检索结果-内蒙古大学图书馆

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Saeed, Zubair Torfeh, Tarraf Aouadi, Souha Ji, Jim Xiuquan Bouhali, Othmane Texas A&m University Department of Electrical and Computer Engineering College StationTX47080 United States Texas A&m University at Qatar Department of Electrical and Computer Engineering Doha Qatar Hamad Medical Corporation National Center for Cancer Care and Research Department of Radiation Oncology Doha3050 Qatar Hamad Bin Khalifa University Qatar Center for Quantum Computing College of Science and Engineering Doha34110 Qatar

ISBN: (纸本)9798350387384

The rising incidents of brain tumors pose significant challenges in diagnosis and treatment. Tumorous brain cancers present unique difficulties due to their critical locations and functional implications. Magnetic Resonance Imaging (MRI) offers safe and precise imaging, free from the risks associated with radiation-based methods. Deep learning, particularly Convolutional Neural Networks (CNN), has emerged as a valuable tool in identifying brain tumors in MRI scans, enabling more accurate diagnoses by fusing two well-known DL models. This study explores a fusion strategy combining AlexNet and VGG16 models, outperforming individual models trained with different learning rates. While VGG16 and AlexNet achieved accuracies of 79% and 77% respectively. Our fusion approach potentially achieved an accuracy of 81%, underscoring its efficacy in enhancing brain tumor classification accuracy. This study helps medical professionals to accurately and timely classify tumors for better outcomes for patients. © 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

Cross-Modality Image Transformation Using Generative Adversarial Network 24th

Cross-Modality Image Transformation Using Generative Adversa...

引用

24th Conference on Man-Machine-Environment System engineering, MMESE 2024

作者： Liu, Haoting Yu, Shiqi Hou, Qingwen Chen, Shuai Guo, Kuiyuan Wang, Xu Li, Qing Beijing Engineering Research Center of Industrial Spectrum Imaging School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China CATARC Technology Co. Ltd. Shenzhen518118 China

ISBN: (纸本)9789819771387

A cross-modality image transformation method using the Generative Adversarial Network (GAN) is proposed in this paper. First, the preprocessing methods are performed to the original image data. The computational steps include adjusting image size and suppressing image noises. Second, a kind of GAN is constructed. Both the generator network and discriminator network are created. Third, the GAN is trained and the back propagation optimization is performed continuously. Finally, the trained GAN can be used for data enhancement. To test the effects of computational steps above, the image transformation from the visible light image to other noise-contaminated image is performed. Lots of experiments have illustrated the correctness of our method. © Beijing KeCui Man-Machine-Environment System engineering Technology research Academy 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

MSMB-GCN: Multi-scale Multi-branch Fusion Graph Convolutional Networks for 3D Human Pose Estimation

MSMB-GCN: Multi-scale Multi-branch Fusion Graph Convolutiona...

引用

2023 IEEE International Conference on robotics and Biomimetics, ROBIO 2023

作者： Ji, Shanshan Meng, Qiwei Wang, Wen Lin, Zheyuan Li, Te Wan, Minhong Zhang, Chunlong Gu, Jason Research Institute of Interdisciplinary Innovation Zhejiang Laboratory Research Center for Intelligent Robotics Hangzhou311100 China Dalhousie University Department of Electrical and Computer Engineering HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9798350325706

In human-robot interaction (HRI), human pose estimation is a necessary technology for the robot to perceive the dynamic environment and make interactive actions. Recently, graph convolutional networks (GCNs) have been increasingly used for 2D to 3D pose estimation tasks since the skeleton topologies can be viewed as graph structures. In this paper, we propose a novel graph convolutional network architecture, Multi-scale Multi-branch Fusion Graph Convolutional Networks (MSMB-GCN), for 3D Human Pose Estimation(3D HPE) task. The proposed model consists of multiple GCN blocks with a multi-branch architecture. This multi-branch architecture enables the model to get multi-scale features for human skeletal representations. The group of GCN blocks, which has strong multi-level feature extraction capabilities, allows the model to learn global and local features, lower-level and higher-level features. Experiment results on the HumanPose benchmark demonstrate that our model outperforms the state-of-the-art and ablation studies validate the effectiveness of our approach. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GCN-LSTM Based Transient Angle Stability Assessment Method for Future Power Systems Considering Spatial-temporal Disturbance Response Characteristics

引用

Protection and Control of Modern Power Systems 2024年第6期9卷 108-121页

作者： Shiwei Xia Chenhui Zhang Yahan Li Gengyin Li Linlin Ma Ning Zhou Ziqing Zhu Huan Ma the School of Electrical and Electronic Engineering North China Electric Power UniversityBeijing 102206China the State Grid Shandong Dispatch and Control Center Jinan 250003China the State Grid Shandong Electric Power Research Institute Jinan 250001China the Department of Computer Science Hong Kong Baptist UniversityHong Kong 999077China

Traditional transient angle stability analysis methods do not fully consider the spatial characteristics of the network topology and the temporal characteristics of the time-series ***,a data-driven method is proposed in this study,combining graph convolution network and long short-term memory network(GCN-LSTM)to analyze the transient power angle sta-bility by exploring the spatiotemporal disturbance char-acteristics of future power systems with high penetration of renewable energy sources(wind and solar energy)and power *** key time-series electrical state quantities are considered as the initial input feature quantities and normalized using the Z-score,whereas the network adjacency matrix is constructed according to the system network *** normalized feature quan-tities and network adjacency matrix were used as the inputs of the GCN to obtain the spatial features,reflecting changes in the network ***,the spa-tial features are inputted into the LSTM network to ob-tain the temporal features,reflecting dynamic changes in the transient power angle of the ***,the spatiotemporal features are fused through a fully con-nected network to analyze the transient power angle stability of future power systems,and the softmax activa-tion cross-entropy loss functions are used to predict the stability of the *** proposed transient power angle stability assessment method is tested on a 500 kV AC-DC practical power system,and the simulation results show that the proposed method could effectively mine the spatiotemporal disturbance characteristics of power sys-tems. Moreover, the proposed model has higher accuracy, higher recall rate, and shorter training and testing times than traditional transient power angle stability algo-rithms.

关键词： Future power system spatiotemporal disturbance characteristics transient power angle stabil-ity graph convolutional network long short-term memory network.

来源：评论

学校读者我要写书评

暂无评论

Practical aberration correction using deep transfer learning with limited experimental data

引用

Optics Express 2025年第6期33卷 14431-14444页

作者： Kok, Yong En Bentley, Alexander Parkes, Andrew J. Somekh, Michael G. Wright, Amanda J. Pound, Michael P. University of Nottingham School of Computer Science NottinghamNG8 1BB United Kingdom Optics and Photonics Group Department of Electrical and Electronic Engineering University of Nottingham NottinghamNG7 2RD United Kingdom Research Center for Humanoid Sensing Zhejiang Laboratory Hangzhou3111100 China

Adaptive optics is a technique for correcting aberrations and improving image quality. When adaptive optics was first used in microscopy, it was common to rely on iterative approaches to determine the aberrations present. It is advantageous to avoid iteration, and therefore there has been a shift to deep learning for aberration prediction. However, issues remain regarding the practicalities of machine learning for adaptive optics, an important one being the requirement for a large training dataset. Here, we explore transfer learning to overcome this need for data by pre-training a network on a large simulated dataset and fine-tuning it with reduced experimental data for application in an experimental setting. We demonstrate that the pre-trained network can make noticeable improvements with fine-tuning on just 24 experimental samples. To further enhance practicality, we significantly extend the range of aberrations present, predicting up to 25 Zernike modes with each coefficient ranging from −1 to 1, and perform a thorough analysis of the type and magnitude of phase-diversity required in the input data for a successful network. Our approach demonstrates substantial aberration reduction on experimental data for 10 Zernike modes, with an average 73% decrease in RMS wavefront error from 1.81 to 0.48 rad when correction is applied. This method achieves complete experimental image capture and aberration inference at rates comparable to the image acquisition time of a typical laser scanning microscope. Additionally, we consider the benefits of further improvements via an iterative step. As such, this work addresses some of the key practical hurdles that remain in the use of deep learning for aberration prediction and correction. © 2025 Optica Publishing Group (formerly OSA). All rights reserved.

关键词： Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

Decisioning-Based Approach for Optimising Control engineering Tools Using Digital Twin Capabilities and Other Cyber-Physical Metaverse Manufacturing System Components

引用

IEEE Transactions on Consumer Electronics 2024年第1期70卷 3212-3221页

作者： Mourad, Nahia Alsattar, Hassan A. Qahtan, Sarah Zaidan, Aws Alaa Deveci, Muhammet Sangaiah, Arun Kumar Pedrycz, Witold British University in Dubai Faculty of Engineering and IT Dubai United Arab Emirates University of Mashreq College of Administrative Science Department of Business Administration Baghdad10067 Iraq Middle Technical University College of Health and Medical Technology-Baghdad Department of Computer Center Baghdad10047 Iraq SP Jain School of Global Management SydneyNSW2141 Australia National Defence University Turkish Naval Academy Department of Industrial Engineering Istanbul34040 Turkey Lebanese American University Department of Electrical and Computer Engineering Byblos Lebanon International Graduate Institute of AI National Yunlin University of Science and Technology Yunlin64002 Taiwan University of Alberta Faculty of Engineering Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Istinye University Faculty of Engineering and Natural Sciences Department of Computer Engineering Istanbul34010 Turkey

The optimisation of control engineering tools based on digital twin capabilities and other cyber-physical metaverse manufacturing system (CPMMS) components are crucial for the successful performance. This study proposes a model for optimising control engineering tools using digital twin capabilities and other CPMMS components to solve the open issues. The main contributions and novelty aspects of the methodological process are outlined as follows: Formulated and developed is a decision matrix based on a utility procedure for 10 control engineering tools with digital twin capabilities and other three CPMMS components (Programmable-Logic-Controller and Human-Machine-Interface, Internet of Things connectivity and cybersecurity features). This matrix accounts for the uncertainty associated with tool assessment and transformation evaluation issue;formulated and develop an integrating fuzzy weighted with zero-inconsistency-interval-valued spherical fuzzy rough sets (IvSFRS-FWZIC) and combined compromise solution (CoCoSo) methods. The IvSFRS-FWZIC method is utilised to assign importance degrees to the digital twin capabilities and other CPMMS components. The applicability and robustness of the proposed approach are validated and evaluated through conducting sensitivity, correlation, and comparative analyses. The proposed approach can assist managers in analysing and selecting the most suitable tool for developing CPMMS. © 1975-2011 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Analysis on the Hesitation and its Application to Decision Making

Decision Making: Applications in Management and Engineering

引用

Decision Making: Applications in Management and engineering 2024年第2期7卷 15-34页

作者： Yang, Youpeng Lee, Sanghyuk Kim, Kyeong Soo Zhang, Haolan Huang, Xiaowei Pedrycz, Witold School of Advanced Technology Xi’an Jiaotong-Liverpool University Jiangsu Suzhou China Department of Computer Science University of Liverpool Liverpool United Kingdom Department of Computer Science New Uzbekistan University Tashkent Uzbekistan SCDM Centre Zhejiang University Ningbo China Department of Electrical & Computer Engineering University of Alberta EdmontonABT6G 2R3 Canada Systems Research Institute Polish Academy of Sciences Warsaw00-901 Poland Research Center of Performance and Productivity Analysis Istinye University Istanbul Turkey

A novel score function based on the Poincaré metric is proposed and applied to a decision-making problem. Decision-making on Fuzzy Sets (FSs) has been considered due to the flexibility of the data, and it is applied to the decision-making. However, decisions with FSs are sometimes nondecisive even for different membership degrees. Hence, Intuitionistic Fuzzy Sets (IFSs) data is applied to design a score function for the decision-making with the Poincaré metric. This function is supported by the profound information of IFSs;IFSs include hesitation degree together with membership and non-membership degree. Hence, IFS membership and non-membership degree are expressed as two-dimensional vectors satisfying the Poincaré metric for simplification. At the same time, the proposed approach addresses the hesitation information in the IFS data. Next, a score function is proposed, constructed and provided. The proposed score function has a strict monotonic property and addresses the preference without resorting to the accuracy function. The strict monotonic property guarantees the preference of all attributes. Additionally, the existing problem of score function design in IFSs is addressed: they return zero scores even with different meanings for the same membership and non-membership degree. The advantages of the proposed score function over existing ones are demonstrated through illustrative examples. From the calculation results, the proposed decision score function discriminates between all candidates. Hence, the proposed research provides a solid foundation for the hesitation analysis on the decision-making problem. © 2024 The Authors.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Ferroelectric Enhancement in a TiN/Hf1-xZrxO2/W Device with Controlled Oxidation of the Bottom Electrode

引用

ACS Applied Electronic Materials 2024年第2期6卷 1078-1086页

作者： Chiniwar, Santosh P. Hsieh, Ya-Chen Shih, Ching-Hsiang Teng, Chih-Yu Yang, Jheng-Lin Hu, Chenming Lin, Bi-Hsuan Tang, Mau-Tsu Tseng, Yuan-Chieh Department of Material Science & Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan International College of Semiconductor Technology National Yang Ming Chiao Tung University Hsinchu30010 Taiwan Department of Electrical Engineering and Computer Sciences University of California BerkeleyCA94720 United States National Synchrotron Radiation Research Center Hsinchu30076 Taiwan

Hf1-xZxO2 (HZO) is a promising ferroelectric (FE) material with CMOS compatibility, while the TiN/HZO/W metal-ferroelectric-metal structure provides balanced thermal expansion for stacking. In this study, we developed a 7 nm film of HZO with a FE polarization (2Pr) value of ∼43 μC/cm2 and cycling endurance of 108 by determining the appropriate oxidation state for a W bottom electrode deposited via atomic layer deposition with a relatively low annealing temperature of 400 °C. To visualize FE uniformity, we used X-ray absorption spectroscopy phase mapping to construct a two-dimensional map of the orthorhombic (O), tetragonal (T), and monoclinic (M) phases of the HZO film. Subsequent orientation- and chemical-state-resolved X-ray analysis revealed that the enhanced FE polarization performance can be attributed to the combined effects of interface strain and oxygen vacancies. Piezoelectric force microscopy verified the switching uniformity of the devices and revealed the electrical characteristics for use in device optimization. © 2024 The Authors. Published by American Chemical Society

关键词： X ray diffraction analysis

来源：评论

学校读者我要写书评

暂无评论

Multidomain Object Detection Framework Using Feature Domain Knowledge Distillation

引用

IEEE Transactions on Cybernetics 2024年第8期54卷 4643-4651页

作者： Jaw, Da-Wei Huang, Shih-Chia Lu, Zhi-Hui Fung, Benjamin C. M. Kuo, Sy-Yen National Taiwan University Department of Electrical Engineering Taipei106 Taiwan National Taipei University of Technology Department of Electronic Engineering Taipei106 Taiwan Fudan University School of Computer Science The Engineering Research Center of Cyber Security Auditing and Monitoring Ministry of Education Shanghai200433 China McGill University School of Information Studies MontrealQCH3A 1X1 Canada

Object detection techniques have been widely studied, utilized in various works, and have exhibited robust performance on images with sufficient luminance. However, these approaches typically struggle to extract valuable features from low-luminance images, which often exhibit blurriness and dim appearence, leading to detection failures. To overcome this issue, we introduce an innovative unsupervised feature domain knowledge distillation (KD) framework. The proposed framework enhances the generalization capability of neural networks across both low- and high-luminance domains without incurring additional computational costs during testing. This improvement is made possible through the integration of generative adversarial networks and our proposed unsupervised KD process. Furthermore, we introduce a region-based multiscale discriminator designed to discern feature domain discrepancies at the object level rather than from the global context. This bolsters the joint learning process of object detection and feature domain distillation tasks. Both qualitative and quantitative assessments shown that the proposed method, empowered by the region-based multiscale discriminator and the unsupervised feature domain distillation process, can effectively extract beneficial features from low-luminance images, outperforming other state-of-the-art approaches in both low- and sufficient-luminance domains. © 2013 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Green InGaN/GaN Multiple-Quantum-Wells With Pre-Layer for High-Efficiency Mini-LEDs

IEEE Electron Device Letters

引用

IEEE Electron Device Letters 2023年第6期44卷 907-910页

作者： Lai, Shouqiang Lai, Chaohsu Li, Saijun Chen, Guolong Zheng, Xi Lu, Tingwei Lin, Zongming Wu, Rongxing Lu, Yijun Kuo, Hao-Chung Chen, Zhong Wu, Tingzhu Xiamen University Department of Electronic Science Xiamen361005 China Xiamen361005 China National Yang Ming Chiao Tung University College of Electrical and Computer Engineering Hsinchu30010 Taiwan Hon Hai Research Institute Semiconductor Research Center Taipei11492 Taiwan

In this study, we investigated the temperature-dependent photoluminescence characteristics of green InGaN/GaN multiple quantum wells (MQWs) with InGaN/GaN pre-wells and InGaN pre-layers, and the electroluminescence properties of the corresponding mini-LEDs were fabricated and studied. According to the fitting results of the temperature-dependent photoluminescence spectra obtained by the Vaishini and Arrhenius models, the S-shaped temperature-dependent peak energies of green InGaN/GaN MQWs grown on pre-wells and pre-layers indicated that these peaks originated from the localized state, and better crystal quality could be found in the MQWs with pre-layers. Moreover, we compared the electroluminescence properties of green mini-LEDs. These results demonstrate the advantages of growing green MQWs with an InGaN prelayer. © 1980-2012 IEEE.

关键词： Semiconductor quantum wells

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：