检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yu, Ercong Zhu, Jinle Li, Qiang Liu, Zilong Chen, Hongyang Shamai, Shlomo Poor, H. Vincent The Yangtze Delta Region Institute University of Electronic Science and Technology of China Huzhou313098 China Chengdu611731 China The School of Computer Science and Electronics Engineering University of Essex United Kingdom The Research Center for Graph Computing Zhejiang Lab Hangzhou311100 China The Technion-Israel Institute of Technology Haifa320003 Israel The Department of Electrical Engineering Princeton University PrincetonNJ08544 United States

This paper is focused on multiuser load modulation arrays (MU-LMAs) which are attractive due to their low system complexity and reduced cost for millimeter wave (mmWave) multi-input multi-output (MIMO) systems. The existing precoding algorithm for downlink MU-LMA relies on a sub-array structured (SAS) transmitter which may suffer from decreased degrees of freedom and complex system configuration. Furthermore, a conventional LMA codebook with codewords uniformly distributed on a hypersphere may not be channel-adaptive and may lead to increased signal detection complexity. In this paper, we conceive an MU-LMA system employing a full-array structured (FAS) transmitter and propose two algorithms accordingly. The proposed FAS-based system addresses the SAS structural problems and can support larger numbers of users. For LMA-imposed constant-power downlink precoding, we propose an FAS-based normalized block diagonalization (FAS-NBD) algorithm. However, the forced normalization may result in performance degradation. This degradation, together with the aforementioned codebook design problems, is difficult to solve analytically. This motivates us to propose a Deep Learning-enhanced (FAS-DL-NBD) algorithm for adaptive codebook design and codebook-independent decoding. It is shown that the proposed algorithms are robust to imperfect knowledge of channel state information and yield excellent error performance. Moreover, the FAS-DL-NBD algorithm enables signal detection with low complexity as the number of bits per codeword increases. Copyright © 2023, The Authors. All rights reserved.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

Sufficient Conditions for Robust Safety in Differential Inclusions Using Barrier Functions

arXiv

引用

arXiv 2022年

作者： Maghenem, Mohamed Ghanbarpour, Masoumeh Saoud, Adnane Université Grenoble Alpes CNRS Grenoble-INP GIPSA-lab GrenobleF-38000 France Department of Electrical and Computer Engineering University of California Santa Cruz United States CentraleSupelec University ParisSaclay France UM6P College of Computing Benguerir Morocco

This paper considers robust-safety notions for differential inclusions. A general framework is proposed to certify the considered notions in terms of barrier functions. While most existing literature studied only what we designate by uniform robust safety, in this paper, we make a clear distinction between uniform and non-uniform robust-safety. For both cases, we establish sufficient (infinitesimal) conditions on the nominal (unperturbed) system. That is, our conditions involve only the barrier function and the system’s right-hand side. Our results allow for unbounded safety regions as well as non-smooth barrier functions. Throughout the paper, examples are provided to illustrate our results. Copyright © 2022, The Authors. All rights reserved.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

Chosen Plaintext Attack on Jpeg Image Encryption with Adaptive Key and Run Consistency

SSRN

引用

SSRN 2022年

作者： He, Hongjie Yuan, Yuan Chen, Fan Ye, Yuyun Tai, Heng-Ming Key Lab of Signal & Information Processing Southwest Jiaotong University Sichuan Province Chengdu611756 China Department of Electrical and Computer Engineering University of Tulsa TulsaOK74104 United States School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China

A JPEG image encryption with an adaptive key generated by a preserved characteristic not only lowers the cost of key management but also enhances the ability to resist various attacks. However, there are still security risks under the chosen-plaintext attack (CPA) conditions. This paper designs a novel CPA scheme to obtain details of the original image. First, the adaptive key can be reproduced from the encrypted image, so that the plaintext images with the same adaptive key can be constructed. Second, the existence of run consistency of MCUs (RCM), which facilitates rapid estimation. In addition, the single permutation for the runs of MCUs with RCM is designed for more accurate estimation. Experimental results show that two plaintext images are sufficient to get the image details. For an image of high quality factors (QFs≥90) or with rich complex texture, the accuracy ratio of estimated permutation sequence is close to 100%. © 2022, The Authors. All rights reserved.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

MAPA: Multi-Accelerator Pattern Allocation Policy for Multi-Tenant GPU Servers

MAPA: Multi-Accelerator Pattern Allocation Policy for Multi-...

引用

Supercomputing Conference

作者： Kiran Ranganath Joshua D. Suetterlein Joseph B. Manzano Shuaiwen Leon Song Daniel Wong Department of Electrical and Computer Engineering University of California Riverside CA USA High-Performance Computing Group Pacific Northwest National Lab WA USA Future System Architecture Lab School of Computer Science University of Sydney Sydney Australia

ISBN: (数字)9781450384421

ISBN: (纸本)9781665483902

Multi-accelerator servers are increasingly being deployed in shared multi-tenant environments (such as in cloud data centers) in order to meet the demands of large-scale compute-intensive workloads. In addition, these accelerators are increasingly being inter-connected in complex topologies and workloads are exhibiting a wider variety of inter-accelerator communication patterns. However, existing allocation policies are ill-suited for these emerging use-cases. Specifically, this work identifies that multi-accelerator workloads are commonly fragmented leading to reduced bandwidth and increased latency for inter-accelerator communication. We propose Multi-Accelerator Pattern Allocation (MAPA), a graph pattern mining approach towards providing generalized allocation support for allocating multi-accelerator workloads on multi-accelerator servers. We demonstrate that MAPA is able to improve the execution time of multi-accelerator workloads and that MAPA is able to provide generalized benefits across various accelerator topologies. Finally, we demonstrate a speedup of 12.4% for 75th percentile of jobs with the worst case execution time reduced by up to 35% against baseline policy using MAPA.

关键词： Network topology Processor scheduling High performance computing Graphics processing units Throughput Hardware Topology

来源：评论

学校读者我要写书评

暂无评论

SpEx+: A complete time domain speaker extraction network 21

SpEx+: A complete time domain speaker extraction network

引用

21st Annual Conference of the International Speech Communication Association, INTERSPEECH 2020

作者： Ge, Meng Xu, Chenglin Wang, Longbiao Chng, Eng Siong Dang, Jianwu Li, Haizhou Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China School of Computer Science and Engineering Nanyang Technological University Singapore Japan Advanced Institute of Science and Technology Ishikawa Japan Department of Electrical and Computer Engineering National University of Singapore Singapore Machine Listening Lab University of Bremen Germany

ISBN: (纸本)9781713820697

Speaker extraction aims to extract the target speech signal from a multi-talker environment given a target speaker's reference speech. We recently proposed a time-domain solution, SpEx, that avoids the phase estimation in frequency-domain approaches. Unfortunately, SpEx is not fully a time-domain solution since it performs time-domain speech encoding for speaker extraction, while taking frequency-domain speaker embedding as the reference. The size of the analysis window for time-domain and the size for frequency-domain input are also different. Such mismatch has an adverse effect on the system performance. To eliminate such mismatch, we propose a complete time-domain speaker extraction solution, that is called SpEx+. Specifically, we tie the weights of two identical speech encoder networks, one for the encoder-extractor-decoder pipeline, another as part of the speaker encoder. Experiments show that the SpEx+ achieves 0.8dB and 2.1dB SDR improvement over the state-of-the-art SpEx baseline, under different and same gender conditions on WSJ0-2mix-extr database respectively. Copyright © 2020 ISCA

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Microscopic-based analysis of nuclei in spheroids via SUNSHINE: An on-chip workflow integrating optical clearing, fluorescence calibration and supervoxel segmentation

引用

computers in Biology and Medicine 2025年 187卷 109761-109761页

作者： Lin, Chia-Hsiang Leng, Zi-Chao Yu, Chien-Hsin Deori Bharali, Lui Kirtan Lin, Cheng-Li Mao, Bin-Hsu Tu, Ting-Yuan Department of Electrical Engineering National Cheng Kung University Tainan City70101 Taiwan Institute of Computer and Communication Engineering Department of Electrical Engineering National Cheng Kung University Tainan City70101 Taiwan Department of Biomedical Engineering College of Engineering National Cheng Kung University Tainan City70101 Taiwan Department of Biotechnology and Medical Engineering National Institute of Technology Odisha Rourkela769008 India Department of Orthopedic Surgery National Cheng Kung University Hospital Tainan City704 Taiwan Skeleton Materials and Biocompatibility Core Lab Research Center of Clinical Medicine National Cheng Kung University Hospital Tainan City704 Taiwan National Cheng Kung University Hospital Tainan City704 Taiwan Musculoskeletal Research Center Innovative Headquarter National Cheng Kung University Tainan City70101 Taiwan Miin Wu School of Computing National Cheng Kung University Tainan City70101 Taiwan Meta-nanoPhotonics Center National Cheng Kung University Tainan City70101 Taiwan Medical Device Innovation Center National Cheng Kung University Tainan City70101 Taiwan

Multicellular spheroids (MCSs) are increasingly employed as 3D cell culture models in biomedical research due to their ability to effectively replicate in vivo cell interactions, making them suitable for high-throughput drug screening. Accurate cell counting is critical for data normalization, therapeutic evaluation, and exploration of culture conditions;however, affordable software solutions for 3D cell counting using microscopic images are limited. To fill this gap, we created SUNSHINE, an innovative on-chip analytical workflow that uniquely merges optical clearing, histogram matching (HM)-assisted fluorescence calibration, and simple linear iterative clustering (SLIC) supervoxel segmentation. This tool offers an efficient method for analyzing the characteristics and counts of fluorescence-labeled nuclei within MCSs. While optical clearing improves the penetration depth of microscopic imaging, deeper regions of thicker samples often yield faint fluorescence signals. SUNSHINE resolves this issue through the HM image post-processing algorithm. Moreover, SLIC is an effective alternative to traditional contour-wise segmentation, enabling the identification of irregularly shaped fluorescent nuclei. We found that SUNSHINE generated results comparable to commercial software like Imaris and machine learning (ML)-based tools, such as StarDist and Cellpose, in our analysis of the effects of seeding density and cell type on spheroid growth. We also used it to measure the volume and spatial distribution of nuclei, focusing on the hypoxic and peripheral regions of spheroids. Overall, this study finds that SUNSHINE serves as a valuable and economical approach for characterizing cellular activity and interactions in 3D, diminishing the reliance on costly proprietary software. © 2025

关键词： Cell culture

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant Quaternion Neural Network Fast Terminal Sliding Mode Control for Guidance and Navigation of UAV’s under Actuator Faults

Fault-Tolerant Quaternion Neural Network Fast Terminal Slidi...

引用

International Conference on Control, Automation and Diagnosis (ICCAD)

作者： Fernando E. Serrano Ahmad Taher Azar Saim Ahmed Nashwa Ahmad Kamal Ibraheem Kasim Ibraheem Instituto de Investigación en Energía Universidad Nacional Autónoma de Honduras Tegucigalpa Honduras Instituto de Robóticae Informática Industrial IRI-CSIC Universidad Politécnica de Cataluña Barcelona España College of Computer and Information Sciences Prince Sultan University Riyadh Saudi Arabia Automated Systems and Soft Computing Lab (ASSCL) Prince Sultan University Riyadh Saudi Arabia Faculty of Computers and Artificial Intelligence Benha University Benha Egypt Faculty of Engineering Cairo University Giza Egypt Department of Electrical Engineering College of Engineering University of Baghdad Baghdad Iraq Department of Electronics and Communication Engineering Uruk University Baghdad Iraq

ISBN: (数字)9798350361025

ISBN: (纸本)9798350361032

This research presents a terminal sliding mode controller and quaternion neural network observer for unmanned aerial vehicle (UAV) guidance and navigation under actuator fault. Initially, to determine which of a quadrotor’s four actuators is failing, a quaternion neural network observer is created. The quadrotor dynamic model includes the DC motor dynamics, which is taken into account when designing the fault-tolerant observer. The quaternion neural network presents four failure modes pertaining to an actuator state in which instability and divergence from the healthy state occur when one of the actuators fails. Next, a fault-tolerant terminal sliding mode controller is engineered to deliver the necessary controller action when all actuators are functioning normally, or if one or more quadrotor UAV actuators malfunction. The rapid terminal sliding mode controller is built in order to acquire the diverse control laws when one or many actuators fail or when the system is in healthy state. The suitable Lyapunov functional at various time instants is taken into account throughout the construction of this fault-tolerant controller to restore optimal performance. In addition to the theoretical outcomes of this investigation, a simulation is run to demonstrate the effectiveness of the observer/controller approach and to contrast it with other sliding mode and neural network observer/controller combinations. The research study’s conclusions and discussions are given at the end.

关键词： Fault diagnosis Actuators Fault tolerance Quaternions Fault tolerant systems Neural networks Observers

来源：评论

学校读者我要写书评

暂无评论

A Novel Load Balancing Scheme for Mobile Edge computing

arXiv

引用

arXiv 2021年

作者： Duan, Zhenhua Tian, Cong Zhang, Nan Zhou, Mengchu Yu, Bin Wang, Xiaobing Guo, Jiangen Wu, Ying Institute of Computing Theory and Technology ISN Lab Xidian University Xi’an710071 China Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States

To overcome long propagation delays for data exchange between the remote cloud data center and end devices in Mobile Cloud computing (MCC), Mobile Edge computing (MEC) is emerging to push mobile computing, network control and storage to the network edges. A cloudlet in MEC is a mobility-enhanced small-scale cloud, which contains several MEC servers located in close proximity to mobile devices. The main purpose of a cloudlet is to stably provide services to mobile devices with low latency. When a cloudlet offers hundreds kinds of services to millions of mobile devices, it is critical to balance the loads so as to improve performance. In this paper, we propose a three-layer mobile hybrid hierarchical P2P (MHP2P) model as a cloudlet. MHP2P performs satisfactory service lookup efficiency and system scalability as well as high stability. More importantly, a load balance scheme is provided so that the loads of MHP2P can be well balanced with the increasing of MEC servers and query load. A large number of simulation experiments indicate that the proposed scheme is efficient for enhancing the load balancing performance in MHP2P based MEC systems. Copyright © 2021, The Authors. All rights reserved.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning

arXiv

引用

arXiv 2023年

作者： Wu, Qiong Li, Jiahan Dai, Pingyang Ye, Qixiang Cao, Liujuan Wu, Yongjian Ji, Rongrong Institute of Artificial Intelligence The Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University Xiamen361005 China School of Information and Control Engineering China University of Mining and Technology Xuzhou221000 China The Media Analytics and Computing Laboratory Department of Artificial Intelligence School of Informatics Xiamen University Xiamen361005 China The Peng Cheng Laboratory Shenzhen518066 China The School of Electronics Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing100049 China The Media Analytics and Computing Lab Department of Computer Science School of Informatics Xiamen University Xiamen361005 China The Youtu Laboratory Tencent Shanghai200233 China The Fujian Engineering Research Center of Trusted Artificial Intelligence Analysis and Application Institute of Artificial Intelligence Xiamen University Xiamen361005 China

Unsupervised domain adaptation person re-identification (Re-ID) aims to identify pedestrian images within an unlabeled target domain with an auxiliary labeled source-domain dataset. Many existing works attempt to recover reliable identity information by considering multiple homogeneous networks. And take these generated labels to train the model in the target domain. However, these homogeneous networks identify people in approximate subspaces and equally exchange their knowledge with others or their mean net to improve their ability, inevitably limiting the scope of available knowledge and putting them into the same mistake. This paper proposes a Dual-level Asymmetric Mutual Learning method (DAML) to learn discriminative representations from a broader knowledge scope with diverse embedding spaces. Specifically, two heterogeneous networks mutually learn knowledge from asymmetric subspaces through the pseudo label generation in a hard distillation manner. The knowledge transfer between two networks is based on an asymmetric mutual learning manner. The teacher network learns to identify both the target and source domain while adapting to the target domain distribution based on the knowledge of the student. Meanwhile, the student network is trained on the target dataset and employs the ground-truth label through the knowledge of the teacher. Extensive experiments in Market-1501, CUHK-SYSU, and MSMT17 public datasets verified the superiority of DAML over state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

State-of-the-Art Deep Learning Methods on Electrocardiogram Data: Systematic Review

引用

JMIR Medical Informatics 2022年第8期10卷 e38454页

作者： Petmezas, Georgios Stefanopoulos, Leandros Kilintzis, Vassilis Tzavelis, Andreas Rogers, John A. Katsaggelos, Aggelos K. Maglaveras, Nicos Lab of Computing Medical Informatics and Biomedical-Imaging Technologies The Medical School Aristotle University of Thessaloniki Thessaloniki Greece Department of Biomedical Engineering Northwestern University Evanston IL United States Department of Material Science Northwestern University Evanston IL United States Department of Electrical and Computer Engineering Northwestern University Evanston IL United States

Background: Electrocardiogram (ECG) is one of the most common noninvasive diagnostic tools that can provide useful information regarding a patient’s health status. Deep learning (DL) is an area of intense exploration that leads the way in most attempts to create powerful diagnostic models based on physiological signals. Objective: This study aimed to provide a systematic review of DL methods applied to ECG data for various clinical applications. Methods: The PubMed search engine was systematically searched by combining “deep learning” and keywords such as “ecg,” “ekg,” “electrocardiogram,” “electrocardiography,” and “electrocardiology.” Irrelevant articles were excluded from the study after screening titles and abstracts, and the remaining articles were further reviewed. The reasons for article exclusion were manuscripts written in any language other than English, absence of ECG data or DL methods involved in the study, and absence of a quantitative evaluation of the proposed approaches. Results: We identified 230 relevant articles published between January 2020 and December 2021 and grouped them into 6 distinct medical applications, namely, blood pressure estimation, cardiovascular disease diagnosis, ECG analysis, biometric recognition, sleep analysis, and other clinical analyses. We provide a complete account of the state-of-the-art DL strategies per the field of application, as well as major ECG data sources. We also present open research problems, such as the lack of attempts to address the issue of blood pressure variability in training data sets, and point out potential gaps in the design and implementation of DL models. Conclusions: We expect that this review will provide insights into state-of-the-art DL methods applied to ECG data and point to future directions for research on DL to create robust models that can assist medical experts in clinical decision-making. ©Georgios Petmezas, Leandros Stefanopoulos, Vassilis Kilintzis, Andreas Tzavelis, John A Rogers

关键词： clinical decision CNN convolutional neural networks decision support deep learning diagnostic tools ECG ECG databases electrocardiogram long short-term memory LSTM residual neural network ResNet

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：