检索结果-内蒙古大学图书馆

arXiv 2019年

作者： Teng, Tong Chen, Jie Zhang, Yehong Low, Bryan Kian Hsiang Department of Computer Science National University of Singapore Singapore College of Computer Science and Software Engineering Shenzhen University China

This paper presents a variational Bayesian kernel selection (VBKS) algorithm for sparse Gaussian process regression (SGPR) models. In contrast to existing GP kernel selection algorithms that aim to select only one kernel with the highest model evidence, our VBKS algorithm considers the kernel as a random variable and learns its belief from data such that the uncertainty of the kernel can be interpreted and exploited to avoid overconfident GP predictions. To achieve this, we represent the probabilistic kernel as an additional variational variable in a variational inference (VI) framework for SGPR models where its posterior belief is learned together with that of the other variational variables (i.e., inducing variables and kernel hyperparameters). In particular, we transform the discrete kernel belief into a continuous parametric distribution via reparameterization in order to apply VI. Though it is computationally challenging to jointly optimize a large number of hyperparameters due to many kernels being evaluated simultaneously by our VBKS algorithm, we show that the variational lower bound of the log-marginal likelihood can be decomposed into an additive form such that each additive term depends only on a disjoint subset of the variational variables and can thus be optimized independently. Stochastic optimization is then used to maximize the variational lower bound by iteratively improving the variational approximation of the exact posterior belief via stochastic gradient ascent, which incurs constant time per iteration and hence scales to big data. We empirically evaluate the performance of our VBKS algorithm on synthetic and massive real-world datasets. Copyright © 2019, The Authors. All rights reserved.

关键词： Additives

来源：评论

学校读者我要写书评

暂无评论

A proactive defense mechanism for mobile communication user data

引用

science China(Information sciences) 2018年第10期61卷 266-268页

作者： Caixia LIU Xinsheng JI Jiangxing WU Xiao QIN The National Digital Switching System Engineering & Technological R&D Center Department of Computer Science and Software Engineering Samuel Ginn College of EngineeringAuburn University

Dear editor,Several studies have recently reported on major vulnerabilities in the Signaling System No.7 (SS7)used in mobile networks [1, 2]. The reported vulnerabilities and security issues would lead to the illegal acquisition and tampering of mobile communication user data, known as cellphone user data. The cellphone user data contain important information such as identity identification, location identification, security parameter-set. Due to

关键词： A proactive defense mechanism for mobile communication user data MSISDN

来源：评论

学校读者我要写书评

暂无评论

Attribute-Based Searchable Encryption Scheme Supporting Efficient Range Search in Cloud Computing

Attribute-Based Searchable Encryption Scheme Supporting Effi...

引用

IEEE Conference on Dependable and Secure Computing

作者： Yuan Li Haiyan Wang Shulan Wang Yong Ding College of Computer Science and Software Engineering Shenzhen University Shenzhen P. R. China Peng Cheng Laboratory Cyberspace Security Research Center Shenzhen P. R. China College of Big Data and Internet Shenzhen Technology University Shenzhen P. R. China Guangxi Key Laboratory of Cryptography Information Security Guilin P. R. China

ISBN: (数字)9781728175348

ISBN: (纸本)9781728175355

With the widespread application of cloud computing technology, data privacy security problem becomes more serious. The recent studies related to searchable encryption (SE) area have shown that the data owners can share their private data with efficient search function and high-strength security. However, the search method has yet to be perfected, compared with the plaintext search mechanism. In this paper, based LSSS matrix, we give a new searchable algorithm, which is suitable for many search method, such as exact search, Boolean search and range search. In order to improve the search efficiency, the 0, 1-coding theory is introduced in the process of ciphertext search. Meanwhile it is shown that multi-search mechanism can improve the efficiency of data sharing. Finally, the performance analysis is presented, which prove our scheme is secure, efficient, and human-friendly.

关键词： Cloud computing Data privacy Search methods Conferences Encryption Performance analysis Security

来源：评论

学校读者我要写书评

暂无评论

Research on Green Energy Saving ECO Intelligent System engineering Cycle

Research on Green Energy Saving ECO Intelligent System Engin...

引用

作者： Jue-Jia Chen Shinn-Dar Wu Dong-Yan Chen Jie Li Ta-Wei Huang Software Engineering Department of Computer Science Neusoft Institute Guangdong School of Chemistry and Materials Engineering Huizhou University USA Saint Paul's College & DePaul University Royal Global Business Center Department of information management and Engineering Neusoft Institute Guangdong

With the improvement of living standards, the national coverage of heaters is also higher. From the original only the northern part of the installation of heating devices, to the south of the central area has also installed heaters, and even some people in the southern area installed heaters. With the increase in sales volume and fierce competition, companies need to reform and innovate products to meet the higher requirements of customers for energy-saving effects, comfort and safety. The design of the heater involves theories of structure, integrated circuit, program algorithm, aerodynamics, heat transfer and so on. Due to the technical level and cost constraints of enterprises, few companies can produce safe, energy-saving, moisturizing and comfortable heaters suitable for the public. In this study, the green energy-saving circulating heater of ECO intelligent system adopts the incremental ECO processing algorithm, with the single-chip STC89 C52 as the main control chip system, combined with the peripheral STC89 C52 temperature data acquisition, HIH-3010 humidity data collector, A/D Conversion module, keyboard settings, LCD1602 liquid crystal display and other circuit modules. This design realizes the temperature value that the heater provides the user with the optimum indoor temperature value and sets the heating according to the user's needs. When the set temperature value is reached or the temperature is high, the controller will control the heating element to reduce power or automatically power off to achieve safe power saving effect.

关键词： .Green energy saving ECO intelligent system engineering

来源：评论

学校读者我要写书评

暂无评论

Correction:A Lightweight Approach for Skin Lesion Detection through Optimal Features Fusion

引用

computers, Materials & Continua 2025年第1期82卷 1459-1459页

作者： Khadija Manzoor Fiaz Majeed Ansar Siddique Talha Meraj Hafiz Tayyab Rauf Mohammed A.El-Meligy Mohamed Sharaf Abd Elatty E.Abd Elgawad Department of Information Technology University of GujratGujrat50700Pakistan Department of Software Engineering University of GujratGujrat50700Pakistan Department of Computer Science COMSATS University Islamabad-Wah CampusWah Cantt47040Pakistan Independent Researcher BradfordBD80HSUK Advanced Manufacturing Institute King Saud UniversityRiyadh11421Saudi Arabia Department of Industrial Engineering College of EngineeringKing Saud UniversityRiyadh11421Saudi Arabia

In the article“A Lightweight Approach for Skin Lesion Detection through Optimal Features Fusion”by Khadija Manzoor,Fiaz Majeed,Ansar Siddique,Talha Meraj,Hafiz Tayyab Rauf,Mohammed ***-Meligy,Mohamed Sharaf,Abd Elatty *** Elgawad computers,Materials&Continua,2022,Vol.70,No.1,pp.1617–***:10.32604/cmc.2022.018621,URL:https://***/cmc/v70n1/44361,there was an error regarding the affiliation for the author Hafiz Tayyab *** of“Centre for Smart Systems,AI and Cybersecurity,Staffordshire University,Stoke-on-Trent,UK”,the affiliation should be“Independent Researcher,Bradford,BD80HS,UK”.

关键词： Fusion Skin Feature

来源：评论

学校读者我要写书评

暂无评论

Emotional semantics-preserved and feature-aligned CycleGAN for visual emotion adaptation

arXiv

引用

arXiv 2020年

作者： Zhao, Sicheng Chen, Xuanbai Yue, Xiangyu Lin, Chuang Xu, Pengfei Krishna, Ravi Yang, Jufeng Ding, Guiguang Sangiovanni-Vincentelli, Alberto L. Keutzer, Kurt School of Software Ts-inghua University Beijing100084 China College of Computer Science Nankai University Tianjin300350 China Department of Electrical Engineering and Computer Sciences University of California Berkeley94709 United States Didi Chuxing Beijing China

Thanks to large-scale labeled training data, deep neural networks (DNNs) have obtained remarkable success in many vision and multimedia tasks. However, because of the presence of domain shift, the learned knowledge of the well-trained DNNs cannot be well generalized to new domains or datasets that have few labels. Unsupervised domain adaptation (UDA) studies the problem of transferring models trained on one labeled source domain to another unlabeled target domain. In this paper, we focus on UDA in visual emotion analysis for both emotion distribution learning and dominant emotion classification. Specifically, we design a novel end-to-end cycle-consistent adversarial model, termed CycleEmotionGAN++. First, we generate an adapted domain to align the source and target domains on the pixel-level by improving CycleGAN with a multi-scale structured cycle-consistency loss. During the image translation, we propose a dynamic emotional semantic consistency loss to preserve the emotion labels of the source images. Second, we train a transferable task classifier on the adapted domain with feature-level alignment between the adapted and target domains. We conduct extensive UDA experiments on the Flickr-LDL & Twitter-LDL datasets for distribution learning and ArtPhoto & FI datasets for emotion classification. The results demonstrate the significant improvements yielded by the proposed CycleEmotionGAN++ as compared to state-of-the-art UDA approaches. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects

arXiv

引用

arXiv 2021年

作者： Ahmad, Muhammad Shabbir, Sidrah Roy, Swalpa Kumar Hong, Danfeng Wu, Xin Yao, Jing Khan, Adil Mehmood Mazzara, Manuel Distefano, Salvatore Chanussot, Jocelyn Department of Computer Science National University of Computer and Emerging Sciences Islamabad Chiniot-Faisalabad Campus Chiniot35400 Pakistan Dipartimento di Matematica e Informatica-MIFT University of Messina Messina98121 Italy Pakistan The Department of Computer Science and Engineering Jalpaiguri Government Engineering College West Bengal 735102 India The Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China The School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Fractional Signals and Systems Beijing100081 China The Institute of Data Science and Artificial Intelligence Innopolis University Innopolis 420500 Russia Institute of Software Development and Engineering Innopolis University Innopolis420500 Russia The Univ. Grenoble Alpes CNRS Grenoble INP GIPSA-Lab Grenoble38000 France

Hyperspectral Imaging (HSI) has been extensively utilized in many real-life applications because it benefits from the detailed spectral information contained in each pixel. Notably, the complex characteristics i.e., the nonlinear relation among the captured spectral information and the corresponding object of HSI data make accurate classification challenging for traditional methods. In the last few years, Deep Learning (DL) has been substantiated as a powerful feature extractor that effectively addresses the nonlinear problems that appeared in a number of computer vision tasks. This prompts the deployment of DL for HSI classification (HSIC) which revealed good performance. This survey enlists a systematic overview of DL for HSIC and compared state-of-the-art strategies of the said topic. Primarily, we will encapsulate the main challenges of traditional machine learning for HSIC and then we will acquaint the superiority of DL to address these problems. This survey breakdown the state-of-the-art DL frameworks into spectral-features, spatial-features, and together spatial-spectral features to systematically analyze the achievements (future research directions as well) of these frameworks for HSIC. Moreover, we will consider the fact that DL requires a large number of labeled training examples whereas acquiring such a number for HSIC is challenging in terms of time and cost. Therefore, this survey discusses some strategies to improve the generalization performance of DL strategies which can provide some future guidelines. © 2021, CC BY.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

ABC: An Auction-Based Blockchain Consensus-Incentive Mechanism

ABC: An Auction-Based Blockchain Consensus-Incentive Mechani...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Zhengpeng Ai Yuan Liu Xingwei Wang Software College Northeastern University Shenyang China Ministry of Education Key Laboratory of Data Analytics and Optimization for Smart Industry (NEU) Shenyang China School of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (数字)9781728190747

ISBN: (纸本)9781728183824

The rapid development of blockchain technology and its various applications have attracted huge attention in the last five years. The consensus mechanism and incentive mechanism are the backbone of a blockchain network. The consensus mechanism plays a crucial role in sustaining the network security, integrity, and efficiency. The incentive mechanism motivates the distributed nodes to “mine” so as to participate the consensus mechanism. The existing mechanisms bear the fairness and justice issues. In this paper, from the perspective of mechanism design, we propose a consensus-incentive mechanism through applying continuous double auction theory, which is abbreviated as ABC mechanism. Our mechanism consists of four stages, including initiation stage, auction stage, completion stage, and confirmation stage. The auction model in use is the continuous double auction to ensure the transactions are stored in a real-time manner. Through extensive experimental evaluations, our mechanism is proven to improve the fairness and justice of the blockchain network.

关键词： Conferences Blockchain Real-time systems Security Communication networks

来源：评论

学校读者我要写书评

暂无评论

Application Architecture of Product Information Traceability Based on Blockchain Technology and a Lightweight Secure Collaborative Computing Scheme

Application Architecture of Product Information Traceability...

引用

E-Commerce and Internet Technology (ECIT), International Conference on

作者： Jiayi Hu Jiahui Deng Nathaniel Gao Jiawei Qian International school Jiangxi University of Finance and Economics Nanchang China College of business and economics Australian National University Canberra Australia Computer science and software engineering East China Normal University Shanghai China

ISBN: (数字)9781728159027

ISBN: (纸本)9781728159034

In the course of the rapid development of e-commerce in China, the problems of information asymmetry, unclear market responsibilities and traceability of product information in B2C sales have been restricting the long-term development of China's online retail market. In the special period when novel coronavirus is raging, e-commerce is very consequential for related medical industries such as surgical masks. Given the gradual development of blockchain technology, it can be explored to employ this technology as a basis to solve the problem of information traceability in the B2C sales process, and through the blockchain's distributed storage architecture, lightweight digital signature algorithm, consistency algorithm and other technologies to make up for product security vulnerabilities, to prevent information from being tampered with. Nevertheless, the authenticity, reliability and integrity of blockchain information transmission can also be solved by the EPC system network technology and Hash Encryption Algorithm. In this paper, we design a product information traceability application framework based on blockchain technology, aiming at the urgent need to solve the product traceability of mask enterprises during the current new crown epidemic. Also, for the corresponding scenarios in e-commerce, we propose a lightweight cooperation scheme based on blockchain technology and give security analysis. Based on lightweight cryptography, our scheme achieves identity-based authentication, peer-to-peer communication and secure collaborative computing.

关键词： blockchain practical electronic commerce platform product information traceability electronic commerce Product Labeling traceability B2C Lightweight Collaborative computing surgical mask program architecture

来源：评论

学校读者我要写书评

暂无评论

Hiding Color Image within a video file using Discrete Wavelets Transform and Artificial Neural Networks

Hiding Color Image within a video file using Discrete Wavele...

引用

International Conference on Electrical, Communication, computer, Power, and Control engineering (ICECCPCE)

作者： Hasan M. Ahmed Department of Software Engineering College of Computer Science and Mathematics / University of Mosul Mosul Iraq

ISBN: (数字)9781728107813

ISBN: (纸本)9781728107820

Growing up technology services and the needing to exchange various information lead to accumulating a large amount of data across computer networks. Internet and private networks are examples of such networks. Transferring the data between computers increases the risk of un-authorizing access of unauthorized people. Protecting data is so important to be safe from unexpected and invisible threats, which are difficult to detect as most notably intrusion and *** aim of this paper is to hide a digital color image inside a digital video file using the Discrete Wavelets Transform (DWT) and Artificial Neural Networks (ANNs). The digital video file, which represents the cover, is splitted into a set of frames and partitioned into three colored layers (red, green and blue). The discrete wavelets transform technique is applied to each one of the three *** hide the colored image (watermark), it is firstly partitioned into the three colored layers (red, green and blue). Then, it is layered into a set of clusters. The ANNs are used as artificial hiding techniques to hide each cluster in the digital video *** results showed that the use of the DWT and ANNs are effective and encourage in hiding data. After applying this work algorithms to a set of samples, the results also showed harmony and compatibility in the process of concealment with the treated samples.

关键词： Discrete wavelet transforms computer architecture Watermarking Training Microprocessors

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：