Query：
学者姓名：魏萱
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
To enhance the economic benefits of jasmine tea, effective breeding and field management are imperative for increasing yield. Therefore, accurately evaluating the growth status of jasmine and obtaining precise phenotypic parameters are crucial. However, challenges arise in 3D phenotypic data collection and analysis due to the thin stems and small leaves characteristic of jasmine plants. This study develops a point cloud acquisition system utilizing the Kinect v2 camera, designed to meet the low-cost requirements for field 3D phenotypic data acquisition. For the point cloud registration problem of jasmine flowers, this study proposes an enhanced Random Sample Consensus (RANSAC) algorithm for coarse registration and a symmetric objective functionbased Iterative Closest Point (ICP) algorithm for fine registration. The proposed method introduces a computational step for evaluating dissimilarity vectors between sampled polygon edge lengths between the initial matching point selection and hypothetical transformation estimation phases in the conventional RANSAC framework, effectively mitigating potential erroneous pose hypotheses.For the ICP algorithm, error minimization is achieved through the utilization of surface normals from corresponding point pairs, allowing both meshes to move simultaneously in opposite directions, thus achieving accurate registration. The system processes the acquired point clouds through downsampling and normalization preprocessing, followed by coarse registration using an improved RANSAC algorithm and fine registration via an ICP algorithm that leverages objective function symmetry. This results in a comprehensive point cloud representation of the jasmine plant. Six phenotypic parameters were extracted: plant height, stem diameter, leaf area, leaf perimeter, stem angle, and leaf count. The results demonstrate that the registration rate of the improved RANSAC algorithm increased by up to 11.985 % during the flowering and fruiting stages, with gains of 7.19 % and 8.51 % during the seedling and growing stages, respectively. The enhanced ICP algorithm significantly outperformed the traditional algorithm, reducing execution time by an average of 0.287 s and decreasing the average reconstruction error by 1.39 cm. This corresponds to a 9.8 % enhancement in processing speed relative to the baseline method. These findings affirm that the proposed method achieves high accuracy and rapid reconstruction speeds in the 3D reconstruction of jasmine plants, offering a valuable reference for phenotypic detection research and applications in similar plant species.
Keyword ：
3D reconstruction 3D reconstruction Jasmine Jasmine Phenotypic acquisition Phenotypic acquisition Point cloud processing Point cloud processing
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wei, Xuan , Chen, Junxiang , Cai, Yueyue et al. Acquisition and analysis of jasmine plant phenotype based on 3D point clouds [J]. | MEASUREMENT , 2026 , 257 . |
| MLA | Wei, Xuan et al. "Acquisition and analysis of jasmine plant phenotype based on 3D point clouds" . | MEASUREMENT 257 (2026) . |
| APA | Wei, Xuan , Chen, Junxiang , Cai, Yueyue , Song, Qiming , Li, Xiaoli , Deng, Xiaolei . Acquisition and analysis of jasmine plant phenotype based on 3D point clouds . | MEASUREMENT , 2026 , 257 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Achieving efficient and accurate detection and localization of duck eggs in the unstructured environment of free-range duck sheds is crucial for developing automated egg-picking robots. This paper proposes an improved YOLOv5s-based model (YOLOv5s-MNKS) designed to enhance detection performance, reduce model complexity, and improve the robot's adaptability and operational efficiency in complex environments. The model utilizes MobileNetV3 as the backbone network, reducing the number of parameters and increasing detection speed. The Squeeze-and-Excitation Module is replaced with a Normalization-based Attention Module to improve feature extraction capability. Group Shuffle Convolution and Bidirectional Feature Pyramid Network are introduced in the Neck layer, enhancing multi-scale feature fusion while reducing parameter count. A Soft-CIoU-NMS loss function is also designed, which improves detection accuracy in scenarios involving dense stacking and occlusion by lowering the confidence of overlapping bounding boxes instead of directly eliminating them. Experimental results demonstrate that the mAP of YOLOv5s-MNKS reaches 95.6%, representing a 0.3% improvement over the original model, while the model size is reduced to 5.7 MB, approximately 40% of the original size. When deployed on the Jetson Nano embedded platform with TensorRT acceleration, the model achieves a detection frame rate of 22.3 frames per second. In simulated and real-world duck shed scenarios, the improved model accurately and quickly identifies and locates duck eggs in complex environments, including occlusion, stacking, and low lighting, demonstrating strong robustness and applicability. This research provides technical support for the future development of duck egg-picking robots.
Keyword ：
Attention mechanism Attention mechanism Duck egg detection Duck egg detection Duck egg-picking robot Duck egg-picking robot Lightweight model Lightweight model YOLOv5s YOLOv5s
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Jie, Dengfei , Wang, Jun , Wang, Hao et al. Real-time recognition research for an automated egg-picking robot in free-range duck sheds [J]. | JOURNAL OF REAL-TIME IMAGE PROCESSING , 2025 , 22 (2) . |
| MLA | Jie, Dengfei et al. "Real-time recognition research for an automated egg-picking robot in free-range duck sheds" . | JOURNAL OF REAL-TIME IMAGE PROCESSING 22 . 2 (2025) . |
| APA | Jie, Dengfei , Wang, Jun , Wang, Hao , Lv, Huifang , He, Jincheng , Wei, Xuan . Real-time recognition research for an automated egg-picking robot in free-range duck sheds . | JOURNAL OF REAL-TIME IMAGE PROCESSING , 2025 , 22 (2) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Near-infrared (NIR) spectroscopy, with its advantages of non-destructive analysis, simple operation, and fast detection speed, has been widely applied in various fields. However, the effectiveness of current spectral analysis techniques still relies on complex preprocessing and feature selection of spectral data. While data-driven deep learning can automatically extract features from raw spectral data, it typically requires large amounts of labeled data for training, limiting its application in spectral analysis. To address this issue, we propose a self-supervised learning (SSL) framework based on convolutional neural networks (CNN) to enhance spectral analysis performance with small sample sizes. The method comprises two learning stages: pre-training and fine-tuning. In the pre-training stage, a large amount of pseudo-labeled data is used to learn intrinsic spectral features, followed by fine-tuning with a smaller set of labeled data to complete the final model training. Applied to our own collected dataset of three tea varieties, the proposed model achieved a classification accuracy of 99.12%. Additionally, experiments on three public datasets demonstrated that the SSL model significantly outperforms traditional machine learning methods, achieving accuracies of 97.83%, 98.14%, and 99.89%, respectively. Comparative experiments further confirmed the effectiveness of the pre-training stage, with the highest accuracy improvement, reaching 10.41%. These results highlight the potential of the proposed method for handling small sample spectral data, providing a viable solution for improved spectral analysis.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhao, Rongyue , Li, Wangsen , Xu, Jinchai et al. A CNN-based self-supervised learning framework for small-sample near-infrared spectroscopy classification [J]. | ANALYTICAL METHODS , 2025 , 17 (5) : 1090-1100 . |
| MLA | Zhao, Rongyue et al. "A CNN-based self-supervised learning framework for small-sample near-infrared spectroscopy classification" . | ANALYTICAL METHODS 17 . 5 (2025) : 1090-1100 . |
| APA | Zhao, Rongyue , Li, Wangsen , Xu, Jinchai , Chen, Linjie , Wei, Xuan , Kong, Xiangzeng . A CNN-based self-supervised learning framework for small-sample near-infrared spectroscopy classification . | ANALYTICAL METHODS , 2025 , 17 (5) , 1090-1100 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
本发明涉及检测技术领域，具体涉及一种检测实验台，包括试管架，试管架包括多个试管槽，试管槽的顶部具有第一开口，底部具有第二开口和第三开口，第一开口上设置有柔性的袋体，袋体对第一开口进行封闭且深入到试管槽内，袋体与试管槽内壁之间具有气体空间；第二开口设置有第一电磁阀；温度控制装置包括温控组件、气泵、管道和与多个气体出口，气体出口分别与第三开口连通；气泵分别通过管道与多个气体出口连通；温控组件对管道进行加热或者冷却；本发明通过标签、柔性的袋体、第一电磁阀以及温度控制装置三者的结合，通入的气体能够在温控的同时形成气压，方便将试管顶起来一部分，使得操作人员能够看到被其他试管遮挡的试管的标签。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 伍鸿强 , 魏萱 , 李兰馨 et al. 一种检测实验台 : CN202510953555.6[P]. | 2025-07-11 . |
| MLA | 伍鸿强 et al. "一种检测实验台" : CN202510953555.6. | 2025-07-11 . |
| APA | 伍鸿强 , 魏萱 , 李兰馨 , 庄玮婧 . 一种检测实验台 : CN202510953555.6. | 2025-07-11 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Seeds are essential to the agri-food industry. However, their quality is vulnerable to biotic and abiotic stresses during production and storage, leading to various types of deterioration. Real-time monitoring and pre-sowing screening offer substantial potential for improved storage management, field performance, and flour quality. This study investigated diverse deterioration patterns in wheat seeds by analyzing 1000 high-quality and 1098 deteriorated seeds encompassing mold, aging, mechanical damage, insect damage, and internal insect infestation. Hyperspectral imaging (HSI) and computer vision (CV) were employed to capture surface data from both the embryo (EM) and endosperm (EN). Internal seed quality was further assessed using scanning electron microscopy, dissection, and standard germination tests. Both conventional machine learning algorithms and deep convolutional neural networks (DCNN) were employed to develop discriminative models using independent datasets. Results revealed that each data source contributed valuable information for seed quality assessment (validation set accuracy: 65.1-89.2 %), with the integration of HSI and CV showing considerable promise. A comparison of early and late fusion strategies led to the development of an end-to-end deep fusion model. The decision fusion-based DCNN model, integrating HSI-EM, HSI-EN, CV-EM, and CV-EN data, achieved the highest accuracy in both training (94.3 %) and validation (93.8 %) sets. Applying this model to seed lot screening increased the proportion of high-quality seeds from 47.7 % to 93.4 %. These findings were further supported by external samples and visualizations. The proposed end-to-end decision fusion DCNN model simplifies the training process compared to traditional two-stage fusion methods. This study presents a potentially efficient alternative for rapid, individual kernel quality detection and control during wheat production. (c) 2025 The Authors. Publishing services by Elsevier B.V. on behalf of KeAi Communications Co., Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
Keyword ：
Computer vision Computer vision Data fusion Data fusion Deep convolutional neural networks Deep convolutional neural networks Hyperspectral imaging Hyperspectral imaging Seed quality Seed quality
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Tingting , Li, Jing , Tong, Jinpeng et al. End-to-end deep fusion of hyperspectral imaging and computer vision techniques for rapid detection of wheat seed quality [J]. | ARTIFICIAL INTELLIGENCE IN AGRICULTURE , 2025 , 15 (3) : 537-549 . |
| MLA | Zhang, Tingting et al. "End-to-end deep fusion of hyperspectral imaging and computer vision techniques for rapid detection of wheat seed quality" . | ARTIFICIAL INTELLIGENCE IN AGRICULTURE 15 . 3 (2025) : 537-549 . |
| APA | Zhang, Tingting , Li, Jing , Tong, Jinpeng , Song, Yihu , Wang, Li , Wu, Renye et al. End-to-end deep fusion of hyperspectral imaging and computer vision techniques for rapid detection of wheat seed quality . | ARTIFICIAL INTELLIGENCE IN AGRICULTURE , 2025 , 15 (3) , 537-549 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Ensuring food safety has become a paramount global challenge, impacting both public health and societal stability. Antibiotics are a class of bacteriostatic agents used to treat animal diseases. However, antibiotics accumulate in food and pose a hazard to human health through the food chain. Traditional antibiotic testing requires well-equipped laboratories and professionals, so it is necessary to develop convenient testing methods. Biosensors have the advantages of excellent detection performance, simple operation, and easy design, which provide great potential for on-site detection. In this paper, nanoparticles are categorized into metal nano-particles, carbon nanoparticles, polymer nanoparticles and compound nanoparticles based on their composition. We summarize the suitability of nanoparticles for different biosensors and the reasons for this based on their properties. The development of portable intelligent detection devices in the field of on-site detection is summarized and outlooked. Finally, the main challenges and future opportunities for biosensors are discussed, providing a clear future direction for the detection of antibiotics in food samples.
Keyword ：
Antibiotics Antibiotics Biosensors Biosensors Food safety Food safety Intelligence Intelligence Nanoparticles Nanoparticles Sensitivity Sensitivity
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Long, Bo , Zhang, Qian , Zhang, Lintong et al. Recent advances in nanomaterial biosensors for the detection of antibiotics to ensure food safety [J]. | CHEMICAL ENGINEERING JOURNAL , 2025 , 521 . |
| MLA | Long, Bo et al. "Recent advances in nanomaterial biosensors for the detection of antibiotics to ensure food safety" . | CHEMICAL ENGINEERING JOURNAL 521 (2025) . |
| APA | Long, Bo , Zhang, Qian , Zhang, Lintong , Xing, Qiongqiong , Liu, Qi , Deng, Liying et al. Recent advances in nanomaterial biosensors for the detection of antibiotics to ensure food safety . | CHEMICAL ENGINEERING JOURNAL , 2025 , 521 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The degradation of edible fungi can lead to a decrease in cultivation yield and economic losses. In this study, a nondestructive detection method for strain degradation based on the fusion of hyperspectral technology and image texture features is presented. Hyperspectral and microscopic image data were acquired from Pleurotus geesteranus strains exhibiting varying degrees of degradation, followed by preprocessing using Savitzky-Golay smoothing (SG), multivariate scattering correction (MSC), and standard normal variate transformation (SNV). Spectral features were extracted by the successive projections algorithm (SPA), competitive adaptive reweighted sampling (CARS), and principal component analysis (PCA), while the texture features were derived using gray-level co-occurrence matrix (GLCM) and local binary pattern (LBP) models. The spectral and texture features were then fused and used to construct a classification model based on convolutional neural networks (CNN). The results showed that combining hyperspectral and image texture features significantly improved the classification accuracy. Among the tested models, the CARS + LBP-CNN configuration achieved the best performance, with an overall accuracy of 95.6% and a kappa coefficient of 0.96. This approach provides a new technical solution for the nondestructive detection of strain degradation in Pleurotus geesteranus.
Keyword ：
feature fusion feature fusion hyperspectral imaging hyperspectral imaging nondestructive detection nondestructive detection Pleurotus geesteranus Pleurotus geesteranus
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Jiang, Yifan , Shang, Jin , Cai, Yueyue et al. The Fusion of Focused Spectral and Image Texture Features: A New Exploration of the Nondestructive Detection of Degeneration Degree in Pleurotus geesteranus [J]. | AGRICULTURE-BASEL , 2025 , 15 (14) . |
| MLA | Jiang, Yifan et al. "The Fusion of Focused Spectral and Image Texture Features: A New Exploration of the Nondestructive Detection of Degeneration Degree in Pleurotus geesteranus" . | AGRICULTURE-BASEL 15 . 14 (2025) . |
| APA | Jiang, Yifan , Shang, Jin , Cai, Yueyue , Liu, Shiyang , Liao, Ziqin , Pang, Jie et al. The Fusion of Focused Spectral and Image Texture Features: A New Exploration of the Nondestructive Detection of Degeneration Degree in Pleurotus geesteranus . | AGRICULTURE-BASEL , 2025 , 15 (14) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Changes in plant physiological activities can be reflected by the water released, and diseases have latent and explosive characteristics within the plant body. Consequently, rapid and accurate monitoring of extremely weak water changes is challenging. Herein, based on the characteristic of free modification of molecular level end effector, three self-assembled covalent organic framework (COF) humidity films were first designed. A wearable sensor with COFs/Negative temperature coefficient/Interdigital electrodePEDOT: PSS&CuNWs/Polydimethylsiloxane (COFs/NTC/IDEPECu/PDMS) structure was developed using a mixture of MXene and CuNWs in an interdigital shape as the electrode, and a commercial NTC as the temperature sensitive film. Among them, the most outstanding sensitivity, response and resolution were 2.536 nA/% relative humidity (RH), 2737.23 % and 0.032 % RH, respectively, and there were a strong linear relationship between the current and RH in the range of 30-55 % RH. Finally, based on which constructed a sensing system for monitoring tomato gray mold, which can not only predict the future trend of leaf surface humidity changes through metaheuristic optimization algorithms, but also wirelessly transmit the collected data to the client, providing valuable reference for the true implementation of future artificial intelligence & internet of things.
Keyword ：
Biological stress Biological stress Covalent organic framework Covalent organic framework Metaheuristic optimization algorithm Metaheuristic optimization algorithm Plant physiological information Plant physiological information Wireless communication Wireless communication
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Huang, Liang , Cai, Yueyue , Huang, Peijie et al. Covalent self-assembled highly sensitive humidity sensing system with wireless communication for plant physiology perception under disease stress [J]. | CHEMICAL ENGINEERING JOURNAL , 2025 , 518 . |
| MLA | Huang, Liang et al. "Covalent self-assembled highly sensitive humidity sensing system with wireless communication for plant physiology perception under disease stress" . | CHEMICAL ENGINEERING JOURNAL 518 (2025) . |
| APA | Huang, Liang , Cai, Yueyue , Huang, Peijie , Liao, Ziqin , Tang, Yu , Pang, Jie et al. Covalent self-assembled highly sensitive humidity sensing system with wireless communication for plant physiology perception under disease stress . | CHEMICAL ENGINEERING JOURNAL , 2025 , 518 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
本发明涉及微胶囊技术领域，具体涉及一种燕窝藻油微胶囊制备方法及应用，方法包括将干燥的燕窝浸入蒸馏水中，浸泡后进行炖煮；炖煮后进行高压灭菌获得燕窝炖煮物，将燕窝炖煮物加入均质组件进行均质化处理获得均质燕窝；将均质燕窝和麦芽糊精形成壁材，壁材溶于水中形成壁材溶液，在壁材溶液中逐滴加入芯材藻油形成混合液；对混合液乳化形成乳液；本发明通过将燕窝炖煮物作为壁材使用，利用燕窝的糖蛋白的成膜性对芯材进行包裹，燕窝富含唾液酸衍生物，藻油富含DHA，糖蛋白形成的包膜和唾液酸清除羟基保护DHA免受氧化和降解；通过氮气作为发射气体，结合冷冻能保护蛋白不容易变质，冷冻使得胶束弹性下降，结合氮气加速和撞击结构提升均质效果。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张怡 , 李兰馨 , 邱靖玲 et al. 一种燕窝藻油微胶囊制备方法及应用 : CN202510984992.4[P]. | 2025-07-17 . |
| MLA | 张怡 et al. "一种燕窝藻油微胶囊制备方法及应用" : CN202510984992.4. | 2025-07-17 . |
| APA | 张怡 , 李兰馨 , 邱靖玲 , 曾红亮 , 潘磊 , 魏萱 . 一种燕窝藻油微胶囊制备方法及应用 : CN202510984992.4. | 2025-07-17 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The evolution of smart agriculture is increasingly dependent on high-resolution, real-time data acquisition to optimize crop management and resource use. Real-time plant monitoring sensors represent a critical technological advancement in this effort, enabling dynamic tracking of key physiological and environmental parameters. While recent innovations in flexible electronics, nanomaterials, and artificial intelligence have substantially improved the sensitivity and non-invasiveness of these sensors, their broader adoption remains constrained by limited long-term stability, signal cross-sensitivity in complex agricultural environments, and high production costs. This review provides a systematic overview of sensor advancements across three core areas-physical, chemical, and biosignal monitoring-highlighting emerging strategies such as low cost manufacturing, biodegradable substrates, and multimodal data fusion powered by edge computing. These approaches show significant potential in translating laboratory-level innovations into practical field applications. By evaluating current technologies and underscoring unresolved challenges, this review not only summarizes the state of the art, but also suggests future pathways to enhance the durability, affordability, and scalability of plant sensors in supporting sustainable agriculture.
Keyword ：
AI analytics AI analytics Multimodal sensing Multimodal sensing Nanomaterials Nanomaterials Real-time plant monitoring Real-time plant monitoring Smart agriculture Smart agriculture Sustainable agriculture Sustainable agriculture
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Bai, Yu , Liao, Ziqin , Shang, Jin et al. A review on real-time plant monitoring sensors for smart agriculture [J]. | CHEMICAL ENGINEERING JOURNAL , 2025 , 523 . |
| MLA | Bai, Yu et al. "A review on real-time plant monitoring sensors for smart agriculture" . | CHEMICAL ENGINEERING JOURNAL 523 (2025) . |
| APA | Bai, Yu , Liao, Ziqin , Shang, Jin , Gan, Wei , Kong, Xiangzeng , Wei, Xuan . A review on real-time plant monitoring sensors for smart agriculture . | CHEMICAL ENGINEERING JOURNAL , 2025 , 523 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
