基纳米导电浆料在可食用基质上丝网印刷

IEEE Transactions on AgriFood Electronics Pub Date : 2026-03-01 Epub Date: 2025-11-27 DOI: 10.1109/TAFE.2025.3630191

Yuvraj Maphrio Mao;Ramya K;Khairunnisa Amreen;Ratnesh Kumar;Sanket Goel

{"title":"Food Based Nano Conductive Pastes With Algae Biocatalyst for Microbial Fuel Cell Electrodes Screen-Printed on Edible Substrates","authors":"Yuvraj Maphrio Mao;Ramya K;Khairunnisa Amreen;Ratnesh Kumar;Sanket Goel","doi":"10.1109/TAFE.2025.3630191","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3630191","url":null,"abstract":"Edible and ingestible electrodes represent a novel advancement in bioelectronics, enabling noninvasive diagnostics or energy harvesting within living systems. This article pioneers food-based nanoconductive pastes (FN-CoPs) for screen-printed electrodes, evaluates for biodegradability through disintegration studies, biocompatibility via microbial growth assessments, and functionality through electrochemical testing. These food-based electrodes demonstrate energy harvesting capabilities from gut bacteria, confirmed through cyclic voltammetry and polarization studies. FN-CoP electrodes are developed on rice paper and cheese substrates and tested with <italic>Lactobacillus and <italic>E. coli, with an enhanced power generation upon introducing Nori algae as a biocatalyst. Rice paper/FN-CoP electrodes initially produced 1.29 μW/cm2 with <italic>E. coli, increasing to 2.09 μW/cm2 with the biocatalyst corresponding to an improvement of 61.72%, while Cheese/FN-CoP electrodes generated 2.57 μW/cm2, rising to 5.73 μW/cm2 with Nori algae biocatalyzer indicating an improvement of 44.85%. A cascade of these biofuel cells powered a red LED in real-time, showcasing their applicability. This innovation advances the potential of ingestible electronics for self-powered continuous health monitoring and personalized treatment. By providing sustainable energy, FN-CoP electrodes pave the way for significant growth in edible and ingestible bioelectronic applications.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"224-233"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147696203","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Tiny-PMDet: A Knowledge-Distilled Lightweight Edge-AI Detector for Grapevine Powdery Mildew Detection on CMOS Sensor Based AIoT Systems 基于CMOS传感器的AIoT系统葡萄白粉病检测的知识提炼轻量级边缘ai检测器Tiny-PMDet

IEEE Transactions on AgriFood Electronics Pub Date : 2026-03-01 Epub Date: 2026-03-13 DOI: 10.1109/TAFE.2026.3667753

Qiang Tong;Nanxin Zeng;Songtao Wu;Kuanhong Xu

{"title":"Tiny-PMDet: A Knowledge-Distilled Lightweight Edge-AI Detector for Grapevine Powdery Mildew Detection on CMOS Sensor Based AIoT Systems","authors":"Qiang Tong;Nanxin Zeng;Songtao Wu;Kuanhong Xu","doi":"10.1109/TAFE.2026.3667753","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3667753","url":null,"abstract":"Edge-AI-powered Artificial Intelligence of Things (AIoT) technologies enable low-power and efficient solutions for intelligent crop monitoring. This article presents Tiny-PMDet, a lightweight yet high-accuracy detector designed for on-sensor grapevine powdery mildew detection using an edge-AI-enabled CMOS (Sony IMX500) based camera. The proposed model integrates an EfficientNet-Lite0 backbone, a sBiFPN neck, and a lightweight decoupled detection head, achieving an effective balance between detection accuracy and computational efficiency. To further enhance detection precision without increasing inference cost, a loss optimization strategy combining Weighted Cross-Entropy, Efficient IoU, and Quality Cross-Entropy is adopted, together with a dual knowledge distillation scheme based on Pearson correlation and cross-head guidance. Experimental results demonstrate that Tiny-PMDet achieves 95.1% AP@0.5 and 94.4% F1-score, outperforming state-of-the-art lightweight detectors while maintaining a lightweight model size of 2.9 MB and a low computational cost of 0.9 GFLOPs. After posttraining quantization and deployment on the IMX500 sensor, Tiny-PMDet achieves real-time inference at 36 FPS with only an approximately 1% accuracy degradation. These results highlight the advantages of edge-AI CMOS sensor-based solutions for enabling low-power, on-site, and network-independent agricultural monitoring, marking a significant step toward scalable AIoT-driven smart agriculture.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"383-394"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0