检索结果-内蒙古大学图书馆

2nd International Conference on Information engineering and Applications, IEA 2012

作者： Li, Hanguang Wang, Qi Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing 210044 China College of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China

ISBN: (纸本)9781447148555

Techniques called feature extraction and pattern recognition are implemented for nephogram representation and recognition. In this approach, the Gabor wavelets are used to extract features of ground nephograms. The principal component analysis (PCA) is applied on the Gabor transformed matrices to reduce the dimensions of these features. Finally by using these features, we can train support vector machine (SVM) classifiers for classifying cloud types. After finishing training, we can use these trained SVM classifiers to classify these cloud types. During these experiments, we used different Kernels and parameters for comparison. Experiment results indicated that the solution proposed in this paper was able to get a good accurate rate which was higher than the solution using Haar-like features and AdaBoost algorithm. © 2013 Springer-Verlag.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Training pool selection for semi-supervised learning

Training pool selection for semi-supervised learning

引用

9th International Symposium on Neural networks, ISNN 2012

作者： Ge, Jian Ma, Tinghuai Yan, Qiaoqiao Yan, Yonggang Tian, Wei Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology 210044 Nanjing China College of Computer and Software Nanjing University of Information Science and Technology 210044 Nanjing China

ISBN: (纸本)9783642313455

Semi-supervised leaning deals with methods for automatically exploiting unlabeled samples in addition to labeled set. The data selection is an important topic in active learning. It addresses the selection the valuable unlabeled data to label, considering that labeling data is a costly job. In this paper, we want to discuss in detail three aspects of technology in data selection, which includes how to select the unlabeled sample, how many unlabeled samples should be selected and how to define the capacity of the training pool. Experiments which use self-training based on C4.5 show that while the L labeled ratio lager continuous, the initial error value becomes smaller. Also when L labeled ratio is less than 10%, the selection ratio value should be set in less than *** error value has no significant change while selection ratio value larger than 1.0. © 2012 Springer-Verlag.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Research on the Signal Reconstruction of the Phased Array Structural Health monitoring Based Using the Basis Pursuit Algorithm

引用

computers, Materials & Continua 2019年第2期58卷 409-420页

作者： Yajie Sun Yanqing Yuan Qi Wang Lihua Wang Enlu Li Li Qiao Jiangsu Engineering Centre of Network Monitoring Nanjing University of Information Science and TechnologyNanjing210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China School of Information and Control Nanjing University of Information Science and TechnologyNanjing210044China Capability Systems Centre School of Engineering and Information TechnologyUniversity of New South WalesCanberra2600Australia

The signal processing problem has become increasingly complex and demand high acquisition system,this paper proposes a new method to reconstruct the structure phased array structural health monitoring *** method is derived from the compressive sensing theory and the signal is reconstructed by using the basis pursuit algorithm to process the ultrasonic phased array *** to the principles of the compressive sensing and signal processing method,non-sparse ultrasonic signals are converted to sparse signals by using sparse *** sparse coefficients are obtained by sparse decomposition of the original signal,and then the observation matrix is constructed according to the corresponding sparse ***,the original signal is reconstructed by using basis pursuit algorithm,and error analysis is carried *** research analysis shows that the signal reconstruction method can reduce the signal complexity and required the space efficiently.

关键词： Basis pursuit algorithm compressive sensing phased array signal reconstruction

来源：评论

学校读者我要写书评

暂无评论

Coverless steganography based on english texts using binary tags protocol

Coverless steganography based on english texts using binary ...

引用

作者： Wu, Yulei Chen, Xianyi Sun, Xingming Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology China Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology Nanjing University of Information Science and Technology China School of Computer and Software Nanjing University of Information Science and Technology China

Information hiding is an evolving and challenging research field. Lately, a novel information hiding method that utilizes the original cover without modification to transmit secret messages has raised attention of the scholars. This method, coverless information hiding, can resist various kinds of existing steganalysis techniques due to its property. In terms of text steganography, coverless information hiding methods have made headway, most of which aim at Chinese steganography. Thus, this paper proposes a coverless steganography based on English, using the tag based protocol to make the secret communication possible. Experimental results reveal that the proposed method has decent success rate and hiding capacity. © 2018 Taiwan Academic network Management Committee. All rights reserved.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Embedding Image Through Generated Intermediate Medium Using Deep Convolutional Generative Adversarial network

引用

computers, Materials & Continua 2018年第8期56卷 313-324页

作者： Chuanlong Li Yumeng Jiang Marta Cheslyar School of Computer and Software Nanjing University of Information Science and TechnologyNing Liu RoadNo.219Nanjing210044China Jiangsu Engineering Centre of Network Monitoring Ning Liu RoadNo.219Nanjing210044China School of Informatics University of EdinburghOld CollegeSouth BridgeEdinburghEH89YLUK

Deep neural network has proven to be very effective in computer vision *** convolutional network can learn the most suitable features of certain images without specific measure functions and outperform lots of traditional image processing *** adversarial network(GAN)is becoming one of the highlights among these deep neural *** is capable of generating realistic images which are imperceptible to the human vision system so that the generated images can be directly used as intermediate medium for many *** promising application of using GAN generated images would be image concealing which requires the embedded image looks like not being tampered to human vision system and also undetectable to most *** synthesizing has drawn lots of attention in computer vision field and is used for image concealing in steganography and *** traditional methods which use synthesized textures for information hiding mainly select features and mathematic functions by human metrics and usually have a low embedding *** paper takes advantage of the generative network and proposes an approach for synthesizing complex texture-like image of arbitrary size using a modified deep convolutional generative adversarial network(DCGAN),and then demonstrates the feasibility of embedding another image inside the generated texture while the difference between the two images is nearly invisible to the human eyes.

关键词： GAN,CNN,texture synthesis steganography watermark image concealing information hiding

来源：评论

学校读者我要写书评

暂无评论

Full-Blind Delegating Private Quantum Computation

引用

computers, Materials & Continua 2018年第8期56卷 211-223页

作者： Wenjie Liu Zhenyu Chen Jinsuo Liu Zhaofeng Su Lianhua Chi Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science&TechnologyNanjing210044China School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China State Grid Electric Power Research Institute NARI Group CorporationNanjing210003China Centre for Quantum Software and Information Faculty of Engineering and Information TechnologyUniversity of Technology SydneyNSW2007Australia Department of Computer Science and Information Technology La Trobe UniversityVIC3086Australia

The delegating private quantum computation(DQC)protocol with the universal quantum gate set{X,Z,H,P,R,CNOT}was firstly proposed by Broadbent et al.[Broadbent(2015)],and then Tan et al.[Tan and Zhou(2017)]tried to put forward a half-blind DQC protocol(HDQC)with another universal set{H,P,CNOT,T}.However,the decryption circuit of Toffoli gate(i.e.T)is a little redundant,and Tan et al.’s protocol[Tan and Zhou(2017)]exists the information *** addition,both of these two protocols just focus on the blindness of data(*** client’s input and output),but do not consider the blindness of computation(*** delegated quantum operation).For solving these problems,we propose a full-blind DQC protocol(FDQC)with quantum gate set{H,P,CNOT,T},where the desirable delegated quantum operation,one of{H,P,CNOT,T},is replaced by a fixed sequence(H,P,CZ,CNOT,T)to make the computation blind,and the decryption circuit of Toffoli gate is also *** shows that our protocol can not only correctly perform any delegated quantum computation,but also holds the characteristics of data blindness and computation blindness.

关键词： Delegating private quantum computation universal quantum gate set full-blind Toffoli gate circuit optimization

来源：评论

学校读者我要写书评

暂无评论

A simplification method of terrain modeling based on spatial-autocorrelation

International Journal of Multimedia and Ubiquitous Engineeri...

引用

International Journal of Multimedia and Ubiquitous engineering 2014年第5期9卷 185-194页

作者： Gu, Yunhua Wu, Xiaoyan Wang, Jin Jiangsu Engineering Center of Network Monitoring School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China

To solve the problem of three-dimensional terrain simplification in large-scale which was based on digital elevation model (DEM) data, a terrain simplified method based on the theory of spatial autocorrelation was proposed. The slope, a key factor for expressing the terrain features, has been taken into account in this method. According to principle of regional similarities in geomorphology is related to DEM data correlation, a cluster analysis was performed on the terrain data to get the thresholds distinguish terrain features. On the basis, the gradient-based distance-weighted method was adopted to fit elevation values of the center point and generated a new terrain mesh. The results of experiments show that the method to some extent reduces the size of the data, while maintaining good terrain features and curvature characteristic. © 2014 SERSC.

关键词： Geomorphology

来源：评论

学校读者我要写书评

暂无评论

LKAW: A Robust Watermarking Method Based on Large Kernel Convolution and Adaptive Weight Assignment

引用

computers, Materials & Continua 2023年第4期75卷 1-17页

作者： Xiaorui Zhang Rui Jiang Wei Sun Aiguo Song Xindong Wei Ruohan Meng Engineering Research Center of Digital Forensics Ministry of EducationJiangsu Engineering Center of Network MonitoringSchool of Computer and SoftwareNanjing University of Information Science&TechnologyNanjing210044China Wuxi Research Institute Nanjing University of Information Science&TechnologyWuxi214100China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET) Nanjing University of Information Science&TechnologyNanjing210044China School of Automation Nanjing University of Information Science&TechnologyNanjing210044China School of Instrument Science and Engineering Southeast UniversityNanjing211189China School of Teacher Education Nanjing University of Information Science&TechnologyNanjing210044China School of Computer Science Engineering Nanyang Technological UniversitySingapore

Robust watermarking requires finding invariant features under multiple attacks to ensure correct *** learning has extremely powerful in extracting features,and watermarking algorithms based on deep learning have attracted widespread *** existing methods use 3×3 small kernel convolution to extract image features and embed the ***,the effective perception fields for small kernel convolution are extremely confined,so the pixels that each watermarking can affect are restricted,thus limiting the performance of the *** address these problems,we propose a watermarking network based on large kernel convolution and adaptive weight assignment for loss *** uses large-kernel depth-wise convolution to extract features for learning large-scale image information and subsequently projects the watermarking into a highdimensional space by 1×1 convolution to achieve adaptability in the channel ***,the modification of the embedded watermarking on the cover image is extended to more *** the magnitude and convergence rates of each loss function are different,an adaptive loss weight assignment strategy is proposed to make theweights participate in the network training together and adjust theweight ***,a high-frequency wavelet loss is proposed,by which the watermarking is restricted to only the low-frequency wavelet sub-bands,thereby enhancing the robustness of watermarking against image *** experimental results show that the peak signal-to-noise ratio(PSNR)of the encoded image reaches 40.12,the structural similarity(SSIM)reaches 0.9721,and the watermarking has good robustness against various types of noise.

关键词： Robust watermarking large kernel convolution adaptive loss weights high-frequency wavelet loss deep learning

来源：评论

学校读者我要写书评

暂无评论

Improving communications with bluetooth enabled collaborative middleware in MANET

引用

Journal of China Universities of Posts and Telecommunications 2012年第SUPPL. 1期19卷 100-107页

作者： Gao, Feng Liu, Qi Hope, Martin Fan, Tong-Rang School of Information Science and Technology Shijiazhuang Tiedao University Shijiazhuang 050043 China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing 210044 China School of Computer Science and Engineering University of Salford Manchester M5 4WT United Kingdom

The main aim of the research presented in this paper was to investigate how can collaborative middleware based collaborative working environment (CWE), combined with bluetooth technology, enhance the communications of mobile users. The high level collaborative middleware is a research and technology development (RTD) challenge and a desirable research outputs for CWEs. This paper outlines a collaborative middleware that has been developed on smartphone technology and enables the creation of a multi-user CWE via a bluetooth network. To achieve this aim, it started with discussing the key design parameters, and then the design of collaborative middleware with collaborative functionality;ended by completed a strengths, weaknesses, opportunities, and threats (SWOT) analysis with focus group to determine the collaborative middleware's potential impact to improve communications between users. The result of the evaluation concludes the bluetooth enabled collaborative middleware can improve the communications of mobile ad-hoc networks. This research also provides two key areas of contribution. Firstly it provides an evolutionary step for the creation of new collaborative applications. Secondly, it has optimised the use of bluetooth beyond the functionality for which it was originally designed. © 2012 The Journal of China Universities of Posts and Telecommunications.

关键词： Bluetooth

来源：评论

学校读者我要写书评

暂无评论

Coverless information hiding method based on the Chinese mathematical expression 1st

Coverless information hiding method based on the Chinese mat...

引用

1st International Conference on Cloud Computing and Security, ICCCS 2015

作者： Chen, Xianyi Sun, Huiyu Tobe, Yoshito Zhou, Zhili Sun, Xingming School of Computer and Software and Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing Jiangsu210044 China Department of Computer Science New York University New YorkNY10012 United States Aoyama Gakuin University Kanagawa252-5258 Japan

ISBN: (纸本)9783319270500

Recently, many fruitful results have been presented in text information hiding such as text format-based, text image-based method and so on. However, existing information hiding approaches so far have been very difficult to resist the detecting techniques in steganalysis based on statistical analysis. Based on the Chinese mathematical expression, an efficient method of coverless text information hiding is presented, which is a brand-new method for information hiding. The proposed algorithm directly generates a stego-vector from the hidden information at first. Then based on text big data, a normal text that includes the stego-vector will be retrieved, which means that the secret messages can be send to the receiver without any modification for the stego-text. Therefore, this method is robust for any current steganalysis algorithm, and it has a great value in theory and practical significance. © Springer International Publishing Switzerland 2015.

关键词： Steganography

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：