检索结果-内蒙古大学图书馆

A Dual-Chaining Watermark Scheme for Data Integrity Protection in Internet of Things

computers, Materials & Continua 2019年第3期58卷 679-695页

作者： Baowei Wang Weiwen Kong Wei Li Neal NXiong Jiangsu Engineering Centre of Network Monitoring Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment TechnologySchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Engineering Research Center of Electronic Information and Control from Fujian Provincial Education Department Fuzhou350108China Department of Mathematics and Computer Science Northeastern State UniversityOklahomaUSA.

Chaining watermark is an effective way to verify the integrity of streaming data in wireless network environment,especially in resource-constrained sensor networks,such as the perception layer of Internet of Things ***,in all existing single chaining watermark schemes,how to ensure the synchronization between the data sender and the receiver is still an unsolved *** the synchronization points are attacked by the adversary,existing data integrity authentication schemes are difficult to work properly,and the false negative rate might be up to 50 *** the additional fixed group delimiters not only increase the data size,but are also easily detected by *** this paper,we propose an effective dual-chaining watermark scheme,called DCW,for data integrity protection in smart campus IoT *** proposed DCW scheme has the following three characteristics:(1)In order to authenticate the integrity of the data,fragile watermarks are generated and embedded into the data in a chaining way using dynamic grouping;(2)Instead of additional fixed group delimiters,chained watermark delimiters are proposed to synchronize the both transmission sides in case of the synchronization points are tampered;(3)To achieve lossless integrity authentication,a reversible watermarking technique is *** experimental results and security analysis can prove that the proposed DCW scheme is able to effectively authenticate the integrity of the data with free distortion at low cost in our smart meteorological Internet of Things system.

关键词： Dual-chaining reversible watermark integrity authentication Internet of things.

来源：评论

学校读者我要写书评

暂无评论

Survey on the Application of Deep Reinforcement Learning in Image Processing

引用

Journal on Artificial Intelligence 2020年第1期2卷 39-58页

作者： Wei Fang Lin Pang Weinan Yi School of Computer&Software Jiangsu Engineering Center of Network MonitoringNanjing University of Information Science&TechnologyNanjingChina State Key Laboratory for Novel Software Technology Nanjing UniversityNanjingChina Jiangsu Key Laboratory of Computer Information Process Technology Soochow UniversitySuzhouChina

feature representations from a large amount of data,and use reinforcement learning to learn the best strategy to complete the *** the combination of deep learning and reinforcement learning,end-to-end input and output can be achieved,and substantial breakthroughs have been made in many planning and decision-making systems with infinite states,such as games,in particular,AlphaGo,robotics,natural language processing,dialogue systems,machine translation,and computer *** this paper we have summarized the main techniques of deep reinforcement learning and its applications in image processing.

关键词： Reinforcement learning image processing

来源：评论

学校读者我要写书评

暂无评论

Survey on the Loss Function of Deep Learning in Face Recognition

引用

Journal of Information Hiding and Privacy Protection 2021年第1期3卷 29-45页

作者： Jun Wang Suncheng Feng Yong Cheng Najla Al-Nabhan Director of Science and Technology Industry Department Nanjing University of Information Science&TechnologyNanjingChina School of Computer&Software Jiangsu Engineering Center of Network MonitoringNanjing University of Information Science&TechnologyNanjingChina Science and Technology Industry Department Nanjing University of Information Science&TechnologyNanjingChina Deptratment of Computer Science King Saud UniversityRiyadhSaudi Arabia

With the continuous development of face recognition network,the selection of loss function plays an increasingly important role in improving *** loss function of face recognition network needs to minimize the intra-class distance while expanding the inter-class *** far,one of our mainstream loss function optimization methods is to add penalty terms,such as orthogonal loss,to further constrain the original loss *** other is to optimize using the loss based on angular/cosine *** last is Triplet loss and a new type of joint optimization based on HST Loss and ACT *** this paper,based on the three methods with good practical performance and the joint optimization method,various loss functions are thoroughly reviewed.

关键词： Loss function face recognition orthogonality loss ArcFace the joint loss

来源：评论

学校读者我要写书评

暂无评论

Mixed Noise Removal by Residual Learning of Deep CNN

引用

Journal of New Media 2020年第1期2卷 1-10页

作者： Kang Yang Jielin Jiang Zhaoqing Pan School of Computer and Software Jiangsu Engineering Center of Network MonitoringNanjing University of Information Science and TechnologyNanjing210044China Country Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing210044China

Due to the huge difference of noise distribution,the result of a mixture of multiple noises becomes very *** normal circumstances,the most common type of mixed noise is to add impulse noise(IN)and then white Gaussian noise(AWGN).From the reduction of cascaded IN and AWGN to the latest sparse representation,a great deal of methods has been proposed to reduce this form of mixed ***,when the mixed noise is very strong,most methods often produce a lot of *** order to solve the above problems,we propose a method based on residual learning for the removal of AWGN-IN noise in this *** training,our model can obtain stable nonlinear mapping from the images with mixed noise to the clean *** a series of experiments under different noise settings,the results show that our method is obviously better than the traditional sparse representation and patch based ***,the time of model training and image denoising is greatly reduced.

关键词： Mixed noise denoising residual learning deep convolutional neural

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Data-Collection with Rendezvous-Based Approaches in Large-Scale WSNs with Multi-UGV 1

引用

5th International Conference on Artificial Intelligence and Security, ICAIS 2019

作者： Zhang, Jian Tan, Ling Zhuang, Wei College of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China Jiangsu Engineering Center of Network Monitoring Nanjing210044 China

ISBN: (数字)9783030242657

ISBN: (纸本)9783030242640

Prolonging the lifetime of wireless sensor networks (WSNs) is a crucial issue referring to energy conservation or balancing of data collection. In this paper, we propose an optimal algorithm for data collection using UGVs based on clustering by definition of rendezvous nodes (RNs). Due to the considerable large difference of long-distance transmission, the rendezvous-based clustered model for load balancing with multiple UGVs is proposed. Furthermore, considering different delay-tolerant applications, we design a data transmission mode called Two-Orbit Back-Propagation algorithm (TOBPA). In these process, we utilized utility function on energy to realize the optimal energy consumption in the sense of energy transmission model and take energy balancing into account meanwhile. As a result, we analyze the cluster lifetimes in different situations and achieve balance to save significant. © 2019, Springer Nature Switzerland AG.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Genetic Algorithm Outsourcing in Cloud Computing

引用

Journal of Cyber Security 2020年第1期2卷 49-61页

作者： Leqi Jiang Zhangjie Fu College of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and TechnologyNanjing210044China

Genetic Algorithm(GA)has been widely used to solve various optimization *** the solving process of GA requires large storage and computing resources,it is well motivated to outsource the solving process of GA to the cloud ***,the algorithm user would never want his data to be disclosed to cloud ***,it is necessary for the user to encrypt the data before transmitting them to the *** the user will encounter a new *** arithmetic operations we are familiar with cannot work directly in the ciphertext *** this paper,a privacy-preserving outsourced genetic algorithm is *** user’s data are protected by homomorphic encryption algorithm which can support the operations in the encrypted *** is elaborately adapted to search the optimal result over the encrypted *** security analysis and experiment results demonstrate the effectiveness of the proposed scheme.

关键词： Homomorphic encryption genetic algorithm outsourcing cloud computing

来源：评论

学校读者我要写书评

暂无评论

Air Quality Forcasting based on Gated Recurrent Long Short-Term Memory Model 19

Air Quality Forcasting based on Gated Recurrent Long Short-T...

引用

2019 ACM Turing Celebration Conference - China, ACM TURC 2019

作者： Wang, Baowei Kong, Weiwen Guan, Hui School of Computer and Software Jiangsu Engineering Centre of Network Monitoring Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and Technology Nanjing China School of Computer and Software Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and Technology Nanjing China

ISBN: (纸本)9781450371582

With the continuous development of Chinese economy and the gradual acceleration of urbanization, it has caused tremendous damage to the *** effect of smog on people's lives has become more apparent. The bad air environment seriously damages the physical and mental health of people. Predicting smog becomes very ***,?how to accurately predict PM2.5 has become an important issue in recent years. The existing prediction models have limitations. They don't accurately capture the law between the concentration of haze and the factors affecting reality. It is difficult to accurately predict nonlinear smog data. One algorithm proposed in this paper is a two-layer model prediction algorithm based on Long Short Term Memory Neural network and Gated Recurrent Unit(LSTM&GRU). This algorithm is an improvement and enhancement of the existing prediction method Long Short Term Memory. The Recurrent Neural network (RNN) is used to process important events in the series of prediction intervals and time delays. LSTM&GRU is a time-characteristic neural network algorithm. The data of this experiment was obtained from Zhenqi Net(***). We selected daily smog data from 2014/1/1 to 2018/1/1 as a train and test dataset. The first 80% of the data was used for training and the rest for testing. The results of this experiment show that our model can play a better prediction. © 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Delay-Tolerant Rendezvous-Based Data Collection for Target Tracking in Large-Scale Wireless Sensor networks with UGV 1

引用

5th International Conference on Artificial Intelligence and Security, ICAIS 2019

作者： Zhang, Jian Xu, Jiang Wang, Tianbao College of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China Jiangsu Engineering Center of Network Monitoring Nanjing210044 China School of Electrical and Information Engineering Jiangsu University Zhenjiang212013 China

ISBN: (数字)9783030242657

ISBN: (纸本)9783030242640

Energy efficiency receives significant attention in wireless sensor networks. In this paper, a UGV is employed as an energy-efficient solution to prolong the network lifetime in target tracking. Data collection strategies for target tracking are investigated including the amount of data and the transmitted distances. For contributed data, the quantization technology is exploited for energy efficiency. Considering the uncertainty of sensing data, we determine a group from intra-cluster members to gather data. And then, we formulate our design a selection optimization problem, maximizing the utilization of the quality of contributed data using information matrix. As a result, we develop an optimization algorithm named rendezvous-based data collection (RDC). Furthermore, two stages of data collection for target tracking are analyzed with a UGV. Simulations verify that the proposed scheme achieves network energy saving as well as energy balance in the framework of target tracking. © 2019, Springer Nature Switzerland AG.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Real-time human cross-race aging-related face appearance detection with deep convolution architecture

Real-time human cross-race aging-related face appearance det...

引用

作者： Tian, Qing Zhang, Wenqiang Mao, Junxiang Yin, Hujun School of Computer and Software Nanjing University of Information Science and Technology Nanjing China Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and Technology Nanjing China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing China MIIT Key Laboratory of Pattern Analysis and Machine Intelligence Nanjing University of Aeronautics and Astronautics Nanjing China School of Electrical and Electronic Engineering The University of Manchester Manchester United Kingdom

Human age estimation (AE) is an emerging research topic in computer vision and machine learning and has attracted increasing amount of research due its wide potential applications. In the process of human aging, facial appearances change from glabrous to crinkly similarly across all races, from European, Hispanic and African to Asian. To specially explore the relationships between aging and facial appearances across races, this paper is devoted to determining the correspondence between facial aging and facial appearances. Specifically, we first extract appearance vector features from facial images with their spatial structure preserved. Then, we propose to select the aging-related features shared by different races to explore their aging-related common facial regions, while removing redundant features. Thirdly, we improve the proposed model by incorporating potential cross-race relationships in an automated learning manner. Additionally, we extend our model with deep convolution architecture. Finally, we evaluate the proposed methodologies on a large face aging database with real-time efficiency. © 2019, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving image retrieval based on additive secret sharing

arXiv

引用

arXiv 2020年

作者： Xia, Zhihua Gu, Qi Xiong, Lizhi Zhou, Wenhao Weng, Jian Engineering Research Center of Digital Forensics Ministry of Education School of Computer and Software Jiangsu Engineering Center of Network Monitoring Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology Nanjing University of Information Science & Technology Nanjing210044 China Jinan University Guangzhou510632 China

The rapid growth of digital images motivates individuals and organizations to upload their images to the cloud server. To preserve the privacy, image owners would prefer to encrypt the images before uploading, but it would strongly limit the efficient usage of images. Plenty of existing schemes on privacy-preserving Content-Based Image Retrieval (PPCBIR) try to seek the balance between security and retrieval ability. However, compared to the advanced technologies in CBIR like Convolutional Neural network (CNN), the existing PPCBIR schemes are far deficient in both accuracy and efficiency. With more cloud service providers, the collaborative secure image retrieval service provided by multiple cloud servers becomes possible. In this paper, inspired by additive secret sharing technology, we propose a series of additive secure computing protocols on numbers and matrices with better efficiency, and then show their application in PPCBIR. Specifically, we extract CNN features, decrease the dimension of features and build the index securely with the help of our protocols, which include the full process of image retrieval in plaintext domain. The experiments and security analysis demonstrate the efficiency, accuracy and security of our scheme. Copyright © 2020, 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

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：