IEEE Transactions on AgriFood Electronics最新文献

{"title":"Dual-Band Microwave Spectroscopy and Machine Learning for Rapid Milk Adulteration Detection","authors":"Amartya Paul;Hemant Kumari;Shubhankar Majumdar","doi":"10.1109/TAFE.2025.3614005","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3614005","url":null,"abstract":"This work presents a novel, low-cost, and portable microwave sensor-based system for the detection and classification of milk adulterants using microwave spectroscopy and machine learning. The sensor operates at two distinct frequencies, 1.25 and 2.4 GHz, and exhibits high sensitivity to dielectric changes caused by adulteration. A set of eight common adulterants, including tap water, mineral water, urea, liquid whey, vegetable protein, soya protein, extraneous water, and sodium carbonate, were tested at concentrations ranging from 5% to 50%. The sensor is operated through a Raspberry Pi, and ADALM-PLUTO Software Defined Radio, and the output is observed on a monitor through a graphical user interface. The transmission response (<inline-formula><tex-math>$S_{21}$</tex-math></inline-formula>) shows attenuation levels dropping from 0 dB to nearly <inline-formula><tex-math>$-text{18}$</tex-math></inline-formula> dB as adulterant concentration increases, with clear resonance suppression. The differential resonance shift (<inline-formula><tex-math>$Delta f = f_{2} - f_{1}$</tex-math></inline-formula>) exhibits a monotonic trend with adulterant percentage, improving sensitivity mapping. Statistical analysis of experimental trials (<inline-formula><tex-math>$N=10$</tex-math></inline-formula> per sample) yielded attenuation mean values with standard deviation error bars, confirming repeatability and robustness. To further strengthen the analytical rigor and decision-making capability of the proposed system, machine learning was employed to extract meaningful patterns from the sensor data and enable reliable classification. A random forest algorithm achieved an overall accuracy of 91.2% and an area under the curve score exceeding 0.7, validated by the confusion matrix and receiver operating characteristic curve. The proposed system demonstrates potential for real-time, noninvasive quality assessment of milk, combining microwave sensing with AI-based decision support to detect and classify adulterants with high sensitivity and specificity.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"137-144"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148514102","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}

{"title":"Low-Cost Microwave System Development for Analysis of Classification and Adulteration of Honey","authors":"Amartya Paul;Hemant Kumari;Simanta Das;Shubhankar Majumdar","doi":"10.1109/TAFE.2026.3666205","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3666205","url":null,"abstract":"This article presents a novel, real-time, portable, and low-cost microwave sensing system for the classification and adulteration detection of natural honey using a log-periodic circular microstrip filter integrated with Wilkinson power dividers (WPDs) and an ADALM-PLUTO software-defined radio. The filter and WPDs operate at <inline-formula><tex-math>$text{2.4};text{GHz}$</tex-math></inline-formula> and incorporate a copper sample chamber designed to accommodate <inline-formula><tex-math>$100; mu mathrm{L}$</tex-math></inline-formula> of liquid samples. Six types of unadulterated honey: 1) Mustard; 2) Wild; 3) Lychee; 4) Garlic; 5) Spiced; and 6) Cacao were tested, and each exhibited unique attenuation signatures ranging from −36.0<inline-formula><tex-math>$mathrm{}$</tex-math></inline-formula>–26.5 <inline-formula><tex-math>$text{dB}$</tex-math></inline-formula>. These measurements were used to define classification thresholds in a Python-based real-time GUI. To evaluate the detection of adulteration, common additives, such as fructose, glucose, sucrose, corn syrup, rice water, and sugar were mixed with each honey at concentrations of 10% to 50%. The system showed a consistent attenuation shift of approximately 2.5–<inline-formula><tex-math>$text{3.0};text{dB}$</tex-math></inline-formula> (8–11% relative change) across adulteration levels, with a resolution of <inline-formula><tex-math>$text{0.5};text{dB}$</tex-math></inline-formula> and a coefficient of variation below 0.4%. These results demonstrate the feasibility of electromagnetic sensing for rapid, nondestructive, and repeatable detection of honey adulteration.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"375-382"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667654","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}

{"title":"Multi-Image Super Resolution Framework for Detection and Analysis of Plant Roots","authors":"Shubham Agarwal;Ofek Nourian;Michael Sidorov;Sharon Chemweno;Ofer Hadar;Naftali Lazarovitch;Jhonathan E. Ephrath","doi":"10.1109/TAFE.2025.3636384","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3636384","url":null,"abstract":"Understanding plant root systems is critical for advancing research in soil–plant interactions, nutrient uptake, and overall plant health. However, accurate imaging of roots in subterranean environments remains a persistent challenge due to adverse conditions, such as occlusion, varying soil moisture, and inherently low contrast, which limit the effectiveness of conventional vision-based approaches. In this work, we propose a novel underground imaging system that captures multiple overlapping views of plant roots and integrates a deep learning-based multi-image superresolution (MISR) framework designed to enhance root visibility and detail. To train and evaluate our approach, we construct a synthetic dataset that simulates realistic underground imaging scenarios, incorporating key environmental factors that affect image quality. Our proposed MISR algorithm leverages spatial redundancy across views to reconstruct high-resolution images with improved structural fidelity and visual clarity. Quantitative evaluations show that our approach outperforms the state-of-the-art superresolution baselines, achieving 2.3% reduction in BRISQUE indicating improved image quality with same CLIP-IQA, thereby enabling enhanced phenotypic analysis of root systems. This in turn facilitates accurate estimation of critical root traits, including root hair count and root hair density. The proposed framework presents a promising direction for robust automatic underground plant root imaging and trait quantification for agricultural and ecological research.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"254-261"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667663","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}

{"title":"Accessible Soil Moisture Sensor System for Small Farmers of San Joaquin Valley, CA","authors":"David Inthavong;Vincent Lee;Hannah Chamberlin;Hubert Cecotti;Serhat Asci;Florence Cassel Sharma;Srinivas Konduru;Dave Goorahoo;Ruth Dahlquist-Willard;Soumyasanta Laha","doi":"10.1109/TAFE.2026.3665742","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3665742","url":null,"abstract":"This article introduces a low-cost, compact, and energy-efficient soil moisture monitoring system designed primarily to support small farmers in California’s San Joaquin Valley with effective crop management. The customized system integrates an Irrometer Watermark Soil Moisture Sensor, a Sensor Adapter, and a wireless enabled PSoC 6 BLE Pioneer Kit to measure soil water tension. Results are displayed in real time on an external LCD in a simple, easy-to-understand format, enabling underprivileged and less educated farmers to make timely decisions for improved crop management. This article further examines future opportunities to integrate the system with web-based technologies, enabling remote monitoring and AI-driven data analysis. The proposed solution addresses critical challenges in soil moisture management faced by small farmers, aiming to enhance efficiency and boost crop productivity through accessible, affordable technology.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"436-443"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667643","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}

{"title":"CCUDA-SS: Cross-Crop Unsupervised Domain Adaptation for Semantic Segmentation","authors":"Numair Nadeem;Muhammad Hamza Asad;Abdul Bais","doi":"10.1109/TAFE.2025.3650340","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3650340","url":null,"abstract":"Accurate semantic segmentation is fundamental to precision agriculture, enabling crop coverage estimation, yield prediction, and resource optimization. However, collecting pixel-level annotations at scale is costly, motivating the use of unsupervised domain adaptation (UDA) to transfer knowledge from annotated (source) to unlabeled (target) datasets. Existing UDA methods, primarily designed for generic visual tasks, struggle with the unique domain shifts in agricultural imagery caused by variations in crop morphology, growth stage, illumination, and imaging conditions. These challenges often result in oversegmentation, under segmentation, and crop-weed misclassification. To address these issues, we propose cross-crop UDA (CCUDA), a transformer-based UDA framework tailored for agricultural domain adaptation. CCUDA leverages mid-level cues—such as row patterns and background textures—that remain consistent across crop types and environments. It employs a hybrid training strategy that combines supervised learning on the source domain with self-training on the target domain through pseudolabels. To mitigate noise in pseudolabels, we introduce masked adversarial alignment, which focusses alignment on uncertain, low-confidence regions while preserving stable representations of confident pixels. Furthermore, to resolve the feature overlap in logit space between crops and weeds due to high interclass similarity, CCUDA incorporates a logit-distance regularizer that enforces explicit separation in logit space, enhancing class discriminability. Finally, a stage-aware sampling strategy balances data exposure across varying crop growth stages, addressing dataset imbalance. CCUDA integrates seamlessly with existing UDA frameworks and, when applied to four state-of-the-art baselines across eight agricultural datasets, achieves up to +5.23% higher mean intersection over union (mIoU) and a +10.04% improvement in crop-class IoU, establishing new benchmarks for robust and generalizable agricultural segmentation.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"334-350"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667693","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}

{"title":"BioVIEW: Automatic Remote Nondestructive Platform for Biodiversity Evaluation","authors":"Miguel Molina-Rotger;Alejandro Morán;Miguel Ángel Miranda;Miquel Roca;Bartomeu Alorda-Ladaria","doi":"10.1109/TAFE.2025.3629559","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3629559","url":null,"abstract":"BioVIEW is a solar-powered, dual-camera Internet of Things (IoT) station designed for long-term, nondestructive biodiversity monitoring in remote habitats. Each station is built from wood and aluminum and integrates two 64-MP cameras, temperature and humidity sensors, programmable LED attractants, and a 30-W photovoltaic power system that powers two Raspberry Pi (RPi) controllers, ensuring months of autonomous operation. The BioVIEW station also provides dual communication options: mobile networks for high-bandwidth image uploads to servers, and LoRaWAN for ultra-low-power telemetry. This setup supports remote management and ensures resilient data delivery. Ten stations deployed across the Balearic Islands (Mallorca, Menorca, Ibiza, Formentera, Cabrera, and Dragonera) are generating a fixed-interval image archive to support supervised learning. In a proof-of-concept study, 62 labeled frames of <italic>Bactrocera oleae</i> were used to train a support vector machine, achieving an accuracy of 0.86 and tracking cumulative counts within one specimen of ground truth over two weeks. Energy profiling across RPi models showed inference budgets ranging from 7 J (MobileNet on RPi 4) to 12 J (SVM on RPi 3), demonstrating the feasibility of edge-based analytics under strict power constraints. By combining energy-efficient hardware, event-driven capture, and a flexible classification framework, BioVIEW enables scalable, high-resolution biodiversity monitoring without harming either target or nontarget species.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"22-28"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11263881","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509954","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}

{"title":"Flapping-Wings Drones for Pests and Diseases Detection in Horticulture","authors":"Orel Awesta;Vera Hollink;Mauro Gallo","doi":"10.1109/TAFE.2025.3589762","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3589762","url":null,"abstract":"Agriculture and horticulture are essential for ensuring safe food to the growing global population, but they also contribute significantly to climate change and biodiversity loss due to the extensive use of chemicals. Integrated pest management is currently employed to monitor and control pest populations, but it relies on labor-intensive methods with low accuracy. Automating crop monitoring using aerial robotics, such as flapping-wing drones, presents a viable solution. This study explores the application of deep learning algorithms, You Only Look Once (YOLO) and Faster region-based convolutional neural network regions with convolutional neural networks (R-CNN), for pest and disease detection in greenhouse environments. The research involved collecting and annotating a diverse dataset of images and videos of common pests and diseases affecting tomatoes, bell peppers, and cucumbers cultivated in Dutch greenhouses. Data augmentation and image resizing techniques were applied to enhance the dataset. The study compared the performance of YOLO and Faster R-CNN, with YOLO demonstrating superior performance. Testing on data acquired by flapping-wing drones showed that YOLO could detect powdery mildew with accuracy ranging from 0.29 to 0.61 despite the shaking movement induced by the actuation system of the drone’s flapping wings.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"99-108"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11113413","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148510496","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}

{"title":"Integrating Digital Twins and MPC for Sustainable Greenhouse Management in Smart Agriculture","authors":"Abdellatif Soussi;Enrico Zero;Christian Di Chiara Herrera;Said Zahmoun;Alessandro Bozzi;Roberto Sacile","doi":"10.1109/TAFE.2025.3572808","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3572808","url":null,"abstract":"This article introduces a digital twin framework for greenhouse climate management, utilizing model predictive control (MPC) to enhance smart farming practices and tackle the challenge of maintaining optimal conditions in diverse weather scenarios. The proposed MPC integrates dynamic system modeling, predictive control, and constraint management to regulate critical variables such as ambient temperature, solar radiation, and airflow. To validate the control framework, historical meteorological data from the city of Savona are used for four seasonal scenarios: winter, spring, summer, and autumn. The main contributions include designing and tuning the MPC, applying soft constraints via equal concern for relaxation for feasibility, and implementing scaling factors to ensure numerical stability. Simulation results demonstrate the controller’s ability to maintain desired climatic conditions while meeting physical and operational constraints. This work highlights the potential of combining digital twin technology with advanced control systems to support sustainable and efficient smart farming.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"39-55"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148512754","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}

{"title":"Aerial-MangoYOLOv8: An Optimized Mango Detection System for UAV-Based Yield Estimation","authors":"Hari Chandana Pichhika;Priyambada Subudhi;Raja Vara Prasad Yerra","doi":"10.1109/TAFE.2025.3631839","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3631839","url":null,"abstract":"While vision-based yield estimation systems are widely used for horticulture crops nowadays, accurately predicting yield in unstructured orchards remains a challenge. Automated unmanned aerial vehicle (UAV)-based aerial data collection offers a scalable solution for such environments. This study utilizes UAVs to collect data from a target mango orchard, marking points of interest to ensure periodic video capture along the same path, maximizing coverage. A significant challenge addressed in this work is the detection of small mangoes in UAV-captured videos. While you only look once (YOLO) models, such as the latest YOLOv8, excel in object detection, they struggle with small objects in aerial imagery. To deal with this, the YOLOv8 model is customized with several enhancements, such as integration of the efficient subpixel convolution network to improve the spatial resolution of feature maps and incorporation of attention-based EfficientNet-B7 in the backbone, which improves feature extraction. Furthermore, the bidirectional feature pyramid network in the neck network ensures multiscale feature fusion for detecting objects of varying sizes. It also integrates elliptical-geometric intersection over union to optimize anchor box accuracy and improve object localization. Due to its high efficacy in accurately detecting mangoes in aerial images, the proposed model is named as <italic>Aerial-MangoYOLOv8</i>. In addition, an Oriented FAST and Rotated BRIEF feature detector is used for tracking the detected mangoes to predict the yield. Rigorous experimental analysis demonstrates the superiority of the Aerial-MangoYOLOv8 model over other YOLO variants and state-of-the-art detection models.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"243-253"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667650","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}

{"title":"Optimized Coverage Map Representation for Bandwidth-Limited Data Exchange of Agricultural Vehicles","authors":"Marcel Moll;Samuel Brodie;Timo Oksanen","doi":"10.1109/TAFE.2026.3669618","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3669618","url":null,"abstract":"Sharing location-based data among multiple agricultural machines or with the cloud is a key enabler for cooperative farming in precision agriculture. Wireless communication is essential for real-time synchronization, but bandwidth remains limited, particularly when links are shared across multiple machines and applications. Reducing the amount of transmitted data is therefore a critical requirement. This article proposes an efficient message structure for coverage-map sharing, where polygons serve as the spatial representation of worked area. A globally applicable scaling method is developed to quantize geodetic coordinates at a user-defined resolution, independent of geographic location. In addition, polygon vertices are minimized without loss of relevant information and transmitted as relative coordinates using Google Protocol Buffers. Additional message-size reductions are achieved through optimized selection of a reference point for relative encoding, based on heuristics and a mixed-integer linear programming benchmark. Applied to a real-world dataset, the proposed approach achieves a compression ratio of <inline-formula><tex-math>$4.66$</tex-math></inline-formula> compared to previous implementations at a resolution of <inline-formula><tex-math>$2 ,text{c}text{m}$</tex-math></inline-formula>. These results demonstrate the potential of the method to reduce bandwidth demands and enable robust multimachine and cloud-based cooperation in agriculture.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"444-456"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11475315","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667674","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}