检索结果-内蒙古大学图书馆

A dense triple-level attention-based network for surgical instrument segmentation

Multimedia Tools and Applications 2024年 1-20页

作者： Yang, Lei Wang, Hongyong Bian, Guibin Liu, Yanhong School of Electrical and Information Engineering Zhengzhou University Henan Province Zhengzhou City450001 China Multi-modal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

In robot-assisted surgery, precise and autonomous segmentation of surgical instruments is pivotal yet challenged by complexities such as intricate surgical scenarios, variable perspectives, low-contrast imaging, diverse instrument dimensions and forms, alongside class imbalance issue. While deep learning has significantly progressed in pixel-wise image segmentation, prevailing end-to-end models grapple with limitations including inadequate context understanding, inefficient feature extraction, and constrained receptive fields, leading to blurred boundaries and loss of local details. To surmount these challenges and enhance segmentation accuracy, this paper proposes a Dense Triple-Attention Network, named DTA-Net, specifically tailored for pixel-level segmentation of surgical instruments in robot-assisted interventions. Proposed DTA-Net introduces a dense attention block to bolster contextual representation, tackling the deficiency in capturing extensive surgical contexts. In addition, it further integrates a Triple-Attention (TA) block to refine feature processing, thereby extracting intricate pixel relationships and enhancing detail retrieval. Complementarily, a Multi-Scale Context Fusion (MCF) mechanism is devised to consolidate multi-resolution features, ensuring comprehensive context exploitation. Extensive evaluations on benchmark datasets, Kvasir-Instrument and Endovis2017, demonstrate that proposed DTA-Net outperforms state-of-the-art models in terms of segmentation accuracy and completeness, which underscores the potential in advancing the precision of robotic surgical interventions through refined instrument segmentation. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Multi Branch Series arc Fault Detection Based on MEEMD and GRU Network 4

Multi Branch Series arc Fault Detection Based on MEEMD and G...

引用

4th International Symposium on Smart and Healthy Cities, ISHC 2022

作者： Yu, Qiongfang Zhang, Yuhai Lu, Wenhao School of Electrical Engineering and Automation Henan Polytechnic University Henan Jiaozuo China Xuchang Longgang Power Generation Co Henan Xuchang China

ISBN: (纸本)9781665491808

The series arc fault poses a maximally threat to the secure of low-voltage system. It is difficult to identify because of the concealment and complexity of arc characteristics. In the cause of effectively identify the cryptic arc characteristics in the current signal and realize the series arc fault detection under multiple branches, a current signal detection approach found on MEEMD and GRU network is proposed. Firstly, an experimental platform is built to collect trunk current signals of branch arc fault under different conditions. Then, the current signal is disintegrated by MEEMD and the training data set and test data set are constructed. The modified GRU network model is applied to identify the arc fault and output the detection results. The experimental results show that the arc fault detection accuracy based on MEEMD-GRU method is 97.28%, which has higher detection accuracy compared with the LSTM model, GRU model and MEEMD-LSTM model. The research has good detection results for series arc fault under multi-branch and provides reference for subsequent research. © 2022 IEEE.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

The Transformer Enhanced Feature Representation with CNNs 12

The Transformer Enhanced Feature Representation with CNNs

引用

12th IEEE International Conference on Identification, Information and Knowledge in the Internet of Things, IIKI 2024

作者： Li, Hengyi Wang, Aihui Gao, Shengda Wang, Yan Geng, Shiyong Dan, Yongping Zhongyuan University of Technology School of Automation and Electrical Engineering Henan Province Zhengzhou450007 China Zhongyuan University of Technology School of Integrated Circuits Henan Province Zhengzhou450007 China

ISBN: (纸本)9798331510633

The self-attention-based Transformer has revolutionized artificial intelligence, achieving remarkable success across various applications beyond traditional convolutional neural networks (CNNs). While multiple studies have explored integrating self-attention mechanisms into CNNs to enhance their performance, these approaches often encounter insufficiency in effectively utilizing self-attention principles. This research proposes a novel approach to address this challenge by integrating the rich and valuable nonlinear information encasulated in the feature maps generated by CNNs with the self-attention mechanisms. Specifically, we leverage the self-attention encoder mechanism to further capture the global dependencies and contextual relations from the informative feature maps, thus enabling more robust and discriminative feature representations. Through experiments and evaluations with benchmark datasets on classification tasks, the findings indicate that our proposed approach not only boosts the performance of CNNs but also delivers a more efficient and scalable solution, achieving the accuracies of 95.65%, 78.48% and 95.65% on datasets CIFAR10/100 and fashion mnist, respectively. This work points to a potential path for future investigations and applications in integrating the transformer encoder with CNNs. © 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

Saliency Improved YOLOv5s Algorithm for Defect Detection of Overhead Line Insulator

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第3期8卷 791-806页

作者： Fang, Xiang Wu, Xiang Ma, Yuanhao Lian, Hao Song, Yuan School of Electrical Engineering Henan University of Technology Zhengzhou China Istituto della Ricerca ed Innovazione Sino-Italian Marche Polytechnic University Marche Italy

Aiming at the problems that the target proportion of insulator defects is small, and the defect features are not obvious, which leading to low detection rate, a YOLOv5s algorithm based on saliency information improvement is proposed. Firstly, saliency information extraction (SANet) module is used to generate saliency images to enhance the discrimination between insulator target and background. Second, a small target detection layers are added, and a large target detection layer are removed to improve the feature extraction ability of the network for small targets and speed up the network reasoning. Then, the attention module (CBAM) is introduced to improve the network’s attention to the target features along both channel and spatial dimensions. Finally, EIoU-Loss as a loss function is used to accelerate the convergence speed and improve the regres-sion accuracy. The experimental results show that compared with the original YOLOv5s network, the improved algorithm with mAP50 and mAP50:95 increases by 3.43% and 3.32%, respect to the frame rate 36 frames per second, which is capable of real-time de-tection. © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

A Research Status of 3D Printing of Different Metal Forms

A Research Status of 3D Printing of Different Metal Forms

引用

作者： Liu, Jianxiu Li, Yi Fan, Jianglei Wu, Shen Li, Ying Wang, Jun School of Mechanical and Electrical Engineering Zhengzhou University of Light Industry Henan Zhengzhou China College of Environmental Arts and Engineering Henan Polytechnic Henan Zhengzhou China

3D printing of metal materials plays an important role in the ranks of 3D printing and is one of the core development directions of 3D printing in the future. According to the different forms of metal raw materials, it can be roughly divided into powder printing, solid-state printing and liquid printing. Printed with powder metal as raw materials include laser selective sintering technology (SLS), laser selective melting technology (SLM), 3D printing technology (3DP), etc. printed with solid metal as raw materials include arc fuse deposition molding(WAAM)and layered solid manufacturing(LOM), etc. according to the different forms of 3D printing raw materials, this paper explores the applicable printing processes of different raw materials, and discusses the processing methods, process characteristics and research status of each process. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

Local Feature Expansion ViT Model for Bearing Fault Diagnosis Under Noise Environment 18th

Local Feature Expansion ViT Model for Bearing Fault Diagnosi...

引用

18th Annual Conference of China Electrotechnical Society, ACCES 2023

作者： Xie, Hongbin Zhang, Xinliang Zhou, Yitian Liu, Guanlin Wu, Zhonghua School of Electrical Engineering and Automation Henan International Joint Laboratory of Direct Drive and Control of Intelligent Equipment Henan Polytechnic University Jiaozuo454003 China Zhoushan Yangwangnaxin Technology Co. Ltd. Zhejiang Zhoushan3161041 China

ISBN: (纸本)9789819714469

Vision Transformer (ViT) shows a great potential in the field of bearing fault diagnosis by virtue of its multi-head self-attention mechanism. However, ViT confines the one-layered convolutional network to the feature map preparation and its accuracy is hindered by the insufficient local features caused by noise interference in practical scenarios. To address this problem, a local feature expansion based ViT, i.e., LFE-ViT, is proposed. A hybrid convolutional residual network is introduced to the embedding module to expand the local information of the bearing faults. Then, by combination of the local feature expansion network and the following multi-head self-attention mechanism, the completely local and global feature representation is achieved for the bearing fault classification. Finally, the derived ViT model is validated on the Case Western Reserve University bearing dataset. The experimental results have shown that it gives better diagnostic performance compared with existing methods under the noise environment. © Beijing Paike Culture Commu. Co., Ltd. 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Video Person Re-identification Based on Transformer-CNN Model 4

Video Person Re-identification Based on Transformer-CNN Mode...

引用

4th International Conference on Artificial Intelligence and Advanced Manufacturing, AIAM 2022

作者： Zhao, Liang Yu, Qiongfang Yang, Yi Henan Polytechnic University School of Electrical Engineering and Automation Jiaozuo China Dut School of Economics and Management Dalian China

ISBN: (纸本)9781665463997

To overcome the problems of pose variation, complex background and more occlusion in video person re-identification, a network model ResTNet based on convolutional neural network and Transformer was proposed. ResNet50 network was used to obtain local features and the output of its middle layer was input to Transformer as prior knowledge in ResTNet. In the Transformer branch, the size of the feature map was continuously reduced. The field of perception was expanded to fully explore the relationships among local features, and generated global features of pedestrians. The model computation was also decreased with the shift window method. Cross-entropy loss and triplet loss were used to optimize the model for the two branches during training, respectively. The Rank-1 and mAP on the large-scale MARS dataset reached 86.8% and 80.3%, respectively, which were 3.8% and 3.3% higher than the benchmark. The Transformer model was not only successfully applied to the field of video person re-identification, but also extensive experiments on several large datasets showed that the proposed ResTNet network can enhance the robustness of the recognition and improve the accuracy of person re-identification effectively. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A control method for an improved H-bridge and NPC hybrid cascaded static var generator 6

A control method for an improved H-bridge and NPC hybrid cas...

引用

6th International Conference on Energy, Power and Grid, ICEPG 2024

作者： Zhao, Xiaofan Chen, Ziang Qian, Weichen Huang, Xiaobo Henan Polytechnic University School of Electrical Engineering and Automatic Henan Jiaozuo454000 China North China University of Water Resources and Electric Power University Henan Zhengzhou450000 China

ISBN: (纸本)9798350377798

Adopting a Hybrid Cascade Static Synchronous Compensator (HC-SVG), which integrates Neutral-Point Clamped (NPC) three-level power units and Cascade H-bridge (CHB) power units, can reduce the number of CHB power units, making it a current research hotspot in the field of reactive power compensation. However, the introduction of high-voltage NPC power units causes high-order harmonics in the DC bus capacitors on both the NPC and CHB sides, affecting the overall compensation performance of the device. This paper proposes an improved control method that extracts and filters the high-order harmonic content of the DC-side capacitors in the reactive power compensation device, resulting in more stable system operation. Finally, a simulation platform is constructed to verify the effectiveness of the theoretical analysis. © 2024 IEEE.

关键词： Bridge circuits

来源：评论

学校读者我要写书评

暂无评论

Fault diagnosis of pumping unit based on lightweight convolutional neural network 8

Fault diagnosis of pumping unit based on lightweight convolu...

引用

8th International Conference on electrical, Mechanical and Computer engineering, ICEMCE 2024

作者： Jiang, Zhengfeng Li, Jianguo Wang, Hua Lanzhou Jiaotong University School of Automation and Electrical Engineering Gansu Lanzhou China Sichuan Polytechnic Technician College Department of Mechanical and Electrical Engineering Sichuan Chengdu China

ISBN: (纸本)9798331506230

In order to ensure the efficient operation of the pumping unit system and monitor its status in real time, rapid and accurate fault diagnosis and identification of the oil well operating curve (work diagram) is a key step to evaluate the working efficiency of the pumping unit. In response to this demand, a lightweight model based on the MobileNetV3 model is proposed, which integrates the lightweight convolutional block attention module (MLCA) and improves the accuracy of dynamometer diagnosis without increasing the computational load of the model. Experiments Expanded on a data set containing 7 types of different working conditions and a total of 9464 work map images, the results show that the model still achieves an average recognition accuracy of up to 98.44%, surpassing the performance of baseline models such as ShuffleNetV2, EfficientNetB0, and MobileNetV3. These data strongly prove that the improved MLCA-MobileNetV3 model performs well on the dynamometer recognition task and has significant practical value and efficiency advantages. © 2024 IEEE.

关键词： Oil well pumping

来源：评论

学校读者我要写书评

暂无评论

Multi-model ensemble learning for battery state-of-health estimation:Recent advances and perspectives

引用

Journal of Energy Chemistry 2025年第1期100卷 739-759页

作者： Chuanping Lin Jun Xu Delong Jiang Jiayang Hou Ying Liang Zhongyue Zou Xuesong Mei State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiaotong UniversityXi’an 710049ShaanxiChina Shaanxi Key Laboratory of Intelligent Robots School of Mechanical EngineeringXi’an Jiaotong UniversityXi’an 710049ShaanxiChina Department of Electrical Engineering and Automation Luoyang Institute of Science and TechnologyLuoyang 471023HenanChina School of Mechanical Engineering Hangzhou Dianzi UniversityHangzhou 310018ZhejiangChina

The burgeoning market for lithium-ion batteries has stimulated a growing need for more reliable battery performance monitoring. Accurate state-of-health(SOH) estimation is critical for ensuring battery operational performance. Despite numerous data-driven methods reported in existing research for battery SOH estimation, these methods often exhibit inconsistent performance across different application scenarios. To address this issue and overcome the performance limitations of individual data-driven models,integrating multiple models for SOH estimation has received considerable attention. Ensemble learning(EL) typically leverages the strengths of multiple base models to achieve more robust and accurate outputs. However, the lack of a clear review of current research hinders the further development of ensemble methods in SOH estimation. Therefore, this paper comprehensively reviews multi-model ensemble learning methods for battery SOH estimation. First, existing ensemble methods are systematically categorized into 6 classes based on their combination strategies. Different realizations and underlying connections are meticulously analyzed for each category of EL methods, highlighting distinctions, innovations, and typical applications. Subsequently, these ensemble methods are comprehensively compared in terms of base models, combination strategies, and publication trends. Evaluations across 6 dimensions underscore the outstanding performance of stacking-based ensemble methods. Following this, these ensemble methods are further inspected from the perspectives of weighted ensemble and diversity, aiming to inspire potential approaches for enhancing ensemble performance. Moreover, addressing challenges such as base model selection, measuring model robustness and uncertainty, and interpretability of ensemble models in practical applications is emphasized. Finally, future research prospects are outlined, specifically noting that deep learning ensemble is poised to advance ens

关键词： Lithium-ion battery State-of-health estimation Data-driven Machine learning Ensemble learning Ensemble diversity

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：