IEEE Transactions on AgriFood Electronics最新文献

{"title":"Silicon Microcuvette-Based Testing System for Optical Absorption Spectroscopy of Vegetable Oils","authors":"Suchismita Paul;Alakananda Das;Anirban Bhattacharyya","doi":"10.1109/TAFE.2025.3632316","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3632316","url":null,"abstract":"A fast and simple testing method for micro-nano liter volumes of agricultural products can be very advantageous in the food industry for quality control purposes. In this work, optical transmittance spectra of olive oils, heated to different temperatures, were compared using a custom-built test system. Results indicate that testing at two specific wavelengths of 370 nm and 470 nm is sufficient to determine their state of oxidation and to distinguish them from other oils. A novel microcuvette (μCUV) was designed with integrated heating as well as optical detection capabilities for this purpose. Silicon micromachining techniques were used to fabricate an inverted pyramidal structure, with an opening 750 μm × 750 μm, sidewall slope of 54.7° and an optical window of 30 μm <italic>×</i> 30 μm at the bottom. To carry real-time spectroscopic measurements, while maintaining a liquid under test at controlled elevated temperatures, microheater structures surrounding the μCUV were designed. The design parameters were the dimensions of the silicon structure, microheater geometry, thickness of the heating element, and inter-element spacing. While several geometries were compared, simulation results indicate that due to the sloped sidewalls of the μCUV and presence of corners, multiple specially designed heaters at the top as well as the bottom of the structure are necessary to obtain a temperature variation of less than 8% across the inner surface of the μCUV. The silicon-based system can be directly integrated into on-chip control electronics catering to a wide range of applications. We propose a fast and versatile liquid test system based on our results.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"262-269"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667682","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":"Size-Adaptive Density Map Estimation and Multiscale Feature Extraction Network for Robust Prawn Postlarvae Counting","authors":"Thai-Ha Dang;Fabio Dos Santos Neto;Xinrong Li;Breana Smithers;Edward Mager;Miguel Acevedo","doi":"10.1109/TAFE.2026.3653433","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3653433","url":null,"abstract":"Accurate prawn postlarvae counting is critical for optimizing aquaculture production and management. Traditional manual counting methods are labor-intensive and prone to errors, while existing automated approaches face challenges, such as small object sizes, overlapping instances, and variations in postlarvae dimensions. To address these limitations, we propose P2CountNet, a novel deep-learning framework that integrates size-adaptive density map estimation with a multiscale feature extraction network for precise and robust prawn postlarvae counting. The size-adaptive density map dynamically adjusts to varying postlarvae sizes, ensuring accurate counting even in dense and heterogeneous environments. Meanwhile, the multiscale feature extraction network captures features across multiple resolutions, effectively detecting tiny and overlapping postlarvae. Experimental evaluations on a newly curated prawn postlarvae dataset demonstrate that P2CountNet significantly outperforms state-of-the-art counting methods, achieving lower mean absolute error and mean squared error. Notably, the proposed method achieves an average counting accuracy of 94.32% for testing datasets. Key contributions include the development of the size-adaptive density estimation technique, the design of a multiscale feature extraction network tailored for small object counting, and extensive evaluations validating the approach. This work provides a robust and efficient solution for prawn postlarvae counting, with promising applications in advancing aquaculture practices.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"292-305"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667685","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":"Sensor-Based Assessment of Plant–Microbe Energy Interactions","authors":"Alessandro Zompanti;Miriana D'Addesa;Bruno Carneiro;Giorgio Pennazza;Etelvina Figueira;Simone Grasso;Anna Sabatini;Davide Cacciari;Luca Vollero;Gil Gonçalves;Marco Santonico","doi":"10.1109/TAFE.2026.3658999","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3658999","url":null,"abstract":"The BIONOTE-L voltametric sensor was used in this work to exploit cyclic voltammetry as an operating principle to interact with the plant/soil system. Indeed, in bacteria, the metabolic process oxidizes organic compounds from the soil organic matter with extracellular electron transfer. Plants can also release electrons into the rhizosphere—in what are known as plant microbial fuel cells (PMFCs). The electrons obtained, when appropriately conveyed, generate an electric current. On this basis, the innovation of a sensor system “interrogating” the plant/soil system via cyclic voltammetry is proposed. This work tries to place a new paradigm: Rather than exploiting the energy autonomously produced, the plant-microorganism system and the interaction that occurs between them can be analyzed in energetic terms, which is novel with respect to the standard approach measuring other parameters related to plant growth. An external input is provided, and the response of the system to this solicitation is observed. The energy extracted does not have the purpose of powering other devices or being stored. Instead, it is treated as data on the state of health of the plant-microorganism system. This test has been structured as a step-by-step experimental investigation, with a gradual increase in complexity. The BIONOTE-L was tested to analyze the behavior of four different genera of bacteria in solution: <italic>Rhizobium</i>, <italic>Bacillus</i>, <italic>Enterobacter</i>, and <italic>Kosakonia</i>. The behavior of <italic>Bacillus</i> was then analyzed in interaction with the soil and with a corn plant (<italic>Zea mays</i> L.). The gradual growth of the bacteria in the solution was assessed using a spectrophotometer (optical density: O.D.) and predicting O.D. with BIONOTE-L with root mean square errors in cross validation from 0.004 to 0.2 (depending on the different bacteria). Specific fingerprints were detected for each hour of bacterial growth (therefore specific for the concentration of bacteria in solution) and for each different genus of bacteria. Finally, the electrical response of <italic>Bacillus</i> in interaction with the soil and plant was characterized, thus providing a specific electrical signature to be monitored in a real-world scenario.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"365-374"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11411895","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667681","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":"Guest Editorial: Special Section on Cutting-Edge Agritech: Modeling, Control, and Sensor Networks for Sustainable Agricultural Practices","authors":"Paola Battilani;Daniele Trinchero","doi":"10.1109/TAFE.2026.3679822","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3679822","url":null,"abstract":"","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"37-38"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11481202","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509669","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":"SPQ: Similarity-Preserving Posttraining Quantization for Portable Crop Disease Detection","authors":"Carlos Victorino Padeiro;Tse-Wei Chen;Takahiro Komamizu;Ichiro Ide","doi":"10.1109/TAFE.2025.3533416","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3533416","url":null,"abstract":"The traditional method of diagnosing crop diseases through expert visual observations is expensive, time-consuming, and prone to errors. Deep neural networks (DNNs), specifically, convolutional neural networks (CNNs), offer promising alternatives, but are not easily accessible to local farmers, due to high resource requirements and reliance on network connectivity. Lightweight models that can operate on resource-limited devices and without network access are crucial to address this gap. Although quantization offers a promising solution for building lightweight models for crop disease detection, it often reduces quality. To address this issue, this article introduces a similarity-preserving quantization (SPQ) method to convert high-precision DNNs (particularly, CNNs in this article) into lower precision models while maintaining similar feature representations. SPQ ensures comparable activation patterns for similar crop images in both the original and quantized models. Experimental results using the MobileNetV2 and ResNet-50 backbones as base full-precision models demonstrate that SPQ improves memory footprint more than three times while preserving the detection performance, and show superior performance to the state-of-the-art quantization methods, especially when the target bit-widths are narrower.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"68-80"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148510705","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":"Robust Model Predictive Control for the Optimal Operation of the Indoor Environment of a Cluster of Smart Greenhouses","authors":"Ehsan Ghorbani;Ahmed Ouammi;Hanane Dagdougui","doi":"10.1109/TAFE.2025.3619458","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3619458","url":null,"abstract":"Smart greenhouses can be defined as cutting-edge technological systems that efficiently control indoor climate conditions to protect crops from harsh outdoor conditions to increase their productivity. In this article, we developed and implemented a robust model predictive control approach that relies on a recursive state estimation method to cope with the impact of measurement and process signal errors. The aim of this approach is to optimally control the internal environment of intelligent greenhouses. A feedback policy problem is decomposing signals for the accessibility of uncertainties. Then, a robust feasibility set can be defined by determining the ellipsoid set on uncertainty to obtain solvable constrained optimization in the CPLEX solver. In the overall formulation, each greenhouse is considered as an independent element. This method can improve the quality of set-point tracking while reducing the computation time required to arrive at a solution. Extensive numerical simulations involving the application of an innovative and robust algorithm to a cluster of greenhouses were conducted to demonstrate the algorithm’s performance and effectiveness.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"81-90"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148510709","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":"ADA-Net: A Lightweight Model for Apple Flower Maturity Detection in Horticultural Plant Monitoring","authors":"Rongfeng Xu;Weikuan Jia;Jingyu Yan;Xiude Chen","doi":"10.1109/TAFE.2025.3615644","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3615644","url":null,"abstract":"In modern orchards, the pollination process of apple blossoms plays a crucial role in determining both the quality and yield of the fruit. While most current studies concentrate on identifying individual apple flowers, there is limited research on assessing the developmental stages of apple flowers in dynamic and complex orchard settings. Challenges arise due to the intricate environmental factors and subtle color changes in the anthers following the maturation of the apple flowers, which complicate accurate detection. To overcome these challenges, ADA-Net, an efficient YOLOv8n-based detection model, is proposed to evaluate the maturity stages of apple flowers. First, the adaptive downsampling network module replaces the conventional downsampling convolution, which reduces the size of the convolutional kernels and groups input feature mean average precision (maps). This modification helps reduce the model’s parameter count and computational complexity, while simultaneously improving detection of small targets. In addition, inspired by the task alignment technique of the task-aligned one-stage object detection (TOOD) model, a DAD Head is employed to separate the classification from localization tasks, thus minimizing task interference and improving overall accuracy. A custom apple flower dataset is used to test the model, and the results show detection accuracies of 80.7% for mature flowers and 82.4% for immature flowers, with a total model parameter count of just 1.8 million. These results offer important insights for advancing the development of automated pollination systems in orchards.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"145-156"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148511604","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":"AgTrust: Framework for Securing Critical Agriculture Technology and Emerging Solutions","authors":"Mir Ali Rezazadeh Baee;Leonie Simpson;Luke Kane;Warren Armstrong;Praveen Gauravaram","doi":"10.1109/TAFE.2025.3634060","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3634060","url":null,"abstract":"Agriculture technology (AgTech) applies emerging technologies, such as the Internet of Things (IoT), sensors, and artificial intelligence to collect, transmit, and process information related to agricultural enterprises. AgTech solutions involve many interconnected systems, each with a range of security vulnerabilities that may impact data trustworthiness. To engage AgTech effectively, a framework is necessary for providing assurances that data used for decision making can be trusted. This article introduces a novel framework “AgTrust” that provides a cohesive solution for enabling trust in farming ecosystems. This includes assurances of data integrity, data quality, and data provenance supported by anomaly detection, quantum-safe encryption, authentication, and the underlying key-management mechanisms. The AgTrust framework is a modular design, intended for flexibility to enable implementation in a range of context and to meet the challenges of a rapidly evolving threat landscape using appropriate security mechanisms to ensure data trustworthiness. The modules providing various security functions can be adapted to future-proof the AgTech development and can be applied to other IoT or smart-device-based networks. The AgTrust framework specifies the functionality required across various layers and services and coordinates interactions between functions. Four case study examples related to the implementation of the AgTrust framework in real-world scenarios are presented and discussed.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"207-223"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148513320","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":"Energy-Efficient Edge–Cloud IoT-Based Architecture for Automated Hive Monitoring of Pollinator Species in Precision Agriculture","authors":"Karminder Singh;Milanpreet Kaur;Suman Kumar","doi":"10.1109/TAFE.2026.3653801","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3653801","url":null,"abstract":"Pollinator insect species play a vital role in crop pollination and precision agriculture. Certain insect species are facing a decline due to the excessive use of fertilizers and climate change, putting global food security at risk and necessitating continuous automated surveillance. Existing surveillance systems suffer from high power consumption due to the processing of large volumes of captured data on resource-constrained hardware. To address these challenges, this study presents a sensing system that overcomes the inefficiencies of traditional detection frameworks through a proposed on-device, energy-efficient architecture. The designed architecture integrates a customized framework that streamlines the processing pipeline, thereby reducing computational load, on-device energy usage, and transmission-related power consumption. Experimental results demonstrate that the proposed architecture significantly reduces energy consumption compared to traditional frameworks. These reductions translate into a substantial improvement in battery life, ranging from 38% to 107% across different operational conditions. Moreover, to enable remote surveillance, stable Internet connectivity is required, which is unfeasible in rural regions. Therefore, the proposed sensing system enables remote optimized data extraction features without disrupting ongoing processes, ensuring seamless functionality in both high and low internet connectivity regions by utilizing 4G cloud-based transmission in the former and local Wi-Fi hotspot access in the latter. Overall, the proposed system outperforms existing systems with significantly lower current consumption and extended battery lifetime.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"306-320"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147667660","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":"Sustainable Paper-Based NFC Tag for On-Field Humidity Sensing","authors":"Sonia Gomez-Gijon;Yann Houeix;Pietro Ibba;Sahira Vasquez;Francisco J. Romero;Paolo Lugli;Luisa Petti;Almudena Rivadeneyra","doi":"10.1109/TAFE.2025.3633440","DOIUrl":"https://doi.org/10.1109/TAFE.2025.3633440","url":null,"abstract":"Extreme weather conditions due to climate change are drastically calling for crop health supervision in agriculture via suitable technologies able to wirelessly, distributively, and sustainably monitor relevant parameters. In this work, we present a wireless, eco-friendly capacitive humidity sensor tag, fabricated via dispense printing on biodegradable paper. The device consists of an near-field communication (NFC) antenna made of biocompatible silver ink and an interdigitated electrode (IDE) sensor using biodegradable carbon ink. The sensor and antenna response to humidity was evaluated in a climatic chamber, showing a strong correlation and sensitivity to increasing and decreasing relative humidity (RH) values. The antenna was designed and characterized to resonate at the NFC frequency of 13.56 MHz. In addition, the encapsulation of the entire device was evaluated, showing minimal variation in the antenna response while enhancing the average sensitivity (0.63% /% RH) and stability of the RH sensing. Placed near a plant, this eco-friendly wireless device can estimate crop drought stress and support optimal water resource utilization while minimizing environmental impact, thereby paving the way for sustainable agricultural practices.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 1","pages":"29-36"},"PeriodicalIF":0.0,"publicationDate":"2026-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148509757","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}