检索结果-内蒙古大学图书馆

12th International electrical engineering Congress, iEECON 2024

作者： Deng, Xianghong Photong, Chonlatee Mahasarakham University Electrical And Computer Engineering Faculty Of Engineering Maha Sarakham Thailand Hunan Mechanical & Electrical Polytechnic Changsha China

ISBN: (纸本)9798350383591

Tea is the most favorite drink in the world and its demand seems to continuously increase;therefore, large amount of tea production while retaining high-quality tea is required for the marketplaces. However, based on many research literacies, the yield and quality of tea are possibly affected by a diversity of diseases, which would need high accuracy in identification in order to determine the most suitable treatment or specific preventive actions. In this study, the tea leaf disease identification based on the three most widely used convolutional Neural Networks VGG16, Resnet50, and DenseNet169 were examined and evaluated. By accommodating the relevant parameters of these three identification models and the learning rates, the performances of the three convolutional neural networks were analyzed and compared. The simulated test results showed that VGG16, Resnet50, and DenseNet169 achieved the highest accuracy rates of 90.6%, 95.2%, and 99.0%, respectively. DenseNet169 provided the fastest convergence speed and the highest accuracy among the models. In addition, the DenseNet169 showed the possibility of the precise diagnosis and identification of other crop leaf diseases as well. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Anomaly-Focused Augmentation Method for Industrial Visual Inspection

引用

IEEE Access 2025年 13卷 89118-89139页

作者： Lara, Melvin A. Hameed, Ibrahim A. Koziorek, Jiri Faculty of Electrical Engineering and Computer Science Department of Cybernetics and Biomedical Engineering Ostrava70800 Czech Republic Department of Mechanical Engineering and Technology Management Ås1433 Norway

In industrial inspection, the detection of surface defects—such as scratches, dents, or other defects—is crucial for ensuring product quality. However, the limited availability of annotated images of such defects poses challenges for developing reliable detection models. This paper proposes a novel image augmentation algorithm to address this limitation by generating synthetic imperfections from a small sample set. Unlike traditional approaches that augment entire images, the proposed approach isolates defects and applies spatial transformations (e.g., rotation, shear) before blending them into background images. This allows for the creation of diverse training datasets. The algorithm employs a 2D binary map to encode the spatial relationship between defect and background regions of images and then applies an AI-driven model to generate new realistic blended images. By leveraging a generator-discriminator framework, the augmentation process is iteratively refined during training to maintain the style and texture of the original imperfections. Experimental results show that the proposed method significantly enhances the performance of defect detection models compared to existing augmentation techniques while preserving the realism of the generated images. © 2013 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Autonomous Robotic Grasping and Sorting System for Industry 4.0 6

Deep Learning Based Autonomous Robotic Grasping and Sorting ...

引用

6th International Conference on Robotics and Automation in Industry, ICRAI 2024

作者： Arsalan, Muhammad Imran, Abid Shah, Syed Salman Malaika, Sahar Iqbal, Zar Afshan GIK Institute Faculty of Mechanical Engineering Pakistan GIKI Institute Faculty of Mechanical Engineering Pakistan UET Department of Computer system Engineering Peshawar Pakistan UET Department of Electrical Engineering Peshawar Pakistan

ISBN: (纸本)9798350355703

This paper introduces a deep learning (DL)-based vision system for real-time object detection, grasping, and sorting using a UR5e robotic manipulator, aimed to address the challenges faced in industrial automation while grasping and sorting randomly placed objects in the workspace. The system utilizes a fine-tuned detection model, YOLOv8s, trained on a custom dataset of three distinct objects for testing a real-time grasping and sorting system using DL. Once the objects are detected in the workspace, image processing techniques are applied to each detected object to extract the accurate grasping information like the centroid and the orientation. This information is then converted to the robotic arm-based coordinate system to ensure the accurate manipulation of the objects in the workspace. The system is tested in the cluttered environment of the tabletop workspace to grasp and sort the objects, significantly enhancing both speed and accuracy in real-time industrial tasks. Experimental results show grasping accuracy of 93.33%, demonstrating the system's potential to improve automation efficiency in Industry 4.0 applications. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Rice Leaf Diseases Classification Based on RiceNet 2nd

Rice Leaf Diseases Classification Based on RiceNet

引用

2nd International Conference on From Smart City to Smart Factory for a Sustainable Future, SCFF 2024

作者： Quan, Tang Ha Minh Hoa, Ngo Thi Faculty of Mechanical–Electrical and Computer Engineering Van Lang University Ho Chi Minh City Viet Nam

ISBN: (纸本)9783031656552

This paper presents a new model called RiceNet, which is applied to classify rice leaf diseases with compatible and improved accuracy. The RiceNet model is built with 30 layers that are responsible for collecting and extracting features from input diseased leaf images. The research experiment was performed on the Paddy Doctor dataset, which includes 10,407 rice leaf disease images labeled with nine disease types and one standard, respectively. The model’s performance was evaluated on the correct type of information classification and implemented for various cases. Research results show that the RiceNet classification model has an accurate classification rate of 93.08%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Artificial intelligence Data augmentation Deep learning Rice disease identification

来源：评论

学校读者我要写书评

暂无评论

Classification Disease in Tomato Leaf Based on the Mix Convolution Neural Network 2nd

Classification Disease in Tomato Leaf Based on the Mix Convo...

引用

2nd International Conference on From Smart City to Smart Factory for a Sustainable Future, SCFF 2024

作者： Hoa, Ngo Thi Quan, Tang Ha Minh Faculty of Mechanical - Electrical and Computer Engineering Van Lang University Ho Chi Minh City Viet Nam

ISBN: (纸本)9783031656552

Tomatoes are among the most common crops we can find everywhere in all culinary backgrounds. Tomatoes diseases can seriously affect crop output and productivity. Therefore, diagnosing and detecting diseases is crucial to help farmers improve tomato crop productivity. The article uses deep learning, specifically convolutional neural networks, to detect and identify leaf diseases. We designed a MIX-CNN network with a mixed network structure and a small-size model, only 62.4K with 29 layers. The network design includes enhancing two consecutive maxpooling layers at the input and two fully connected layers at the output to mitigate overfitting. The results demonstrate that the proposed network effectively classified the leaf disease dataset acquired from the PlantVillage dataset, achieving an accuracy of 97.6%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Convolution neural network Deep learning MIX-CNN Tomato leaf disease

来源：评论

学校读者我要写书评

暂无评论

Shuffled multi-evolutionary algorithm with linear population size reduction

引用

Soft Computing 2024年第21期28卷 12671-12688页

作者： Ahandani, Morteza Alinia Kharrati, Hamed Rahimi, Afshin Department of Electrical Engineering Langarud Branch Islamic Azad University Langarud Iran Faculty of Electrical and Computer Engineering University of Tabriz Tabriz Iran Department of Mechanical Automotive and Materials Engineering University of Windsor WindsorONN9B 3P4 Canada

The evolutionary algorithms with shuffling concept divide a population into several groups and then each group try to evolve its members in an independent evolutionary process. In an attempt to increase and diversify search moves and preventing the premature convergence of such algorithms, this paper proposes a meta-heuristic technique by employing several evolutionary processes for different groups. In this strategy, different groups can be evolved using a randomly selected evolutionary process. In accordance with this purpose and to provide an ability of jumping out of local optima, which can be useful for finding global optima in complex optimization problems, four different evolutionary strategies inspired from shuffled frog leaping (SFL), shuffled complex evolution (SCE), shuffled differential evolution (SCE) and opposition-based learning (OBL) are incorporated into a new structure called the shuffled multi-evolutionary algorithm (SMEA). The SMEA is extended with linear population size reduction (LPSR) known as L-SMEA, which continually decreases the population size and number of groups according to a linear function. The SMEA is evaluated on CEC2014 and CEC2017 benchmark functions. The obtained results are compared with SFL, SCE and SDE and other state-of-the-art algorithms proposed in the literatures. Performing the statistical analysis of the obtained results demonstrate that the proposed L-SMEA is superior to other three algorithms including SFL, SCE and SDE and some other state-of-the-art algorithms. Also, the performed experiments indicate the contribution of employing multiple evolutionary strategies beside of linear population size reduction leads to achieving a more effective and robust algorithm than those used single evolutionary strategy. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Gear Fault Diagnosis Using the WSET-CNN-BKA-LSSVM Method 5

Gear Fault Diagnosis Using the WSET-CNN-BKA-LSSVM Method

引用

5th International Conference on Electronic Communication and Artificial Intelligence, ICECAI 2024

作者： Yuan, Zhiliang Xu, Chengkai Qiao, Mijia Southeast University Chengxian College School of Electrical and Computer Engineering Jiangsu Nanjing China Southeast University Chengxian College Faculty of Mechanical and Electrical Engineering Jiangsu Nanjing China

ISBN: (纸本)9798350386943

In response to the complexity of the operating environment for some gears, which results in insufficient sample data collection, a gear fault diagnosis method based on WSET-CNN-BKA-LSSVM is proposed. Firstly, traditional linear time-frequency analysis, which handles signals with blurred characteristics and divergent time-frequency energy, fails to effectively extract features from weak signals. This paper introduces Synchroextracting Transform (SET) to enhance and extract weak features in gear vibration signals, utilizing SET to extract faint feature information from rolling bearings. Subsequently, the signal is input into a CNN to continue extracting feature information. Finally, the parameters and penalty factor of the LSSVM kernel function are dynamically optimized using the Black Kite optimization algorithm to establish a gear fault diagnosis model. Utilizing the gear box dataset from Southeast University's laboratory, the data undergo noise reduction and sliding sampling to improve performance, and subsequently, the optimized LSSVM method is used for gear fault diagnosis. Results from multiple diagnostics show that the developed model achieves a diagnosis accuracy of 990% on the test set while maintaining a fast diagnostic speed. © 2024 IEEE.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Towards Simpler Modelling Expressions for the mechanical Characterization of Soft Materials

引用

Micro and Nanosystems 2024年第3期16卷 172-182页

作者： Kontomaris, Stylianos-Vasileios Malamou, Anna Stylianou, Andreas Chliveros, Georgios Faculty of Engineering and Architecture Metropolitan College Athens Greece BioNanoTec LTD Nicosia Cyprus Radar Systems and Remote Sensing Lab School of Electrical & Computer Engineering National Technical University of Athens Athens Greece Department of Mechanical Engineering Faculty of Engineering School of Sciences European University Cyprus Nicosia2404 Cyprus

Aims: The aim of this paper is to develop a new, simple equation for deep spherical indentations. Background: The Hertzian theory is the most widely applied mathematical tool when testing soft materials because it provides an elementary equation that can be used to fit force-indentation data and determine the mechanical properties of the sample (i.e., its Young’s modulus). However, the Hertz equation is only valid for parabolic or spherical indenters at low indentation depths. For large indentation depths, Sneddon’s extension of the Hertzian theory offers accurate force-indentation equations, while alternative approaches have also been developed. Despite ongoing mathematical efforts to derive new accurate equations for deep spherical indentations, the Hertz equation is still commonly used in most cases due to its simplicity in data processing. Objective: The main objective of this paper is to simplify the data processing for deep spherical indentations, primarily by providing an accurate equation that can be easily fitted to force-indentation data, similar to the Hertzian equation. Methods: A simple power-law equation is derived by considering the equal work done by the indenter using the actual equation. Results: The mentioned power-law equation was tested on simulated force-indentation data created using both spherical and sphero-conical indenters. Furthermore, it was applied to experimental force-indentation data obtained from agarose gels, demonstrating remarkable accuracy. Conclusion: A new elementary power-law equation for accurately determining Young’s modulus in deep spherical indentation has been derived. © 2024 Bentham Science Publishers.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

A novel forecasting model for time series using optimized interval division and fuzzy relationships

引用

Neural Computing and Applications 2025年第5期37卷 3869-3885页

作者： PhamToan, Dinh Vo-Van, Tai Faculty of Mechanical - Electrical and Computer Engineering School of Technology Van Lang University Ho Chi Minh City Viet Nam College of Natural Science Can Tho University Can Tho City Viet Nam

This study builds an effective forecasting model for time series based on significant improvements of the fuzzy clustering algorithm. Firstly, we use the universal set, which is the percentage change between two consecutive time points, and divide it into unequal intervals using the automatic clustering algorithm that adjusts the number of clusters. Next, we propose the networks so that establish the fuzzy relationship of the elements in the universal set and the intervals based on the improved inverse fuzzy number. Finally, a new principle for future forecasting is built based on these two improvements. The proposed model details the steps and is clearly illustrated through a specific numerical. The convergence of the proposed algorithm is also considered and addressed. The proposed model has demonstrated effectiveness by outperforming many other models applied to the M3 dataset with 3,003 series, the M4 dataset with 100,000 series, and the well-known benchmark dataset. The proposed model is also applied to forecast the number of people infected and deceased due to COVID-19 in Southeast Asian countries. This application also demonstrates the advantages of the proposed model over many existing models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A Real-time Approach for Multi-physics Field Reconstruction of Active Phased Array Antenna

引用

IEEE Transactions on Antennas and Propagation 2025年第6期73卷 3585-3592页

作者： Feng, Shizhe Chen, Qihang Li, Zhixiong Sotelo, Miguel Angel The State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology Tianjin300130 China The Faculty of Mechanical Engineering Opole University of Technology Opole45-758 Poland The Department of Computer Engineering University of Alcalá Madrid28801 Spain

This study proposes an effective approach to reconstruct the multi-physics field of the active phased array antenna (APAA) through limited information of temperature and strain. First, the multi-physics coupling model of the APAA is constructed to analyze the thermal-mechanical-electromagnetic responses;the model calculation accuracy is verified by experimental testing. Then, a large number of samples containing the temperature and deformation information are generated through the coupling model. Subsequently, the multi-physics field reconstruction model is established based on the extreme gradient boosting (XGBoost) method, in which the parallelization computing is implemented to fully improve the prediction efficiency. Lastly, the testing samples are used to evaluate the performance of the reconstruction model. The obtained results indicate that the developed model is able to reconstruct the multi-physics field of the APAA in real time more precisely through comparing with existing machine learning methods. This approach can provide reliable temperature and displacement reconstruction information for the compensation of the APAA electromagnetic performance. © 1963-2012 IEEE.

关键词： Antenna phased arrays

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：