检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Yanlin Chen Xiaoqing Zhang Tianao Wang Chen Tang Haili Ye Jiang Liu Department of Computer Science and Engineering Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Shenzhen Institute of Advanced Technology Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Chinese Academy of Sciences Shenzhen China School of Ophthalmology and Optometry Wenzhou Medical University Wenzhou China The Oujiang Laboratory The Affiliated Eye Hospital Wenzhou Medical University Wenzhou China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Pathology symptoms of Parkinson disease (PD) are different from those of retinal diseases in the retinal layers, which are subtle. However, segmenting pathology information of PD from retinal layers automatically based on optical coherence tomography (OCT) images has not been studied before. Although existing Transformer-based segmentation methods have achieved good segmentation results, they have limitations in capturing local context information. Convolutional neural networks (CNNs) can construct local context dependencies among pixels, which is complementary to Transformers. Particularly, edge information extraction is significant for accurate retinal layer segmentation, which is ignored by both Transformers and CNNs but can be captured by frequency domain learning methods. To fully leverage the advantages of Transformers, CNNs, and frequency domain learning methods, we propose a Wavelet Transformer (WaveFormer) for retinal layer segmentation based on OCT images. In the WaveFormer, we design a Wavelet Spatial Attention block to exploit the potential of frequency information. Based on these advantages, WaveFormer can be data-efficient in limited OCT images of PD. The experimental results on the OCT-PD segmentation dataset show that our WaveFormer outperforms existing Transformers and CNNs. For example, WaveFormer outperforms Swin-UNet by 3.41% of IoU.

关键词： Learning systems Image segmentation Pathology Wavelet domain Image edge detection Frequency-domain analysis Transformers

来源：评论

学校读者我要写书评

暂无评论

Creating Single Color Centers in Nanodiamonds with Ion Implantation

Creating Single Color Centers in Nanodiamonds with Ion Impla...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Xiaohui Xu Zachariah O. Martin Michael Titze Yongqiang Wang Demid Sychev Jacob Henshaw Alexei S. Lagutchev Han Htoon Ed Bielejec Simeon Bogdanov Vladimir M. Shalaev Alexandra Boltasseva School of Materials Engineering Birck Nanotechnology Center Purdue University West Lafayette IN USA Elmore Family School of Electrical and Computer Engineering Birck Nanotechnology Center Purdue University West Lafayette IN USA Sandia National Laboratories Albuquerque New Mexico USA Los Alamos National Laboratory Los Alamos New Mexico USA Department of Electrical and Computer Engineering Nick Holonyak Jr. Micro and Nanotechnology Laboratory Illinois Quantum Information Science and Technology Center University of Illinois at Urbana-Champaign Urbana Illinois USA

We report the first demonstration of single silicon vacancy center creation in 20 nm nanodiamonds using silicon ion implantation combined with thermal annealing. Room-temperature single photon emission with linewidth ... 详细信息

ISBN: (纸本)9781957171258

关键词： Defect center materials Emission Ion beams Ions Near infrared radiation Photons

来源：评论

学校读者我要写书评

暂无评论

Collaborative Authentication for 6G Networks: An Edge Intelligence based Autonomous Approach

arXiv

引用

arXiv 2023年

作者： Fang, He Xiao, Zhenlong Wang, Xianbin Xu, Li Hanzo, Lajos The School of Electronic and Information Engineering Soochow University Soochow215301 China The Department of Informatics and Communication Engineering School of Informatics Xiamen University Xiamen361005 China The Department of Electrical and Computer Engineering Western University LondonONN6A 5B9 Canada The College of Computer and Cyber Security The Fujian Provincial Key Laboratory of Network Security and Cryptology Fujian Normal University Fuzhou350117 China School of Electronics and Computer Science University of Southampton SO17 1BJ United Kingdom

The conventional device authentication of wireless networks usually relies on a security server and centralized process, leading to long latency and risk of single-point of failure. While these challenges might be mitigated by collaborative authentication schemes, their performance remains limited by the rigidity of data collection and aggregated result. They also tend to ignore attacker localization in the collaborative authentication process. To overcome these challenges, a novel collaborative authentication scheme is proposed, where multiple edge devices act as cooperative peers to assist the service provider in distributively authenticating its users by estimating their received signal strength indicator (RSSI) and mobility trajectory (TRA). More explicitly, a distributed learning-based collaborative authentication algorithm is conceived, where the cooperative peers update their authentication models locally, thus the network congestion and response time remain low. Moreover, a situation-aware secure group update algorithm is proposed for autonomously refreshing the set of cooperative peers in the dynamic environment. We also develop an algorithm for localizing a malicious user by the cooperative peers once it is identified. The simulation results demonstrate that the proposed scheme is eminently suitable for both indoor and outdoor communication scenarios, and outperforms some existing benchmark schemes. Copyright © 2023, The Authors. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Multiscale Graph Neural Networks for Protein Residue Contact Map Prediction

arXiv

引用

arXiv 2022年

作者： Liu, Kuang Kalia, Rajiv K. Liu, Xinlian Nakano, Aiichiro Nomura, Ken-Ichi Vashishta, Priya Zamora-Resendiz, Rafael Collaboratory for Advanced Computing and Simulations Department of Computer Science Department of Physics & Astronomy Department of Chemical Engineering & Materials Science Department of Quantitative & Computational Biology University of Southern California Los AngelesCA90089 United States Department of Computer Science Hood College FrederickMD21701 United States Lawrence Berkeley National Laboratory BerkeleyCA94720 United States

Machine learning (ML) is revolutionizing protein structural analysis, including an important subproblem of predicting protein residue contact maps, i.e., which amino-acid residues are in close spatial proximity given the amino-acid sequence of a protein. Despite recent progresses in ML-based protein contact prediction, predicting contacts with a wide range of distances (commonly classified into short-, medium- and long-range contacts) remains a challenge. Here, we propose a multiscale graph neural network (GNN) based approach taking a cue from multiscale physics simulations, in which a standard pipeline involving a recurrent neural network (RNN) is augmented with three GNNs to refine predictive capability for short-, medium- and long-range residue contacts, respectively. Test results on the ProteinNet dataset show improved accuracy for contacts of all ranges using the proposed multiscale RNN+GNN approach over the conventional approach, including the most challenging case of long-range contact prediction. © 2022, CC BY.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A BCLC Staging System for Hepatocellular Carcinoma using Swin Transformer and CT Imaging

A BCLC Staging System for Hepatocellular Carcinoma using Swi...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Shun-Cheng Chang Pochuang Wang Weichung Wang Tung-Hung Su Jia-Horng Kao Che Lin Graduate Institute of Communication Engineering National Taiwan University (NTU) Taipei Taiwan Department of Computer Science and Information Engineering NTU Taipei Taiwan NTU Institute of Applied Mathematical Sciences Taipei Taiwan Department of Internal Medicine Division of Gastroenterology and Hepatology National Taiwan University Hospital Taipei Taiwan Department of Electrical Engineering NTU Taipei Taiwan NTU Center for Advanced Computing and Imaging in Biomedicine Taipei Taiwan NTU Smart Medicine and Health Informatics Program Taipei Taiwan

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

The Barcelona Clinic Liver Cancer (BCLC) staging system plays a crucial role in clinical planning, offering valuable insights for effectively managing hepatocellular carcinoma. Accurate prediction of BCLC stages can significantly ease the workload on radiologists. However, few datasets are explicitly designed for discerning BCLC stages. Despite the common practice of appending BCLC labels to clinical data within datasets, the inherent imbalance in BCLC distribution is further amplified by the diverse purposes for which datasets are curated. In this study, we aim to develop a BCLC staging system using the advanced Swin Transformer model. Additionally, we explore the integration of two datasets, each originally intended for separate objectives, highlighting the critical challenge of preserving class distribution in practical study designs. This exploration is pivotal for ensuring the applicability of our developed staging system in the designed clinical settings. Our resulting BCLC staging system demonstrates an accuracy of 55.81% (±7.8%), contributing to advancing medical image-based research for predicting BCLC stages.

关键词： Liver cancer Accuracy Computed tomography Biological system modeling Transformers Planning Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Fea Study on the Tsv Copper Filling Influenced by the Additives and Electroplating Process

SSRN

引用

SSRN 2023年

作者： Zhao, Zifeng Liu, Ziyu Chen, Lin Sun, Qingqing Liu, Hongye Sun, Yabin School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China State Key Laboratory of ASIC and System School of Microelectronics Fudan University Shanghai200433 China Jiashan Fudan Institute Zhejiang Province Jiaxing314100 China Department of Electrical Engineering East China Normal University Shanghai200241 China

Abstract Through-Silicon Via (TSV) is a key technology of three-dimensional (3D) integration. However, it is easy to have voids in the Cu filling process of TSV. Additives and optimized filling process are used to solve this problem. However, the comprehensive analysis of these affecting parameter needs many experiments and cost much time. Thus, the finite element analysis (FEA) for the mass transferring of electroplating is carried out by the COMSOL software in the work. The filling processes with different inhibitor concentrations are first studied and the most suitable density of 64mol/m2 is obtained. However, high inhibitor concentration will lead to much lower plating speed. Thus, the effect of filling process such as current density and plating bath flow velocity on the voids are investigated under the optimized concentrations above. The best filling quality is obtained at the current density of 1.4 ASD and the bath stirring velocity of 0.4 m/s. The underlying growth mechanism of these influencing factors are also analyzed and revealed. © 2023, The Authors. All rights reserved.

关键词： Copper

来源：评论

学校读者我要写书评

暂无评论

Photonic Indistinguishability of the Tin-Vacancy Center in Nanostructured Diamond

引用

Physical Review Letters 2022年第17期129卷 173603-173603页

作者： Jesús Arjona Martínez Ryan A. Parker Kevin C. Chen Carola M. Purser Linsen Li Cathryn P. Michaels Alexander M. Stramma Romain Debroux Isaac B. Harris Martin Hayhurst Appel Eleanor C. Nichols Matthew E. Trusheim Dorian A. Gangloff Dirk Englund Mete Atatüre Cavendish Laboratory University of Cambridge JJ Thomson Avenue Cambridge CB3 0HE United Kingdom Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Cambridge Massachusetts 02139 USA Department of Engineering Science University of Oxford Parks Road Oxford OX1 3PJ United Kingdom

Tin-vacancy centers in diamond are promising spin-photon interfaces owing to their high quantum efficiency, large Debye-Waller factor, and compatibility with photonic nanostructuring. Benchmarking their single-photon indistinguishability is a key challenge for future applications. Here, we report the generation of single photons with 99.7−2.5+0.3% purity and 63(9)% indistinguishability from a resonantly excited tin-vacancy center in a single-mode waveguide. We obtain quantum control of the optical transition with 1.71(1)-ns-long π pulses of 77.1(8)% fidelity and show it is spectrally stable over 100 ms. A modest Purcell enhancement factor of 12 would enhance the indistinguishability to 95%.

关键词： Coherent control Color centers Laser spectroscopy Nanophotonics Optical coherence Photoemission Photon statistics Quantum control Quantum description of light-matter interaction Quantum optics Quantum optics with artificial atoms Single photon sources

来源：评论

学校读者我要写书评

暂无评论

Group Movable Antenna With Flexible Sparsity: Joint Array Position and Sparsity Optimization

arXiv

引用

arXiv 2024年

作者： Lu, Haiquan Zeng, Yong Jin, Shi Zhang, Rui The National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing210096 China The Purple Mountain Laboratories Nanjing211111 China School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen518172 China The Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

Movable antenna (MA) is a promising technology to exploit the spatial variation of wireless channel for performance enhancement, by dynamically varying the antenna position within a certain region. However, for multi-antenna communication systems, moving each antenna independently not only requires prohibitive complexity to find the optimal antenna positions, but also incurs sophisticated movement control in practice. To address this issue, this letter proposes a new MA architecture termed group MA (GMA), enabling the group movement of all elements collectively in a continuous manner, and simultaneously achieving flexible array architecture by antenna selection (AS). In this letter, we focus on the uniform sparse array based GMA, where equally spaced antenna elements are selected to achieve desired array sparsity. The array position and sparsity level are jointly optimized to maximize the sum rate of the multi-user communication system. Numerical results verify the necessity to optimize the position and sparsity of GMA, and considerable performance gain is achieved as compared to the conventional fixed-position antenna (FPA). Copyright © 2024, The Authors. All rights reserved.

关键词： Antenna arrays

来源：评论

学校读者我要写书评

暂无评论

Movable Antenna for Wireless Communications: Prototyping and Experimental Results

arXiv

引用

arXiv 2024年

作者： Dong, Zhenjun Zhou, Zhiwen Xiao, Zhiqiang Zhang, Chaoyue Li, Xinrui Min, Hongqi Zeng, Yong Jin, Shi Zhang, Rui The National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing210096 China The Purple Mountain Laboratories Nanjing211111 China The School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen518172 China The Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

Movable antenna (MA), which can flexibly change the position of antenna in three-dimensional (3D) continuous space, is an emerging technology for achieving full spatial performance gains. In this paper, a prototype of MA communication system with ultra-accurate movement control is presented to verify the performance gain of MA in practical environments. The prototype utilizes the feedback control to ensure that each power measurement is performed after the MA moves to a designated position. The system operates at 3.5 GHz or 27.5 GHz, where the MA moves along a one-dimensional horizontal line with a step size of 0.01λ and in a two-dimensional square region with a step size of 0.05λ, respectively, with λ denoting the signal wavelength. The scenario with mixed line-of-sight (LoS) and non-LoS (NLoS) links is considered. Extensive experimental results are obtained with the designed prototype and compared with the simulation results, which validate the great potential of MA technology in improving wireless communication performance. For example, the maximum variation of measured power reaches over 40 dB and 23 dB at 3.5 GHz and 27.5 GHz, respectively, thanks to the flexible antenna movement. In addition, experimental results indicate that the power gain of MA system relies on the estimated path state information (PSI), including the number of paths, their delays, elevation and azimuth angles of arrival (AoAs), as well as the power ratio of each path. Copyright © 2024, The Authors. All rights reserved.

关键词： Feedback control

来源：评论

学校读者我要写书评

暂无评论

Fast, Accurate Manifold Denoising by Tunneling Riemannian Optimization

arXiv

引用

arXiv 2025年

作者： Wang, Shiyu Avagyan, Mariam Shen, Yihan Lamy, Arnaud Wang, Tingran Márka, Szabolcs Márka, Zsuzsa Wright, John Department of Electrical Engineering Columbia University New York United States Data Science Institute Columbia University New York United States Department of Computer Science Columbia University New York United States Department of Physics Columbia University New York United States Columbia Astrophysics Laboratory Columbia University New York United States Department of Applied Physics and Applied Mathematics Columbia University New York United States

Learned denoisers play a fundamental role in various signal generation (e.g., diffusion models) and reconstruction (e.g., compressed sensing) architectures, whose success derives from their ability to leverage low-dimensional structure in data. Existing denoising methods, however, either rely on local approximations that require a linear scan of the entire dataset or treat denoising as generic function approximation problems, often sacrificing efficiency and interpretability. We consider the problem of efficiently denoising a new noisy data point sampled from an unknown ddimensional manifold M ∈ D, using only noisy samples. This work proposes a framework for test-time efficient manifold denoising, by framing the concept of "learning-to-denoise" as "learning-to-optimize". We have two technical innovations: (i) online learning methods which learn to optimize over the manifold of clean signals using only noisy data, effectively "growing" an optimizer one sample at a time. (ii) mixed-order methods which guarantee that the learned optimizers achieve global optimality, ensuring both efficiency and near-optimal denoising performance. We corroborate these claims with theoretical analyses of both the complexity and denoising performance of mixed-order traversal. Our experiments on scientific manifolds demonstrate significantly improved complexity-performance tradeoffs compared to nearest neighbor search, which underpins existing provable denoising approaches based on exhaustive search. Copyright © 2025, The Authors. All rights reserved.

关键词： Nearest neighbor search

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：