检索结果-内蒙古大学图书馆

Convolutional sparse autoencoders for image classification

IEEE Transactions on Neural Networks and Learning Systems 2018年第7期29卷 3289-3294页

作者： Luo, Wei Li, Jun Yang, Jian Xu, Wei Zhang, Jian College of Mathematics and Informatics South China Agricultural University Guangzhou510000 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Computer Engineering Huaihai Institute of Technology Lianyungang222000 China

Convolutional sparse coding (CSC) can model local connections between image content and reduce the code redundancy when compared with patch-based sparse coding. However, CSC needs a complicated optimization procedure to infer the codes (i.e., feature maps). In this brief, we proposed a convolutional sparse auto-encoder (CSAE), which leverages the structure of the convolutional AE and incorporates the max-pooling to heuristically sparsify the feature maps for feature learning. Together with competition over feature channels, this simple sparsifying strategy makes the stochastic gradient descent algorithm work efficiently for the CSAE training;thus, no complicated optimization procedure is involved. We employed the features learned in the CSAE to initialize convolutional neural networks for classification and achieved competitive results on benchmark data sets. In addition, by building connections between the CSAE and CSC, we proposed a strategy to construct local descriptors from the CSAE for classification. Experiments on Caltech-101 and Caltech-256 clearly demonstrated the effectiveness of the proposed method and verified the CSAE as a CSC model has the ability to explore connections between neighboring image content for classification tasks. © 2012 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Intelligent reflecting surface aided multi-cell NOMA networks

arXiv

引用

arXiv 2020年

作者： Ni, Wanli Liu, Xiao Liu, Yuanwei Tian, Hui Chen, Yue State Key Lab. of Networking and Switching Technology Beijing Univ. of Posts and Telecommun Beijing China School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom

This paper proposes a novel framework of resource allocation in intelligent reflecting surface (IRS) aided multi-cell non-orthogonal multiple access (NOMA) networks, where a sum-rate maximization problem is formulated. To address this challenging mixed-integer non-linear problem, we decompose it into an optimization problem (P1) with continuous variables and a matching problem (P2) with integer variables. For the non-convex optimization problem (P1), iterative algorithms are proposed for allocating transmit power, designing reflection matrix, and determining decoding order by invoking relaxation methods such as convex upper bound substitution, successive convex approximation and semidefinite relaxation. For the combinational problem (P2), swap matching-based algorithms are proposed to achieve a two-sided exchange-stable state among users, BSs and subchannels. Numerical results are provided for demonstrating that the sum-rate of the NOMA networks is capable of being enhanced with the aid of the IRS. Copyright © 2020, The Authors. All rights reserved.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Progressive bilateral-context driven model for post-processing person Re-identification

arXiv

引用

arXiv 2020年

作者： Cao, Min Chen, Chen Dou, Hao Hu, Xiyuan Peng, Silong Kuijper, Arjan School of Computer Science and Technology Soochow University Suzhou215006 China Institute of Automation Chinese Academy of Sciences Beijing100190 China Fraunhofer IGD Darmstadt64283 Germany Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Computer Science and Engineering Nanjing University of Science and Technology China Mathematical and Applied Visual Computing TU Darmstadt Darmstadt64283 Germany

Most existing person re-identification methods compute pairwise similarity by extracting robust visual features and learning the discriminative metric. Owing to visual ambiguities, these content-based methods that determine the pairwise relationship only based on the similarity between them, inevitably produce a suboptimal ranking list. Instead, the pairwise similarity can be estimated more accurately along the geodesic path of the underlying data manifold by exploring the rich contextual information of the sample. In this paper, we propose a lightweight post-processing person re-identification method in which the pairwise measure is determined by the relationship between the sample and the counterpart’s context in an unsupervised way. We translate the point-to-point comparison into the bilateral point-to-set comparison. The sample’s context is composed of its neighbor samples with two different definition ways: the first order context and the second order context, which are used to compute the pairwise similarity in sequence, resulting in a progressive post-processing model. The experiments on four large-scale person re-identification benchmark datasets indicate that (1) the proposed method can consistently achieve higher accuracies by serving as a post-processing procedure after the content-based person re-identification methods, showing its state-of-the-art results, (2) the proposed lightweight method only needs about 6 milliseconds for optimizing the ranking results of one sample, showing its high-efficiency. Code is available at: https://***/123ci/PBCmodel. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Feedforward neural network based on ensemble evolutionary algorithm with self-adaptive strategy and parameter for intrusion detection

引用

International Journal of Wireless and Mobile Computing 2019年第2期17卷 202-211页

作者： Xue, Yu Tang, Tao Liu, Alex X. School of Computer and Software Nanjing University of Information Science and Technology Pukou Nanjing China Department of Computer Science and Engineering Michigan State University East Lansing United States

The applications of Wireless Sensor Networks (WSNs) have driven the development of many fields, and the information security is an important issue in the WSNs. Intrusion Detection System (IDS) is a kind of effective system for identifying network attacks and protecting data security, which has a great significance for WSNs. In this paper, we transform the intrusion detection problem into a classification problem and introduce the Feedforward Neural Network (FNN) classifier to solve it. At the same time, we propose a novel Self-adaptive Parameter and Strategy Differential Particle Swarm (SPS-DPS) optimisation algorithm to find the optimal weights for the FNN. Experiments are performed on eight data sets which are constructed based on the intrusion detection data set KDDCUP99, and the results are compared with five Evolutionary Computation (EC) methods. The results show that the SPS-DPS based FNN method can solve the intrusion detection problem well compared with the other methods. Copyright © 2019 Inderscience Enterprises Ltd.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Optimization Method for an Information Interaction Interface from Error-Cognition to Information Feature Mapping

Research Square

引用

Research Square 2020年

作者： Wu, Xiaoli Caldwell, Sabrina School of Design Art & Medial Nanjing University of Science & Technology Nanjing210094 China Research School of Computer Science The Australian National University ACT Australia College of Mechanical and Electrical Engineering Hohai University Changzhou China Lab of Human Factors and Information System Interaction & Design Hohai University Changzhou China

Background- With the rapid development of digital and intelligent information systems, display of visual information in interfaces has become an important challenge in the field of human-computer interaction. Objective- We propose a method for the optimization of information interaction interfaces from error-cognition through the mapping of information characteristics. Method- A mapping method of matrix description is adopted to analyze the association properties between error-cognition sets and design information sets. Results- Based on the mapping relationship between the domains of error-cognition and design information, a cross-correlational analysis is carried out between error-cognition and design information. Conclusion- We obtain the relationship matrix between the error-cognition of correlation between design information and the degree of importance among design information. Application- Taking the task interface of a warfare navigation display as an example, error factors and the features of design information are extracted. Based on the results, we also propose an optimization design scheme for the monitoring task interface. © 2020, CC BY.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

SEGIVE: A Practical Framework of Secure GPU Execution in Virtualization Environment

SEGIVE: A Practical Framework of Secure GPU Execution in Vir...

引用

IEEE International Conference on Performance, Computing and Communications (IPCCC)

作者： Ziyang Wang Fangyu Zheng Jingqiang Lin Guang Fan Jiankuo Dong State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Data Assurance and Communication Security Research Center CAS Beijing China School of Cyber Security University of Science and Technology of China Hefei School of Computer Science and Technology Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (数字)9781728198293

ISBN: (纸本)9781728198309

With the advancement of processor technology, general-purpose GPUs have become popular parallel computing accelerators in the cloud. However, designed for graphics rendering and high-performance computing, GPUs are born without sound security mechanisms. Consequently, the GPU-based service in the cloud is vulnerable to attacks from the potentially compromised guest OS as large amounts of sensitive code and data are offloaded directly to the unprotected *** this paper, we propose SEGIVE, a practical framework of secure GPU execution in the virtualization environment, which protects offloaded device code and data from disclosure or tampering by malicious guest OSes through the full life cycle of security-critical GPU applications. First, SEGIVE secures all the traffic transferred to GPUs with Intel SGX technology, including the users' sensitive data and GPU binaries. Second, with various memory isolation mechanisms, SEGIVE enhances security in multi-user execution scenarios by sharing a GPU among multiple workloads, which avoids underutilization of device resources. Besides, SEGIVE requires no modifications to application source codes, the GPU architecture, or I/O interconnection to fulfill security principles, and thus almost all prevailing GPU-based applications can easily benefit from SEGIVE with little porting effort. We have implemented SEGIVE with KVM-QEMU on off-the-shelf NVIDIA GPUs and CPUs. Evaluation results show that with security-enhances, the performance of SEGIVE prototype is still competitive to the native execution on compute-intensive applications, especially for the public-key cryptography algorithm.

关键词： Cloud computing Graphics processing units computer architecture Public key cryptography Software Security Virtualization

来源：评论

学校读者我要写书评

暂无评论

Frequency tunable non-reciprocal bandpass filter and diplexer using time-modulated microstrip λg/2 resonators

TechRxiv

引用

TechRxiv 2020年

作者： Wu, Xiaohu Nafe, Mahmoud Álvarez Melcón, Alejandro Gómez-Díaz, Juan Sebastián Liu, Xiaoguang School of Electronic and Information Engineering Nanjing University of Information Science and Technology Nanjing210044 China The Department of Electrical and Computer Engineering University of California Davis 95616 United States The Department of Information and Communication Technologies Technical University of Cartagena Murcia30202 Spain

This paper presents novel designs of frequency reconfigurable distributed non-reciprocal bandpass filter and diplexer based on spatio-temporally modulated microstrip λg/2 resonators. The modulation is achieved by loading both ends of the λg/2 transmission line resonators with time-modulated capacitors. To provide an inherent biasing isolation between the RF and the modulation signals, the modulation voltage source is connected at the center of the resonator, where there is a natural voltage null. A single inductor is used to further enhance such biasing isolation. The wideband nature of this isolation scheme enables the the tuning of the devices over a wide frequency range. With more than 30-dB RF to modulation isolation, the proposed resonator structure also enables low insertion loss by eliminating RF signal leakage to the modulation ports. Two examples of a 3-pole bandpass filter and a diplexer are demonstrated with good agreement between the measurement and the simulation. The fabricated filter shows a minimal insertion loss of 3.9 dB, a 20-dB isolation bandwidth of 42 MHz at 1.0 GHz, and frequency tuning range of 885–1031 MHz. The measured diplexer has two non-reciprocal bandpass channels at 829 MHz and 997 MHz, respectively. The two channels can be independently reconfigured without affecting each other. © 2020, CC BY-SA.

关键词： Bandpass filters

来源：评论

学校读者我要写书评

暂无评论

Deep learning methods for automatic evaluation of delayed enhancement-MRI. The results of the EMIDEC challenge

arXiv

引用

arXiv 2021年

作者： Lalande, Alain Chen, Zhihao Pommier, Thibaut Decourselle, Thomas Qayyum, Abdul Salomon, Michel Ginhac, Dominique Skandarani, Youssef Boucher, Arnaud Brahim, Khawla de Bruijne, Marleen Camarasa, Robin Correia, Teresa M. Feng, Xue Girum, Kibrom B. Hennemuth, Anja Huellebrand, Markus Hussain, Raabid Ivantsits, Matthias Ma, Jun Meyer, Craig Sharma, Rishabh Shi, Jixi Tsekos, Nikolaos V. Varela, Marta Wang, Xiyue Yang, Sen Zhang, Hannu Zhang, Yichi Zhou, Yuncheng Zhuang, Xiahai Couturier, Raphael Meriaudeau, Fabrice ImViA laboratory University of Burgundy Dijon France MRI department University Hospital of Dijon Dijon France Femto-ST laboratory University of Franche-Comté Belfort France Cardiology department University Hospital of Dijon Dijon France CASIS Company Quetigny France National Engineering School of Sousse University of Sousse Sousse Tunisia LASEE laboratory National Engineering School of Monastir University of Monastir Monastir Tunisia Biomedical Imaging Group Rotterdam Erasmus MC Rotterdam Netherlands Department of Radiology and Nuclear Medicine Erasmus MC Rotterdam Netherlands Department of Computer Science University of Copenhagen Copenhagen Denmark Centre of Marine Sciences University of Algarve Faro Portugal School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom Department of Biomedical Engineering University of Virginia Charlottesville United States Charité – Universitätsmedizin Berlin Berlin Germany Fraunhofer MEVIS Bremen Germany German Centre for Cardiovascular Research Berlin Germany Department of Mathematics Nanjing University of Science and Technology Nanjing China Data Analysis and Intelligent Systems Lab Department of Computer Science University of Houston Houston United States Medical Robotics and Imaging Lab Department of Computer Science University of Houston Houston United States National Heart and Lung Institute Imperial College London London United Kingdom College of Computer Science Sichuan University Chengdu China College of Biomedical Engineering Sichuan University Chengdu China School of Biological Science and Medical Engineering Beihang University Beijing China School of Data Science Fudan University Shanghai China

A key factor for assessing the state of the heart after myocardial infarction (MI) is to measure whether the myocardium segment is viable after reperfusion or revascularization therapy. Delayed enhancement-MRI or DE-MRI, which is performed several minutes after injection of the contrast agent, provides high contrast between viable and nonviable myocardium and is therefore a method of choice to evaluate the extent of MI. To automatically assess myocardial status, the results of the EMIDEC challenge that focused on this task are presented in this paper. The challenge’s main objectives were twofold. First, to evaluate if deep learning methods can distinguish between normal and pathological cases. Second, to automatically calculate the extent of myocardial infarction. The publicly available database consists of 150 exams divided into 50 cases with normal MRI after injection of a contrast agent and 100 cases with myocardial infarction (and then with a hyperenhanced area on DE-MRI), whatever their inclusion in the cardiac emergency department. Along with MRI, clinical characteristics are also provided. The obtained results issued from several works show that the automatic classification of an exam is a reachable task (the best method providing an accuracy of 0.92), and the automatic segmentation of the myocardium is possible. However, the segmentation of the diseased area needs to be improved, mainly due to the small size of these areas and the lack of contrast with the surrounding structures. © 2021, CC BY-NC-SA.

关键词： Cardiology

来源：评论

学校读者我要写书评

暂无评论

SALKG: A Semantic Annotation System for Building a High-quality Legal Knowledge Graph

SALKG: A Semantic Annotation System for Building a High-qual...

引用

IEEE International Conference on Big Data

作者： Mingwei Tang Cui Su Haihua Chen Jingye Qu Junhua Ding School of Information Engineering Nanjing Audit University Nanjing P. R. China The University of North Texa Denton USA College of Computer Science and Technology Beihua University Jilin P. R. China

ISBN: (数字)9781728162515

ISBN: (纸本)9781728162522

Knowledge graph has become an essential tool for semantic analysis with the development of natural language processing and deep learning. A high-quality knowledge graph is handy for building a high-performance knowledge-driven application. Despite recent advances in information extraction (IE) techniques, no suitable automated methods can be applied to constructing a domain-specific, comprehensive, and high-quality knowledge graph. However, a semi-automatic strategy, which can ensure the basic quality requirements of a knowledge graph, has been successfully implemented in the elementary science domain. This paper presents a semantic annotation system developed for building a high-quality legal knowledge graph (SALKG) using the semi-automatic strategy. We introduce its system design, architecture, algorithms, functions, and implementation. To investigate the effectiveness of SALKG, we conduct a preliminary annotation experiment with 280 legal texts which were collected from the Harvard Caselaw Access Project. The user evaluation from 32 graduate students demonstrates the high usability of SALKG in semantic annotation and the potential for building a high-quality legal knowledge graph. The system can also be adapted to other fields for constructing domain-specific knowledge graphs.

关键词： Law Annotations Semantics Big Data Tools Usability System analysis and design

来源：评论

学校读者我要写书评

暂无评论

Distributed Resource Allocation for Network Slicing of Bandwidth and Computational Resource

Distributed Resource Allocation for Network Slicing of Bandw...

引用

IEEE International Conference on Communications (ICC)

作者： Anqi Huang Yingyu Li Yong Xiao Xiaohu Ge Sumei Sun Han-Chieh Chao School of Electronic Information and Communications Huazhong Univ. of Science & Technology China Institute for Infocomm Research Singapore School of Electrical Engineering National Dong Hwa University Taiwan

ISBN: (数字)9781728150895

ISBN: (纸本)9781728150901

Network slicing has been considered as one of the key enablers for 5G to support diversified services and application scenarios. This paper studies the distributed network slicing utilizing both the spectrum resource offered by communication network and computational resources of a coexisting fog computing network. We propose a novel distributed framework based on a new control plane entity, regional orchestrator, which can be deployed between base stations and fog nodes to coordi- nate and control their bandwidth and computational resources. We propose a distributed resource allocation algorithm based on Alternating Direction Method of Multipliers with Partial Variable Splitting (DistADMM-PVS). We prove that DistADMM-PVS minimizes the average latency of the entire network and at the same time guarantee satisfactory latency performance for every supported type of service. Simulation results show that DistADMM-PVS converges much faster than some other existing algorithms. In addition, the joint network slicing with both bandwidth and computational resources offers around 15% overall latency reduction compared to network slicing with only a single resource.

关键词： Network slicing Task analysis Resource management Bandwidth Edge computing Delays computer architecture

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：