IEEE Transactions on AgriFood Electronics最新文献

{"title":"Multiscale Reparameterized Deep Architecture for Efficient and Interpretable Livestock Verification","authors":"Manya Joshi;Chiranjit Pal;Sanjay Kumar Singh;Sameer Shrivastava","doi":"10.1109/TAFE.2026.3671987","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3671987","url":null,"abstract":"Reliable livestock identification is vital for traceability, health monitoring, and smart farm management. It is also increasingly important in the agricultural insurance sector to ensure accurate animal records and fair claim verification. However, existing deep learning models often rely on large backbones with high computational demands, limiting real-world deployment. This article presents <italic>EfficientVLDNet</i>, a lightweight and discriminative deep metric learning framework designed for fine-grained livestock verification using facial imagery. The proposed network incorporates a <italic>reparameterized convolutional refinement block</i> to enhance the structural diversity without additional inference cost and a <italic>multiscale fusion head</i> to unify local and global representations. An <italic>adaptive triplet loss</i> dynamically adjusts interclass margins according to sample difficulty, improving discriminative power and convergence stability. Experimental results on a curated sheep face verification dataset demonstrate that <italic>EfficientVLDNet</i> achieves a new state-of-the-art performance with <italic>95.28% accuracy</i>, <italic>0.79 precision</i>, <italic>0.61 recall</i>, and <italic>0.69 F1-score</i>, surpassing prior benchmarks while maintaining only <italic>6.84 M parameters</i>. Furthermore, comparison on the public <italic>SheepBreed</i> dataset confirms its competitive advantage, achieving <italic>97.8% accuracy</i> and an F1-score of <italic>95.0%</i>, outperforming existing models. Visualization through gradient-based explainability methods confirms that the proposed model consistently focuses on key biometric regions muzzle, eyes, and ears reflecting interpretable decision behavior. By unifying <italic>accuracy</i>, <italic>efficiency</i>, and <italic>interpretability</i>, <italic>EfficientVLDNet</i> establishes a new benchmark for fine-grained livestock verification and offers a deployable solution for on-device, real-time precision livestock management.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 2","pages":"549-561"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149131161","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":"Analyzing Correlative Interdependency of Environmental and Agricultural Practices Factors in Conventional Farming Through Data Analytics","authors":"Fawad Azeem;Zaki Masood;Muhammad Afzaal;Iffat Azeem","doi":"10.1109/TAFE.2026.3698548","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3698548","url":null,"abstract":"The conventional farming is dependent environmental factors as well agricultural practices factors (APFs). The environment factors (EFs) include humidity, solar intensity and temperature whereas APFs include, provision of nutrients, irrigation and pesticide sprays. The conventional farming is facing low agricultural yields that could be due to the cumulative as well as correlative interdependent impact of EFs and APFs resulting in inappropriate plant growth. This correlative interdependent factors impact is hard to analyze at large scale and requires controlled environment analysis keeping the environmental and agricultural practices same as of the conventional farming. In this research, the multifactor correlation indexing for the real field is performed to analyze the correlation of EFs and APFs and their impact on the plant growth. An incubator is designed to analyze the dynamics of large scale farming and establish a correlation index between the nutrients, soil characteristics and irrigation practices under the field ambient conditions. For the case study, the six month data of cotton field in Sindh Jamshoro was taken for study. The incubator is specialized machine with dual functions of maintaining the field data environment while maintaining field ambient temperature, humidity and solar irradiation. The second function of incubator is to monitor and record the soil parameters in real time, such as soil pH, moisture, conductivity, soil nutrients, Nitrogen (N), Potassium (K), and Phosphorous (P). The correlation indexing map revealed strong correlations between soil nutrient and irrigation and it was found that current traditional practices uses excess water with time dependent supplies of N, P, and K. It was further revealed that ambient temperature has good corelation with soil temperature that impact seeding. Currently, seed sowing practices time dependent with no proper sowing assessment frameworks. A significant amount of water, N, P, and K supplies can be saved while deploying sensors in a field for modern and precise farming practices.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 2","pages":"637-647"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149131597","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":"Hardware-Aware Open-Set Multispectral Authentication of Chinese Herbal Medicines Using Compact Vis-NIR Signatures","authors":"Mingkun Zhang;Chao Ma;Jiayu Huang;Sudan Chen;Mingtong Du;Huawei Niu;Jianwei Ma","doi":"10.1109/TAFE.2026.3723575","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3723575","url":null,"abstract":"Fast authentication of high-value Chinese herbal medicines requires sensing pipelines that are accurate in the laboratory, compact enough for field deployment, and robust to counterfeit sources not seen during training. Conventional visible-near infrared (Vis-NIR) studies often report closed-set classification using the full spectral vector, which gives limited guidance for designing a low-cost multispectral electronic detector. This article presents a hardware-aware open-set multispectral authentication framework for two representative herbal medicines, Codonopsis Radix and Pseudostellariae Radix. The study uses 1200 region-of-interest (ROI) Vis-NIR spectra spanning 365–980 nm, covering one authenticated reference group and three counterfeit-source groups for each herb. A stratified random ROI protocol is used as the main evaluation setting. The proposed workflow compares spectral preprocessing and class-balanced learning baselines, then couples training-only greedy band selection, compact multispectral index features, and a leave-one-counterfeit protocol for unseen counterfeit screening. On the original measurement grid, derivative-preprocessed spectra with a balanced radial-basis-function support vector machine achieved 89.75% accuracy, 86.09% macro-F1, and 0.9358 area under the receiver operating characteristic curve (AUROC) on the combined authentic-vs-counterfeit task. The compact-channel wrapper reached 0.8866 AUROC with nine selected channels and 0.9083 AUROC with 12 selected channels, reducing spectral channels by 71.0% and 61.3%, respectively. In leave-one-counterfeit authentication, the model assigned low authentic probability to several unseen counterfeit sources, reaching 0.9699 AUROC and 94.87% unseen-counterfeit recall when Counterfeit II was held out in the combined dataset. These results show that Vis-NIR measurements can serve not only as classifier inputs but also as a design basis for compact field-screening hardware.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 2","pages":"748-759"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149131991","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":"Smart Farming: Dual-Mode Soil Sensor for High-Precision Moisture and Salinity Estimation Using Frequency- and Time-Domain Analysis","authors":"Rasool Keshavarz;Javad Jafaryahya;Taro Kikuchi;Negin Shariati","doi":"10.1109/TAFE.2026.3721033","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3721033","url":null,"abstract":"Accurate and simultaneous measurement of soil moisture and salinity remains a significant challenge in precision agriculture, as most existing sensors are designed to measure only one parameter or suffer from reduced accuracy under varying soil conditions. This limitation affects irrigation management, crop productivity, and long-term soil health monitoring. This article presents a compact electronic sensing system for simultaneous monitoring of soil moisture and salinity, designed for precision agriculture, and intelligent irrigation management. The proposed sensor integrates dual-domain sensing within a unified electronic architecture, combining time-domain signal analysis with wideband frequency-domain measurements to improve parameter discrimination and measurement reliability. In the time-domain mode, a continuous-wave excitation signal is processed through an analog phase and magnitude detection circuit to extract phase difference (<inline-formula><tex-math>$Delta varphi $</tex-math></inline-formula>) and magnitude ratio, which are sensitive to changes in the dielectric properties of soil. In the frequency-domain mode, the system performs broadband analysis from 50 to 300 MHz to identify null-frequency shift (<inline-formula><tex-math>$Delta f$</tex-math></inline-formula>) and null-depth, enabling enhanced sensitivity to salinity-induced conductivity variations. A lightweight machine-learning model is implemented for real-time mapping of the extracted electronic sensing features to volumetric water content (VWC) and soil salinity levels, enabling calibration-free operation across different soil conditions. Experimental validation using soil samples with varying moisture and salinity concentrations demonstrates high measurement accuracy, achieving a mean squared error of 1.5% for VWC estimation and below 2.8% for salinity prediction.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 2","pages":"760-771"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149131998","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":"Detection-Driven Key-Frame Edge Offloading for Real-Time UAV Grape Bunch MOTS","authors":"Zhen Cao;Lammert Kooistra;Hilmy Baja;Wensheng Wang;João Valente","doi":"10.1109/TAFE.2026.3671664","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3671664","url":null,"abstract":"Real-time instance-level perception is required for UAV operations in vineyards, but on-board compute and rural uplinks preclude full-frame streaming and large models. We develop an edge-offloading pipeline in which a TensorRT-accelerated YOLOv8n on a Jetson Xavier NX performs detection-driven key-frame selection and region-of-interest (ROI) compression, while multiobject tracking and segmentation (MOTS) runs on an edge server. The onboard selector filters redundant frames using Intersection-over-Union matching. A three-thread parallelized schedule overlaps detection, selection, and compression. On two vineyard sequences (frontal and path-planned), FP16 TensorRT reduced detector latency by 48% (to 27.5 ms). The proposed offloading strategy discarded 54–69% of redundant frames, reducing bandwidth consumption to 23–27% via ROI-centric compression. While the end-to-end throughput (<inline-formula><tex-math>$approx$</tex-math></inline-formula> 1.3 FPS) is bounded by the detector, it supports online monitoring at typical vineyard flight speeds. Compared to a full-sequence baseline, our selective offloading significantly reduced identity switches (IDS) (from 40 to 6 in frontal views) and improved relative tracking accuracy by stabilizing association, improving tracking stability (notably reducing IDS) relative to a full-sequence baseline under bandwidth-constrained field operations, while absolute MOTS remains challenging in cluttered vineyard scenes.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 2","pages":"508-519"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11457748","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149133433","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":"Harvesting Point Localization of Tomatoes in a Greenhouse Environment","authors":"Jin Chen;Mingzhao Lou;Tiancheng Yu;Guoqiang Ren;Huanyu Jiang","doi":"10.1109/TAFE.2026.3718426","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3718426","url":null,"abstract":"The precise localization of tomatoes is crucial for the stable operation of harvesting robots. To improve the abilities of tomato detection and positioning in a greenhouse, this study proposed a method of harvesting point localization using deep learning. The method focused on tomatoes using a vertical vine training system in a greenhouse. By incorporating the Transformer-based cross stage partial transformer (C3TR) module to capture global dependencies, the proposed method improved the segmentation performance of the you only look once (YOLO)v5s-seg baseline. The harvesting point was obtained by extracting centroid of the segmentation contour. By incorporating fruit shape priors, this study proposes a tomato completion method under occlusion conditions. The experimental results show the improved model achieves 90.7%, 90.6%, 96.4%, and 0.907 in terms of precision, recall, mean average precision (mAP)@50, and F1 score, respectively. The performance of the improved model is superior to that of the YOLO series baseline models. This study designed the 2-D, 3-D localization, and robotic arm grasping experiment. The average pixel error of the 2-D experiment is 2.531, and the average space error is about 1.0 cm, which verifies the effectiveness and practicality of the method. This study can provide a theoretical basis and technical support for the development of intelligent tomato harvesting equipment.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 2","pages":"486-497"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130697","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":"Greenhouse Evaluation of Printed Paper-Based Sensors for Leaf-Level Humidity Monitoring in Tomato Leaves","authors":"Sahira Vasquez;Almudena Rivadeneyra;Pietro Ibba;Antonio Altana;Martina Aurora Costa Angeli;Sonia Gomez-Gijon;Paolo Lugli;Luisa Petti","doi":"10.1109/TAFE.2026.3713932","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3713932","url":null,"abstract":"Monitoring environmental conditions inside greenhouses is essential to optimize crop growth, improve water-use efficiency, and reduce resource consumption. Among these parameters, relative humidity (RH) strongly influences plant transpiration, stomatal regulation, and disease development. However, conventional sensors typically measure bulk environmental conditions and often fail to capture microclimatic variations near plant surfaces. In this work, we present a flexible paper-based impedimetric humidity sensor fabricated by dispense printing poly(3,4-ethylenedioxythiophene) polystyrene sulfonate interdigitated electrodes on a cellulose substrate. The sensor response was first characterized under controlled climate chamber conditions to evaluate its frequency-dependent impedance behavior, hysteresis under humidity cycling, and temperature cross-sensitivity, while mechanical robustness under bending deformation was also assessed. Subsequently, the device was deployed in the environment and attached to the abaxial leaf surface of tomato leaves to monitor the dynamics of local humidity. Measurements performed over four consecutive day–night cycles showed that the printed sensors reliably tracked environmental RH variations and exhibited good agreement with a commercial reference sensor. When positioned directly on the leaves, the sensors captured localized humidity dynamics influenced by plant transpiration and leaf microclimate effects. Additional humidity–temperature cross-sensitivity measurements confirmed that humidity remained the dominant parameter governing the sensor response within the investigated temperature range. These results demonstrate the potential of cost-effective, biodegradable printed sensors for in situ monitoring of plant microenvironments, providing a promising approach for scalable sensing platforms in precision agriculture and smart greenhouse management.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 2","pages":"710-719"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11664146","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149130905","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":"Learning to Pick: A Visuomotor Policy for Clustered Strawberry Picking","authors":"Zhenghao Fei;Wenwu Lu;Linsheng Hou;Zunzhong Ye;Chen Peng","doi":"10.1109/TAFE.2026.3655755","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3655755","url":null,"abstract":"Strawberries naturally grow in clusters, interwoven with leaves, stems, and other fruits, which frequently leads to occlusion. This inherent growth habit presents a significant challenge for robotic picking, as traditional percept-plan-control systems struggle to reach fruits amid the clutter. Effectively picking an occluded strawberry demands dexterous manipulation to carefully bypass or gently move the surrounding soft objects and precisely access the ideal picking point—located at the stem just above the calyx. To address this challenge, we introduce a strawberry-picking robotic system that learns from human demonstrations. Our system features a 4-DoF SCARA arm paired with a human teleoperation interface for efficient data collection. We propose the end pose assisted action chunking transformer (EPACT) to learn a fine-grained visuomotor policy. By incorporating end-pose supervision, our approach enables the robot to acquire dexterous manipulation skills such as pushing aside leaves or navigating tight clusters that are difficult to achieve with traditional pipelines. Experiments demonstrate that our method successfully transfers human-like dexterity to the robot, enabling clustered strawberry picking and outperforming imitation learning baselines, underscoring its potential for practical application in complex agricultural environments.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 2","pages":"462-470"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149131430","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":"Coupled Resonator-Based Microwave Sensor for Nitrogen Fertilizing Agents Monitoring in Precision Agriculture","authors":"Nima Karbaschi;Mehri Ziaee Bideskan;Zahra Abbasi","doi":"10.1109/TAFE.2026.3707438","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3707438","url":null,"abstract":"This work presents a high-sensitivity, coupled split-ring resonator (SRR)-based microwave sensor for real-time, noncontact monitoring of dissolved nitrogen-based fertilizer compounds in precision agriculture. The proposed design integrates a reader-tag architecture with a L-shaped coupled lines as a capacitive enhancement to improve electric field confinement and quality factor. The sensing potential of the proposed structure is experimentally evaluated for solutions from both ionic (ammonium chloride) and nonionic (urea) nitrogen fertilizing agent in a high concentration range of 0–6000 ppm. Results demonstrate significant amplitude variations of the transmission response (<inline-formula><tex-math>$S_{21}$</tex-math></inline-formula>) for <inline-formula><tex-math>$NH_{4}Cl$</tex-math></inline-formula> and a logarithmic frequency shift for urea, with limits of detection of 90 and 61 ppm, respectively. The proposed system resonates at approximately 1065 MHz (unloaded) and uniquely combines a wide dynamic range, robust sensitivity, and compatibility with on-field measurement conditions. These capabilities make it a strong candidate for integration into smart agriculture platforms.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 2","pages":"699-709"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149131756","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":"LeafCast: A Lightweight Edge-Deployable Network for Temporal Plant Growth Prediction","authors":"Ameer Tamoor Khan;Valentine Guzniczak;Signe Marie Jensen","doi":"10.1109/TAFE.2026.3698276","DOIUrl":"https://doi.org/10.1109/TAFE.2026.3698276","url":null,"abstract":"In this article, we present leaf-aware, lightweight, edge-ready conditional adversarial spatio-temporal predictor (LeafCast), a lightweight neural network for predicting future plant growth states from single early-stage observations. Where existing approaches rely on computationally expensive architectures that demand powerful hardware, LeafCast achieves comparable prediction quality with only 3.9 M parameters, a 55× reduction over standard Pix2Pix models. The key to this efficiency lies in three architectural innovations: plant-aware attention gates that direct computational resources toward biologically meaningful regions, texture refinement blocks that preserve fine leaf details despite the compact model size, and a crop-focused loss function that prioritizes growth regions over static background. We trained and evaluated LeafCast on 5669 paired images of mustard plants collected at the PhenoLab facility, University of Copenhagen. The model achieves 34.17 dB peak signal-to-noise ratio (PSNR) and 0.935 structural similarity index measure (SSIM) while requiring only 4.83 giga floating-point operations (GFLOP), enabling real-time inference at 83.60 ms per image with open neural network exchange (ONNX) optimization. An ablation study confirms independent contributions of each architectural component, and comparison against lightweight baselines demonstrates that domain-aware design outperforms generic compression strategies. These results demonstrate that high-quality plant growth prediction is achievable within the strict computational constraints of mobile and edge platforms, opening practical possibilities for in-field phenotyping and precision agriculture applications.","PeriodicalId":100637,"journal":{"name":"IEEE Transactions on AgriFood Electronics","volume":"4 2","pages":"627-636"},"PeriodicalIF":0.0,"publicationDate":"2026-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149133693","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}