Query：
学者姓名：叶大鹏
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
本实用新型公开了一种茶叶视觉分析剔除装置，包括支架、输送平台、控制系统、摄像分析系统、升降结构、吸附结构和分离结构。所述控制系统、摄像分析系统、升降结构和吸附结构之间电性连接，所述升降结构设置在所述支架上，所述吸附结构包括负压吸附源和吸附枪，所述吸附枪设置在所述升降结构上，所述升降结构能驱动所述吸附枪垂直于所述输送平台升降，其特征在于，还包括分离结构，所述分离结构包括分离筒，所述分离筒套设在所述吸附枪外，当所述升降结构带动所述吸附枪下降时，所述分离筒的端面能先于所述吸附枪压紧在所述输送平台的表面。本茶叶视觉分析剔除装置，可减少分析剔除过程中合格嫩芽误剔除数量，从而降低生产成本。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 叶大鹏 , 高宇轩 , 翁海勇 et al. 一种茶叶视觉分析剔除装置 : CN202420828912.7[P]. | 2024-04-19 . |
| MLA | 叶大鹏 et al. "一种茶叶视觉分析剔除装置" : CN202420828912.7. | 2024-04-19 . |
| APA | 叶大鹏 , 高宇轩 , 翁海勇 , 陈明夏 , 黄德耀 . 一种茶叶视觉分析剔除装置 : CN202420828912.7. | 2024-04-19 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
本发明提出一种确定冬笋探测装置最佳微波发射信号频段的方法，通过测定冬笋以及竹林内土壤的含水率和介电特性，分析不同微波信号频率对应冬笋和土壤介电特性的变化规律以及不同含水率下土壤的介电特性的变化情况，将冬笋以及土壤含水率之间的差异转化为介电特性的差异；根据测得的介电特性大小，分析冬笋与土壤之间介质损耗因素最大的频段范围，作为天线带宽；构建不同含水率下的冬笋‑土壤介电模型以分析对天线发射信号S参数的影响，以确定冬笋探测装置最佳微波发射信号频段的中心频率。并通过天线辐射方向图进一步验证最佳微波发射信号频段的中心频率。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 谢立敏 , 赵杰 , 刘永强 et al. 一种确定冬笋探测装置最佳微波发射信号频段的方法 : CN202411951339.X[P]. | 2024-12-27 . |
| MLA | 谢立敏 et al. "一种确定冬笋探测装置最佳微波发射信号频段的方法" : CN202411951339.X. | 2024-12-27 . |
| APA | 谢立敏 , 赵杰 , 刘永强 , 叶大鹏 , 余锦旭 . 一种确定冬笋探测装置最佳微波发射信号频段的方法 : CN202411951339.X. | 2024-12-27 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
针对毛边锯材清边锯切时，锯材边缘尺寸人工目测及下锯位置确定环节效率低下的问题，文章设计了基于机器视觉的自动化检测系统。选用CCD工业相机、锯材自动化输送机构等硬件搭建机器视觉检测系统。基于LabVIEW软件的机器视觉开发平台功能，可以实现锯材图像的采集、处理、边缘识别和几何测量。实验数据表明：系统对锯材有效宽度测量与人工测量的误差小于2 mm，检测效率达到12块/分钟。锯材机器视觉检测系统采集的图像信息，可为自动清边机的锯材姿态调整，多片锯间隙自适应调整提供依据，提高锯材加工装备的自动化水平。
Keyword ：
机器视觉 机器视觉 检测 检测 清边机 清边机 锯材 锯材
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 李海芸 , 邱荣斌 , 董楸煌 et al. 锯材自动清边机机器视觉检测系统的设计 [J]. | 木工机床 , 2025 , 4 (02) : 1-3,9 . |
| MLA | 李海芸 et al. "锯材自动清边机机器视觉检测系统的设计" . | 木工机床 4 . 02 (2025) : 1-3,9 . |
| APA | 李海芸 , 邱荣斌 , 董楸煌 , 叶大鹏 . 锯材自动清边机机器视觉检测系统的设计 . | 木工机床 , 2025 , 4 (02) , 1-3,9 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Liquid culture is a nutrient-rich liquid medium used to grow and study microorganisms, yet it is highly vulnerable to contamination, which only can be observed at the symptomatic stage when turbidity appears, leaving limited opportunities for timely intervention. Optical chemometrics has been extensively explored for determination of contamination by analyzing the absorption spectra of specific molecular bands. However, its effectiveness is often constrained in complex solutions due to water's strong absorption. To this end, this study presents a rapid, non-invasive optical approach that combines micro-hyperspectral imaging with machine learning to explore scattering characteristics for the early detection of microbial contamination. First, micro-hyperspectral imaging data were collected using the transmittance mode. Secondly, hyperspectral data was processed with feature selection algorithms-Random Frog (RF), Competitive Adaptive Reweighted Sampling (CARS), and Uninformative Variable Elimination (UVE) to reduce the dimensionality of the original hyperspectral data. Thirdly, machine learning models, including Neural Networks (NN), k-Nearest Neighbors (kNN), Support Vector Machine (SVM), and Partial Least Squares Discriminant Analysis (PLSDA), were trained using the selected feature vectors. The experimental results demonstrated that the combination of PLSDA and CARS achieved the highest accuracy of 89.4% in detecting asymptomatic microbial contamination, 99.2% in uncontaminated and 99.7% in contaminated liquid culture. Finally, Mie scattering simulations were conducted to confirm the characteristic scattering patterns associated with early microbial contamination. Overall, this study highlights the effectiveness of integrating Mie scattering, hyperspectral imaging, and machine learning to enable a rapid optical approach for early detection of microbial contamination in liquid cultures. © 2025 ASABE. All rights reserved.
Keyword ：
Brillouin scattering Brillouin scattering Contamination Contamination Data handling Data handling Discriminant analysis Discriminant analysis Feature extraction Feature extraction Hyperspectral imaging Hyperspectral imaging Learning systems Learning systems Least squares approximations Least squares approximations Motion compensation Motion compensation Nearest neighbor search Nearest neighbor search Neural networks Neural networks Support vector machines Support vector machines Water absorption Water absorption
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Libin , Weng, Haiyong , Sun, Shangpeng et al. Integrating Micro-Hyperspectral Imaging and Mie Scattering for Early Detection of Microbial Contamination in Liquid Culture [C] . 2025 . |
| MLA | Wu, Libin et al. "Integrating Micro-Hyperspectral Imaging and Mie Scattering for Early Detection of Microbial Contamination in Liquid Culture" . (2025) . |
| APA | Wu, Libin , Weng, Haiyong , Sun, Shangpeng , Ye, Dapeng . Integrating Micro-Hyperspectral Imaging and Mie Scattering for Early Detection of Microbial Contamination in Liquid Culture . (2025) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
为了满足机器人学课程的实验教学需求，设计了笛卡尔坐标机器人实验教学平台。该实验教学平台选用通用的零部件进行积木式装配，控制系统上、下位机分别采用普通PC机和STM32单片机，并集成工业相机和控制手柄等设备。基于该实验教学平台设计了运动学分析、运动控制和机器视觉等渐进式实验教学项目，有利于初学机器人学课程的学生通过辅助的实验教学，更直观的理解机器人学原理，并为进一步学习构型更加复杂的机器人知识和技术奠定基础，从而实现对学生的知识、能力和素质的全面培养。
Keyword ：
实验教学 实验教学 机器人运动学 机器人运动学 机器视觉 机器视觉 笛卡尔坐标机器人 笛卡尔坐标机器人
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 李海芸 , 董楸煌 , 叶大鹏 . 笛卡尔坐标机器人实验教学平台构建与探索 [J]. | 机电技术 , 2025 , 6 (01) : 95-100 . |
| MLA | 李海芸 et al. "笛卡尔坐标机器人实验教学平台构建与探索" . | 机电技术 6 . 01 (2025) : 95-100 . |
| APA | 李海芸 , 董楸煌 , 叶大鹏 . 笛卡尔坐标机器人实验教学平台构建与探索 . | 机电技术 , 2025 , 6 (01) , 95-100 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
BackgroundRice blast is one of the most destructive diseases in rice cultivation, significantly threatening global food security. Timely and precise detection of rice panicle blast is crucial for effective disease management and prevention of crop losses. This study introduces ConvGAM, a novel semantic segmentation model leveraging the ConvNeXt-Large backbone network and the Global Attention Mechanism (GAM). This design aims to enhance feature extraction and focus on critical image regions, addressing the challenges of detecting small and complex disease patterns in UAV-captured imagery. Furthermore, the model incorporates advanced loss functions to handle data imbalances effectively, supporting accurate classification across diverse disease severities.ResultsThe ConvGAM model, leveraging the ConvNeXt-Large backbone network and the Global Attention Mechanism (GAM), achieves outstanding performance in feature extraction, crucial for detecting small and complex disease patterns. Quantitative evaluation demonstrates that the model achieves an overall accuracy of 91.4%, a mean IoU of 79%, and an F1 score of 82% on the test set. The incorporation of Focal Tversky Loss further enhances the model's ability to handle imbalanced datasets, improving detection accuracy for rare and severe disease categories. Correlation coefficient analysis across disease severity levels indicates high consistency between predictions and ground truth, with values ranging from 0.962 to 0.993. These results confirm the model's reliability and robustness, highlighting its effectiveness in rice panicle blast detection under challenging conditions.ConclusionThe ConvGAM model demonstrates strong qualitative advantages in detecting rice panicle blast disease. By integrating advanced feature extraction with the ConvNeXt-Large backbone and GAM, the model achieves precise detection and classification across varying disease severities. The use of Focal Tversky Loss ensures robustness against dataset imbalances, enabling accurate identification of rare disease categories. Despite these strengths, future efforts should focus on improving classification accuracy and adapting the model to diverse environmental conditions. Additionally, optimizing model parameters and exploring advanced data augmentation techniques could further enhance its detection capabilities and expand its applicability to broader agricultural scenarios.
Keyword ：
ConvNeXt ConvNeXt FocalTverskyLoss FocalTverskyLoss GAM GAM Rice blast Rice blast Semantic segmentation Semantic segmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Shaodan , Huang, Deyao , Wu, Libin et al. UAV rice panicle blast detection based on enhanced feature representation and optimized attention mechanism [J]. | PLANT METHODS , 2025 , 21 (1) . |
| MLA | Lin, Shaodan et al. "UAV rice panicle blast detection based on enhanced feature representation and optimized attention mechanism" . | PLANT METHODS 21 . 1 (2025) . |
| APA | Lin, Shaodan , Huang, Deyao , Wu, Libin , Cheng, Zuxin , Ye, Dapeng , Weng, Haiyong . UAV rice panicle blast detection based on enhanced feature representation and optimized attention mechanism . | PLANT METHODS , 2025 , 21 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
UAV image acquisition and deep learning techniques have been widely used in field hydrological monitoring to meet the increasing data volume demand and refined quality. However, manual parameter training requires trial-and-error costs (T&E), and existing auto-trainings adapt to simple datasets and network structures, which is low practicality in unstructured environments, e.g., dry thermal valley environment (DTV). Therefore, this research combined a transfer learning (MTPI, maximum transfer potential index method) and an RL (the MTSA reinforcement learning, Multi-Thompson Sampling Algorithm) in dataset auto-augmentation and networks auto-training to reduce human experience and T&E. Firstly, to maximize the iteration speed and minimize the dataset consumption, the best iteration conditions (MTPI conditions) were derived with the improved MTPI method, which shows that subsequent iterations required only 2.30% dataset and 6.31% time cost. Then, the MTSA was improved under MTPI conditions (MTSA-MTPI) to auto-augmented datasets, and the results showed a 16.0% improvement in accuracy (human error) and a 20.9% reduction in standard error (T&E cost). Finally, the MTPI-MTSA was used for four networks auto-training (e.g., FCN, Seg-Net, U-Net, and Seg-Res-Net 50) and showed that the best Seg-Res-Net 50 gained 95.2% WPA (accuracy) and 90.9% WIoU. This study provided an effective auto-training method for complex vegetation information collection, which provides a reference for reducing the manual intervention of deep learning.
Keyword ：
auto-DL method auto-DL method data augmentation automatic data augmentation automatic network training automatic network training automatic reinforcement learning for DL reinforcement learning for DL segmentation deep learning segmentation deep learning vegetation detection vegetation detection
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Yayong , Zhou, Beibei , Chen, Xiaopeng et al. A method of deep network auto-training based on the MTPI auto-transfer learning and a reinforcement learning algorithm for vegetation detection in a dry thermal valley environment [J]. | FRONTIERS IN PLANT SCIENCE , 2025 , 15 . |
| MLA | Chen, Yayong et al. "A method of deep network auto-training based on the MTPI auto-transfer learning and a reinforcement learning algorithm for vegetation detection in a dry thermal valley environment" . | FRONTIERS IN PLANT SCIENCE 15 (2025) . |
| APA | Chen, Yayong , Zhou, Beibei , Chen, Xiaopeng , Ma, Changkun , Cui, Lei , Lei, Feng et al. A method of deep network auto-training based on the MTPI auto-transfer learning and a reinforcement learning algorithm for vegetation detection in a dry thermal valley environment . | FRONTIERS IN PLANT SCIENCE , 2025 , 15 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Biomass monitoring of mushroom liquid strains during the fermentation process demands real-time analysis with minimal manual intervention, highlighting the urgent need for intelligent surveillance. This study introduced a soft sensor method based on edge computing machine vision, termed Edge CV, for in situ non-invasive estimation of biomass. In our experiment, the hardware of the Edge CV system includes the Jetson Nano with 4 GB RAM, 64 GB ROM, and a 128-core Maxwell GPU for executing intelligent machine vision tasks, along with embedded cameras for image data acquisition. Furthermore, a cascaded machine vision model was developed to enable biomass evaluation on the Edge CV system. The cascaded machine vision model mainly consists of three steps: first, the object detection task to locate the observation window, achieving a mean Average Precision (mAP50:95) of 82.3% with 78.7 GFLOPs; then, the segmentation task to extract liquid strain data within the observation window, yielding a mean intersection over union (MIoU) of 85.9% with 110.4 GFLOPs; and finally, calculating mycelium biomass indices via the morphological image processing task. The correlation between Edge CV inference and manual measurement showed an R2 of 0.963 and an RMSE of 0.027 for normalized biomass indices, demonstrating a robust and consistent trend. Therefore, this study illustrates the practical application of edge computing-based machine vision for biomass soft sensing during the fermentation process.
Keyword ：
biomass biomass edge computing edge computing liquid strain liquid strain machine vision machine vision soft sensing soft sensing
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wu, Libin , Xiao, Guimiao , Huang, Deyao et al. Edge Computing-Based Machine Vision for Non-Invasive and Rapid Soft Sensing of Mushroom Liquid Strain Biomass [J]. | AGRONOMY-BASEL , 2025 , 15 (1) . |
| MLA | Wu, Libin et al. "Edge Computing-Based Machine Vision for Non-Invasive and Rapid Soft Sensing of Mushroom Liquid Strain Biomass" . | AGRONOMY-BASEL 15 . 1 (2025) . |
| APA | Wu, Libin , Xiao, Guimiao , Huang, Deyao , Zhang, Xiandong , Ye, Dapeng , Weng, Haiyong . Edge Computing-Based Machine Vision for Non-Invasive and Rapid Soft Sensing of Mushroom Liquid Strain Biomass . | AGRONOMY-BASEL , 2025 , 15 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Trace amounts of antibiotics in water can accumulate in the human body through the food chain, posing significant health risks. Therefore, there is an urgent need to develop simple and effective methods for detecting antibiotics in water. In this study, we prepared electrochemical aptamer sensors based on carbon nanotubes@polystyrene sulfonate-gold nanoparticles/reduced graphene oxide (CNT@PSS-AuNPs/rGO) layered thin films for real-time, on-site detection of ciprofloxacin (CIP) in aquaculture environments, utilizing a portable sensing detection device. The CNT@PSS-AuNPs/rGO layered film offers an excellent specific surface area, providing ample binding sites for the aptamer. The functionalized CNT@PSS-AuNPs enhance the dispersibility and conductivity of the substrate material and increase the surface area of the electrode when loaded with rGO. Under optimal experimental conditions, the developed sensor exhibits a dynamic range from 4 ng/mL to 1.0 x 103 ng/mL and a limit of detection of 4 ng/mL (S/N = 3), demonstrating satisfactory sensitivity. The sensor also shows good stability, with a relative standard deviation of less than 1% after 100 repeated measurements. Moreover, when combined with a portable detection platform, CIP levels in aqueous environments can be analyzed intelligently, rapidly, and timely. Our study aims to promote simple and effective detection strategies, potentially extending their practical applications.
Keyword ：
CIP CIP Electrochemical sensor Electrochemical sensor Layered film Layered film Portability Portability Reduced graphene oxide Reduced graphene oxide
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Long, Bo , Zhang, Qian , Zhang, Lintong et al. Sensors based on CNT@PSS-AuNPs/rGO layered films for portable detection of ciprofloxacin [J]. | ADVANCED COMPOSITES AND HYBRID MATERIALS , 2025 , 8 (1) . |
| MLA | Long, Bo et al. "Sensors based on CNT@PSS-AuNPs/rGO layered films for portable detection of ciprofloxacin" . | ADVANCED COMPOSITES AND HYBRID MATERIALS 8 . 1 (2025) . |
| APA | Long, Bo , Zhang, Qian , Zhang, Lintong , Liu, Qi , Xing, Qiongqiong , Qu, Fangfang et al. Sensors based on CNT@PSS-AuNPs/rGO layered films for portable detection of ciprofloxacin . | ADVANCED COMPOSITES AND HYBRID MATERIALS , 2025 , 8 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
【目的】通过基于信号序列优化机器听觉模型的研究，为蜂群健康与活动状态的监测提供依据。【方法】在蜂箱内设置音频传感器，以非侵入性和无干扰性的方式持续记录6类蜂群音频，针对传统的音频分类方法中未考虑时序信息和分类准确度不高等问题，提出一种基于双向长短期记忆(bidirectional long short-term memory, BiLSTM)网络优化的多分类模型。基于梅尔频率倒谱系数提取音频特征，并构建以BiLSTM为基准的蜂群状态分类模型；引入卷积神经网络(convolutional neural network, CNN)和自注意力机制(self-attention mechanism, SA)对BiLSTM的输入和输出进行优化；构建优化的CNN-BiLSTM-SA模型用于6类蜂群状态的精准识别。【结果】与CNN和BiLSTM模型相比，CNN-BiLSTM-SA模型的分类准确率最高，训练集和验证集准确率均大于0.990 0,测试集准确率为0.988 6,交叉验证平均准确率为0.981 5。【结论】CNN-BiLSTM-SA模型为蜂箱内蜂群状态精准识别提供了有效技术支持，有助于未来智能养蜂和音频传感监控的发展。
Keyword ：
卷积神经网络 卷积神经网络 双向长短期记忆 双向长短期记忆 机器听觉 机器听觉 自注意力机制 自注意力机制 蜂群状态 蜂群状态
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 叶大鹏 , 陈林杰 , 张林通 et al. 基于信号序列优化的蜂群状态精准识别机器听觉模型 [J]. | 福建农林大学学报(自然科学版) , 2025 , 54 (02) : 268-278 . |
| MLA | 叶大鹏 et al. "基于信号序列优化的蜂群状态精准识别机器听觉模型" . | 福建农林大学学报(自然科学版) 54 . 02 (2025) : 268-278 . |
| APA | 叶大鹏 , 陈林杰 , 张林通 , 张雯清 , 魏增辉 , 黄少康 et al. 基于信号序列优化的蜂群状态精准识别机器听觉模型 . | 福建农林大学学报(自然科学版) , 2025 , 54 (02) , 268-278 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
