检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Huang, Hong Song, Yu Wu, Yao Shi, Jia Xie, Xia Jin, Hai National Engineering Research Center for Big Data Technology Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Link prediction and node classification are two important downstream tasks of network representation learning. Existing methods have achieved acceptable results but they perform these two tasks separately, which requires a lot of duplication of work and ignores the correlations between tasks. Besides, conventional models suffer from the identical treatment of information of multiple views, thus they fail to learn robust representation for downstream tasks. To this end, we tackle link prediction and node classification problems simultaneously via multi-task multi-view learning in this paper. We first explain the feasibility and advantages of multi-task multi-view learning for these two tasks. Then we propose a novel model named as MT-MVGCN to perform link prediction and node classification tasks simultaneously. More specifically, we design a multi-view graph convolutional network to extract abundant information of multiple views in a network, which is shared by different tasks. We further apply two attention mechanisms: view attention mechanism and task attention mechanism to make views and tasks adjust the view fusion process. Moreover, view reconstruction can be introduced as an auxiliary task to boost the performance of the proposed model. Experiments on real-world network datasets demonstrate that our model is efficient yet effective, and outperforms advanced baselines in these two tasks. © 2021, CC BY.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Parametric heart activity condensed photoacoustic stimulation from MRI images

引用

AIP Conference Proceedings 2023年第1期2523卷

作者： T. Senthil Kumar Maram Ashok M. Suresh Anand Karthikeyan Palaniappan 1Department of Electronics and Communication Engineering GRT Institute of Engineering and Technology Tiruttani Tamil Nadu India. 2Department of Computer Science and Engineering Malla Reddy Institute of Engineering and Technology Secunderabad Telangana India. 3Department of Computer Science and Engineering Sri Sairam Engineering College Chennai Tamil Nadu India. 4Department of Centre for System Design Computer Science and Engineering Chennai Institute of Technology Chennai Tamil Nadu India.

In this article, we propose a computer research approach that uses only a few tomographic optoacoustic projections to analyze main components for high-frame volumetric heart imagery is seen herein in the non-invasive imaging of a smoking rodent. This approach is beneficial for discerning periodic movements. The training process allows the heart motion information to be effectively compressed and used in a higher frame rate as prior information for image restoration. Image consistency with report book decrease in the data flow is seen to be safeguarded. We prove that the parametric motion can be effectively obtained under such conditions by focusing on moment data from a single tomographic detector. A visualization of perfusing a contrast agent in vivo indicates the possibility of recording intermittent (quasi) events not recorded in the training process. The proposed method can be used to dramatically improve optoacoustic imaging time resolution and help create more accessible and data efficiency systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RadioGAT: A Joint Model-based and Data-driven Framework for Multi-band Radiomap Reconstruction via Graph Attention Networks

arXiv

引用

arXiv 2024年

作者： Li, Xiaojie Zhang, Songyang Li, Hang Li, Xiaoyang Xu, Lexi Xu, Haigao Mei, Hui Zhu, Guangxu Qi, Nan Xiao, Ming Shenzhen Research Institute of Big Data The Chinese University of Hong Kong-Shenzhen Guangdong China College of Physics Nanjing University of Aeronautics and Astronautics Nanjing210016 China Department of Electrical and Computer Engineering University of Louisiana at Lafayette LafayetteLA70503 United States Research Institute China United Network Communications Corporation Beijing100048 China China Mobile Communications Group Jiangxi Co. Ltd 330038 China Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Nanjing University of Aeronautics and Astronautics Nanjing210016 China State Key Laboratory of Integrated Services Networks Xidian University Xi'An710071 China Department of Information Science and Engineering School of Electrical Engineering of KTH Royal Institute of Technology Stockholm Sweden

Multi-band radiomap reconstruction (MB-RMR) is a key component in wireless communications for tasks such as spectrum management and network planning. However, traditional machine-learning-based MB-RMR methods, which rely heavily on simulated data or complete structured ground truth, face significant deployment challenges. These challenges stem from the differences between simulated and actual data, as well as the scarcity of real-world measurements. To address these challenges, our study presents RadioGAT, a novel framework based on Graph Attention Network (GAT) tailored for MBRMR within a single area, eliminating the need for multiregion datasets. RadioGAT innovatively merges model-based spatial-spectral correlation encoding with data-driven radiomap generalization, thus minimizing the reliance on extensive data sources. The framework begins by transforming sparse multiband data into a graph structure through an innovative encoding strategy that leverages radio propagation models to capture the spatial-spectral correlation inherent in the data. This graph-based representation not only simplifies data handling but also enables tailored label sampling during training, significantly enhancing the framework's adaptability for deployment. Subsequently, The GAT is employed to generalize the radiomap information across various frequency bands. Extensive experiments using raytracing datasets based on real-world environments have demonstrated RadioGAT's enhanced accuracy in supervised learning settings and its robustness in semi-supervised scenarios. These results underscore RadioGAT's effectiveness and practicality for MBRMR in environments with limited data availability. Copyright © 2024, The Authors. All rights reserved.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

Advances in Dry Etch Processing for High-Density Vertical Interconnects in Fan-Out Panel-Level Packaging and IC Substrates

Advances in Dry Etch Processing for High-Density Vertical In...

引用

Electronic Components and Technology Conference (ECTC)

作者： Friedrich-Leonhard Schein Mohammed Elghazzali Christian Voigt Ioannis Tsigaras Hirofumi Sawamoto Ewald Strolz Roland Rettenmeier Lars Böttcher Faculty IV - Electrical Engineering and Computer Science TU Berlin Berlin Germany Business Unit Advanced Packaging Evatec AG Trübbach Switzerland System Integration & Interconnection Technologies Fraunhofer IZM Berlin Germany

Within the advanced packaging technologies there is an increasing demand for very high I/O count solutions to fulfill requirements of high performance computing applications like big data analysis. Thus, the density of lateral and vertical interconnects is being pushed to its limits to achieve a minimum delay in communication between chips or chiplets from different technology nodes. Here we focus on dry etch technology as an approach to overcome the difficulties of currently used processes for the formation of vertical interconnects (vias) in organic buildup films. Nowadays, laser drilling into the organic dielectric is the state-of-the-art technology to prepare vertical interconnects between the Cu layers. However, drawbacks like sequential processing, limited control of sidewall smoothness or registration accuracy become extremely challenging when millions of sub-vias have to be realized on 600 mm2 panels. One alternative technique to address the need of forming steep microstructures in various materials is deep reactive-ion etching (DRIE). In this paper we analyze how DRIE could be applied for via formation in silica-filled organic dielectric build-up films. Our approach included a metallic hard mask for material-selective etching and for generating various via diameters. For our experiments, a dual frequency capacitive coupled plasma (CCP) tool was used. The plasma etch module was designed for panel-level substrates up to size and was integrated into a high volume manufacturing system. We investigated the influence of different gas mixtures, power settings on etch rate, selectivity (e.g. on silica and organic), directionality, uniformity and homogeneity. The overall compatibility and implications of the dry etching approach for the semi-additive process and redistribution layer formation have been discussed.

关键词： Silicon compounds Films Lasers Process control Tools Packaging Plasmas

来源：评论

学校读者我要写书评

暂无评论

Investigation of the long-term adhesion and barrier properties of a PDMS-Parylene stack with PECVD ceramic interlayers for the conformal encapsulation of neural implants 23

Investigation of the long-term adhesion and barrier properti...

引用

23rd European Microelectronics and Packaging Conference and Exhibition, EMPC 2021

作者： Babaroud, Nasim Bakhshaee Dekker, Ronald Holk, Ole Tiringer, Ursa Taheri, Peyman Horvath, Domonkos Nanasi, Tibor Ulbert, Istvan Serdijn, Wouter Giagka, Vasiliki Department of Microelectronics Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft Netherlands Technologies for Bioelectronics Group Department of System Integration and Interconnection Technologies Fraunhofer Institute for Reliability and Micro-Integration IZM Berlin Germany Delft University of Technology Delft Netherlands Institute of Cognitive Neuroscience and Psychology Research Center for Natural Science Budapest Hungary Philips Research Eindhoven Netherlands Rotterdam Netherlands

ISBN: (纸本)9780956808677

In this paper, we investigate the long-term adhesion strength and barrier property of our recently proposed encapsulation stack that includes PDMS-Parylene C and PECVD interlayers (SiO2 and SiC) for adhesion improvement. To evaluate the adhesion strength of our proposed stack, the sample preparation consisted in depositing approximately 25 nm of SiC and 25 nm of SiO2 on half wafers, previously coated with Parylene C. Next, 50 µm PDMS was spin-coated on top. Finally, the samples were detached from the Si wafer and soaked in a PBS solution at 67 °C to accelerate the aging process. Two samples were also implanted, subcutaneously, on the left and right subscapular regions of a rat. The optical inspection and peel tests performed after two months confirmed our preliminary findings and showed a significant improvement of the adhesion in our proposed encapsulation stack compared to the case of PDMS on Parylene C alone. In addition, the X-ray photoelectron spectroscopy (XPS) analysis at the interface between SiC and Parylene C showed different peaks for the interface compared to the reference spectra, which could be an indication of a chemical bond. Finally, water vapor transmission rate (WVTR) tests were performed to investigate the barrier property of our proposed encapsulation stack against water vapor transmission. The results demonstrated that the proposed stack acts as a significantly (two orders of magnitude) higher barrier against moisture compared to only Parylene C and PDMS encapsulation layers. The proposed method yields a fully transparent encapsulation stack over a broad wavelength spectrum that can be used for the conformal encapsulation of flexible devices and thus, making them compatible with techniques such as optical imaging and optogenetics. © 2021 2021 23rd European Microelectronics and Packaging Conference and Exhibition, EMPC 2021. All rights reserved.

关键词： Adhesion

来源：评论

学校读者我要写书评

暂无评论

RASSS: A hijack-resistant confidential information management scheme for distributed systems

RASSS: A hijack-resistant confidential information managemen...

引用

作者： Bu, Lake Isakov, Mihailo Kinsy, Michel A. Adaptive and Secure Computing System Laboratory Department of Electrical and Computer Engineering Boston University Boston United States

In distributed systems there is often a need to store and share sensitive information (e.g., encryption keys, digital signatures, login credentials etc.) among the devices. It is also generally the case that this piece of information cannot be entrusted to any individual device since the malfunction or compromising of one node could jeopardize the security of the entire system. Even if the information is split among the devices, there is still a risk when an attacker can compromise a group of them. Therefore we have designed and implemented a secure and robust secret sharing scheme to enable a more resilient sharing of confidential information. This solution provides three important features: (i) it uses threshold secret sharing to split the information into shares to be kept by all devices in the system;so the information can only be retrieved collaboratively by groups of devices;(ii) it guarantees the privacy of the confidential information under a certain number of passive hijacking attacks;and (iii) it ensures the integrity of the confidential information against any number of hijackers who actively and collusively attack the devices. It is able to identify all the compromised devices, while still keeping the secret unforgeable to attackers. © 2019 Institution of engineering and Technology. All rights reserved.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Finite-control-set economic model predictive control for a DC/AC inverter

引用

Control engineering Practice 2025年 163卷

作者： Kong, Xiaobing Zhang, Pengyu Ma, Lele Zhu, Zheng Liu, Xiangjie Lee, Kwang Y. Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources North China Electric Power University Beijing102206 China The Department of Electrical and Computer Engineering Baylor University Waco TX 76798 United States

Finite-control-set model predictive control (FCS-MPC) is an effective approach for controlling modern power electronics. The three-level sparse neutral point clamped inverter (3L-SNPCI) fulfills the task of converting DC power into the desired three-phase AC power in high-renewable-penetration power systems. The stable and economic operation of the 3L-SNPCI is crucial to the security and reliability of renewable energy grid connection. Controlling of 3L-SNPCI is quite challenging, due to the strong nonlinearity and the discrete feasible region caused by the finite control set. In this paper, a stable economic model predictive control scheme is developed to achieve the key tasks of current tracking, neutral point voltage balance, and inverter economic performance by directly incorporating the economic indices into the controller design. The non-convex optimization problem caused by the inverter nonlinearity is transformed into a convex one with linear inequality constraints by employing the Big-M method. The bounded stability is indirectly guaranteed with the dynamic of the inverter control system approximating that of a stabilized continuous linear time-invariant system sharing the same parameters. Simulation and experiment concerning both the steady-state and transient-state conditions with different disturbance are presented to show the effectiveness and robustness of the proposed controller. © 2025

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Multi-granularity ensemble sample selection and label correction for classification with noisy labels

引用

Applied Soft Computing 2025年 180卷

作者： Kecan Cai Hongyun Zhang Witold Pedrycz Duoqian Miao Chaofan Chen Department of Computer Science and Technology Tongji University Shanghai 201804 PR China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 201804 PR China Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6G 2R3 Canada Systems Research Institute Polish Academy of Sciences 00-901 Warsaw Poland Istinye University Faculty of Engineering and Natural Sciences Department of Computer Engineering Sariyer/Istanbul Turkiye

Sample selection is crucial in classification tasks with noisy labels, yet most existing sample selection methods rely on a single criterion. These approaches often face challenges, including low purity of selected clean samples, and underfitting due to an insufficient number of selected clean training samples. To address these challenges, this paper proposes GNet-SSLC, a novel multi-granularity network framework that integrates multiple criteria ensemble sample selection (SS) and multiple views label correction (LC). In the SS phase, this paper proposes a metric learning-based dual k-Nearest Neighbor (k-NN) sample selection method. This method first uses corrected soft labels from the initial k-NN round to guide the selection of clean samples in the subsequent k-NN round. To further enhance selection accuracy, we combine this dual k-NN approach with a small loss sample selection technique through a voting mechanism. This multiple criteria ensemble method addresses the issues of low purity and instability inherent in single criterion approaches. In the LC phase, this paper designs a multiple views label correction framework that generates high-quality pseudo-labels for selected noisy samples. A key innovation of the framework is the design of a regularized contrastive learning loss, which optimizes the semi-supervised learning process by leveraging multiple views of training samples. The additional inclusion of training samples with high-quality pseudo-labels can effectively mitigate underfitting caused by a limited number of clean training samples. Experimental results on both synthetic and real-world noisy datasets indicate that GNet-SSLC enhances the purity and stability of the selected clean samples, and significantly improves classification performance. The enhancement is particularly notable with high noise rate dataset, such as CIFAR-100 dataset with 80% noise rate, achieving a 19.3% increase in classification accuracy compared to the baseline method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Phenology and Water Level Time-Series Mangrove Index for Improved Mangrove Monitoring

SSRN

引用

SSRN 2024年

作者： Sun, Weiwei Huang, Ke Yang, Gang Fu, Bolin Chen, Chao Meng, Xiangchao Feng, Tian Ge, Yong Department of Geography and Spatial Information Techniques Ningbo University Ningbo315211 China Zhejiang Collaborative Innovation Center Ningbo Universities Collaborative Innovation Center for Land and Marine Spatial Utilization and Governance Research Ningbo315211 China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences & Natural Resources Research Chinese Academy of Sciences Beijing100101 China College of Geomatics and Geoinformation Guilin University of Technology Guilin541006 China School of Geography Science and Geomatics Engineering Suzhou University of Science and Technology Suzhou215009 China

Mangroves are declining and degrading under the influence of human activities and natural factors, making their accurate mapping and dynamic monitoring essential. However, most of the existing mangrove indices based on the spectral characteristics of multispectral images have some limitations in recognition accuracy and universality. Therefore, this study aimed to develop a robust and efficient Phenology and Water level Time-series Mangrove Index (PWTMI) for mangrove monitoring. PWTMI is constructed by combining spectral and temporal characteristics from dense time-series multispectral data, wherein phenology and water level time-series characteristics are extracted from NDVI and MNDWI time series. The results show that PWTMI outperforms existing multispectral-based mangrove indices and has an accuracy similar to a hyperspectral-based mangrove index, with overall accuracy ranging from 91.49% to 98.83% and F1 score ranging from 0.91 to 0.98 in four typical areas in China, indicating great potential for long time-series and large-scale mangrove monitoring. © 2024, The Authors. All rights reserved.

关键词： Water levels

来源：评论

学校读者我要写书评

暂无评论

Modelling and Simulation of Induction Machine Under DC Current Injection Braking

Modelling and Simulation of Induction Machine Under DC Curre...

引用

IEEE International Conference on Control and Robotics engineering (ICCRE)

作者： Pichai Aree Department of Electrical and Computer Engineering Power System and Electrical Machine Research Group Klong Luang Pathumthani Thailand

ISBN: (数字)9781728167916

ISBN: (纸本)9781728167923

Three-phase Induction machines (IM) are widely used as industrial drive applications. Braking them through DC current injection is one of the interesting applications. In this paper, their mathematical models under DC injection are presented for simulating their braking performances under various connecting types of stator windings. The potential use of IM as the external brake unit to control the speed of another running motor for torque-speed curve testing is demonstrated using the computer simulation. The factors influencing the braking torque of IM are discussed.

关键词： Stator windings Torque Windings Rotors Mathematical model Induction motors

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：