检索结果-内蒙古大学图书馆

A new watermarking scheme for colour image using QR decomposition and ternary coding

MULTIMEDIA TOOLS AND APPLICATIONS 2019年第7期78卷 8113-8132页

作者： Su, Qingtang Liu, Yonghui Liu, Decheng Yuan, Zihan Ning, Hongye Ludong Univ Sch Informat & Elect Engn Yantai 264025 Peoples R China Shanghai Dianji Univ Sch Elect Engn Shanghai 201306 Peoples R China

At present, the binary images are often used as the original watermark images of many watermarking methods, but partial methods cannot be easily extended to colour image watermarking methods. For resolving this problem, we propose a new watermarking method using ternary coding and QR decomposition for colour image. In the procedure of embedding watermark, the colour image watermark is coded to ternary information;the colour host image is also separated into image blocks of sized 3x3, and these image blocks are further decomposed via QR decomposition;then, one ternary watermark is embedded into one orthogonal matrix Q of QR decomposition by the proposed rules. In the procedure of extracting watermark, the proposed method uses the blind-manner to extract the embedded ternary information. The novelty of this scheme lies in the proposed ternary coding for watermark image, which can improve the imperceptibility, embedded watermark capacity and real-time feature of the watermarking scheme. The results of simulation show the presented technique is better than other compared schemes with respect to imperceptibility, embedded watermark capacity and real-time feature under the similar robustness.

关键词： QR decomposition ternary coding Blind watermarking Colour image

来源：评论

学校读者我要写书评

暂无评论

ternary Compression for Communication-Efficient Federated Learning

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2022年第3期33卷 1162-1176页

作者： Xu, Jinjin Du, Wenli Jin, Yaochu He, Wangli Cheng, Ran East China Univ Sci & Technol Minist Educ Key Lab Adv Control & Optimizat Chem Proc Shanghai 200237 Peoples R China Tongji Univ Shanghai Inst Intelligent Sci & Technol Shanghai 200092 Peoples R China Univ Surrey Dept Comp Sci Guildford GU2 7XH Surrey England Tongji Univ Shanghai Inst Intelligent Sci & Technol Shanghai 200092 Peoples R China Southern Univ Sci & Technol Dept Comp Sci & Engn Guangdong Prov Key Lab Brain Inspired Intelligen Shenzhen 518055 Peoples R China

Learning over massive data stored in different locations is essential in many real-world applications. However, sharing data is full of challenges due to the increasing demands of privacy and security with the growing use of smart mobile devices and Internet of thing (IoT) devices. Federated learning provides a potential solution to privacy-preserving and secure machine learning, by means of jointly training a global model without uploading data distributed on multiple devices to a central server. However, most existing work on federated learning adopts machine learning models with full-precision weights, and almost all these models contain a large number of redundant parameters that do not need to be transmitted to the server, consuming an excessive amount of communication costs. To address this issue, we propose a federated trained ternary quantization (FTTQ) algorithm, which optimizes the quantized networks on the clients through a self-learning quantization factor. Theoretical proofs of the convergence of quantization factors, unbiasedness of FTTQ, as well as a reduced weight divergence are given. On the basis of FTTQ, we propose a ternary federated averaging protocol (T-FedAvg) to reduce the upstream and downstream communication of federated learning systems. Empirical experiments are conducted to train widely used deep learning models on publicly available data sets, and our results demonstrate that the proposed T-FedAvg is effective in reducing communication costs and can even achieve slightly better performance on non-IID data in contrast to the canonical federated learning algorithms.

关键词： Communication efficiency deep learning federated learning ternary coding

来源：评论

学校读者我要写书评

暂无评论

A self-adaptive soft-recoding strategy for performance improvement of error-correcting output codes

引用

PATTERN RECOGNITION 2023年第1期143卷

作者： Lin, Guangyi Gao, Jie Zeng, Nan Xu, Yong Liu, Kunhong Wang, Beizhan Yao, Junfeng Wu, Qingqiang Xiamen Univ Sch Informat Xiamen 361005 Peoples R China Xiamen Univ Technol Sch Elect Engn & Automat Xiamen 361024 Peoples R China Fujian Med Univ Sch Publ Hlth Fuzhou 350122 Peoples R China Fujian Univ Technol Sch Comp Sci & Math Fuzhou 350016 Peoples R China

The technique of error-correcting output codes (ECOC) has been proven to be of high discriminative ability in many classification applications. However, most algorithms on the ECOC were designed based on the binary or ternary codes (referred to as the hard codes), which might fail to precisely correct errors in dealing with tough tasks. In this study, a Soft-Recoding strategy based on a self-adaptive algorithm is proposed, which replaces the traditional hard codes with the real-value elements to better fit the output distribution of the base learners. This is achieved by minimizing the ratio of two distances: the distance of the output vector to the ground-truth class, and the average distance of the output vector to the remaining classes. Extensive experiments using five different hard ECOC algorithms and the corresponding softened versions on twenty datasets with diversified numbers of features and classes confirm the effectiveness of our Soft-Recoding strategy in promoting the performance of the original ECOC algorithms. Our source code and additional results are available at: ***/MLDMXM2017/ SA-soft-recoding.

关键词： Error-correcting output code Soft-recoding ternary coding Regression Multiclass classification

来源：评论

学校读者我要写书评

暂无评论

Research on Federated Learning for Non‐IID Data

International Core Journal of Engineering

引用

International Core Journal of Engineering 2023年第3期9卷 44-52页

作者： Canming Cao Zhengyi Chai

In recent years, federated learning has attracted widespread attention as a technology to solve the problem of data islands, and has begun to be applied in fields such as finance, healthcare, and smart cities. Introduce federated learning from three levels. First introduce the concept of federated learning, and explain the concept of federated learning through the definition, architecture, classification and comparison with traditional distributed learning; then from the perspective of machine learning and deep learning, various current federated learning algorithms are analyzed Classification comparison and in‐depth analysis; finally, in‐depth classification of federated learning optimization algorithms from the perspectives of communication cost, client selection, and aggregation mode optimization, summarizes the research status of federated learning, and puts forward the communication and system differences faced by federated learning. Data heterogeneity and data heterogeneity are the three major problems and solutions, as well as the outlook for the future.

关键词： Communication Efficiency Deep Learning Federated Learning ternary coding

来源：评论

学校读者我要写书评

暂无评论

An efficient weak sharpening detection method for image forensics

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2018年 50卷 93-99页

作者： Ding, Feng Zhu, Guopu Dong, Weiqiang Shi, Yun-Qing New Jersey Inst Technol Dept Elect & Comp Engn Newark NJ 07102 USA Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen 518055 GD Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur Beijing 100093 Peoples R China

In recent years, image sharpening detection has become one of the main topics in the field of image forensics. It is, however, still a challenge to detect the images sharpened with weak sharpening strength. To address this challenge, we propose an efficient method for image sharpening detection. In the proposed method, a ternary coding strategy with adaptive threshold is introduced to reveal the overshoot artifacts caused by weak sharpening. Extensive experiments are conducted to illustrate the superiority of the proposed method. The experimental results show that the proposed method can achieve a considerable improvement in sharpening detection, especially for slightly sharpened images.

关键词： Image forensics Sharpening detection Overshoot artifact Edge perpendicular binary coding ternary coding

来源：评论

学校读者我要写书评

暂无评论

High Efficiency Modulation Scheme with ternary coding for Satellite Transmissions

High Efficiency Modulation Scheme with Ternary Coding for Sa...

引用

2nd International Conference on Computer Science and Network Technology (ICCSNT)

作者： Wang Haotong Liu Xiguo Liu Min Zhao Zhiyong Naval Aeronaut & Astronaut Univ Dept Elect & Informat Engn Yantai Peoples R China

ISBN: (纸本)9781467329644;9781467329637

For high bandwidth efficiency and better performance of the satellite communication, a novel modulation and demodulation scheme named ternary Coded Pulse Shape Modulation (TC-PSM) is proposed. By analyzing the character of high band satellite channels and the features of existing modulation schemes, TC-PSM scheme is presented. The performance of the TC-PSM scheme is analyzed theoretically and the simulation result is presented. The analysis shows that the proposed method can increase the date rate to bandwidth ratio with a little grow of the cost of the signal to noise ratio and the normalized PAPR is lower than that of NOTDM. The proposed method is suitable for the satellite communication system.

关键词： modulation bandwidth efficiency satellite transmission PAPR ternary coding

来源：评论

学校读者我要写书评

暂无评论

Modeling Sustainability Reporting with ternary Attractor Neural Networks 6th

Modeling Sustainability Reporting with Ternary Attractor Neu...

引用

6th International Conference on Mining Intelligence and Knowledge Exploration (MIKE)

作者： Gonzalez, Mario Dominguez, David Pantoja, Odette Guerrero, Carlos Rodriguez, Francisco B. Univ Amer SI2 Lab Quito Ecuador Univ Autonoma Madrid Dept Ingn Informat Escuela Politecn Super Grp Neurocomp Biol Madrid 28049 Spain Escuela Politec Nacl FCA Quito Ecuador

ISBN: (纸本)9783030059187;9783030059170

This work models the Corporate Sustainability General Reporting Initiative (GRI) using a ternary attractor network. A dataset of 15 years evolution of the GRI reports for a world-wide set of companies was compiled from a recent work and adapted to match the pattern coding for a ternary attractor network. We compare the performance of the network with a classical binary attractor network. Two types of criteria were used for encoding the ternary network, i.e., a simple and weighted threshold, and the performance retrieval was better for the latter, highlighting the importance of the real patterns' transformation to the three-state coding. The network exceeds the retrieval performance of the binary network for the chosen correlated patterns (GRI). Finally, the ternary network was proved to be robust to retrieve the GRI patterns with initial noise.

关键词： Sustainability ternary coding Bi-linear and Bi-quadratic retrieval

来源：评论

学校读者我要写书评

暂无评论

Fault Reconfiguration of Shipboard Power System Based on Triple Quantum Differential Evolution Algorithm

引用

Journal of Shanghai Jiaotong university(Science) 2016年第4期21卷 433-442页

作者：王丛佼王锡淮肖健梅陈晶张思全 Department of Electrical Engineering Logistic Engineering CollegeShanghai Maritime University

Fault reconfiguration of shipboard power system is viewed as a typical nonlinear and multi-objective combinatorial optimization problem. A comprehensive reconfiguration model is presented in this paper, in which the restored loads, switch frequency and generator efficiency are taken into account. In this model, analytic hierarchy process(AHP) is proposed to determine the coefficients of these objective functions. Meanwhile, a quantum differential evolution algorithm with triple quantum bit code is proposed. This algorithm aiming at the characteristics of shipboard power system is different from the normal quantum bit representation. The individual polymorphic expression is realized, and the convergence performance can be further enhanced in combination with the global parallel search capacity of differential evolution algorithm and the superposition properties of quantum theory. The local optimum can be avoided by dynamic rotation gate. The validity of algorithm and model is verified by the simulation examples.

关键词： quantum differential evolution algorithm ternary coding dynamic rotation gate shipboard power system fault reconfiguration

来源：评论

学校读者我要写书评

暂无评论

Self-Timed Multiplier for Multiply-Add Unit

Self-Timed Multiplier for Multiply-Add Unit

引用

IEEE North-West-Russia-Section Young Researchers in Electrical and Electronic Engineering Conference (ElConRusNW)

作者： Stepanov, B. Diachenko, Y. Rogdestvenski, Y. Diachenko, D. Russian Acad Sci Inst Informat Problems Fed Res Ctr Comp Sci & Control IIP RAS Moscow Russia

ISBN: (纸本)9781509004454

Paper discusses the peculiarities of self-timed multiplier implementation for unit multiplying two operands and then adding the product to third operand without an intermediate rounding according to the IEEE 754 Standard. The multiplier is a hardware implementation of modified Booth algorithm on a base of self-timed adder with redundant signal code. An optimal self-timed redundant coding of internal and output signals in the multiplier was proposed. The circuitry and layout problems were solved for self-timed multiplier implementation. Wallace tree structure, which is the main part of the multiplier, was optimized for the facilities of 65-nm CMOS process with six metal layers taking into account more number of signals in the multiplier circuit, than in the synchronous analog. A release of the self-timed multiplier implementation in CMOS process with 65-nm design rules is introduced.

关键词： Booth algorithm self-timed multiplier ternary coding ternary Wallace tree layout

来源：评论

学校读者我要写书评

暂无评论

Texture Representation via Joint Statistics of Local Quantized Patterns

引用

IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS 2014年第1期E97D卷 155-159页

作者： Song, Tiecheng Xu, Linfeng Huang, Chao Luo, Bing Univ Elect Sci & Technol China Sch Elect Engn Chengdu 611731 Peoples R China

In this paper, a simple yet efficient texture representation is proposed for texture classification by exploring the joint statistics of local quantized patterns (jsLQP). In order to combine information of different domains, the Gaussian derivative filters are first employed to obtain the multi-scale gradient responses. Then, three feature maps are generated by encoding the local quantized binary and ternary patterns in the image space and the gradient space. Finally, these feature maps are hybridly encoded, and their joint histogram is used as the final texture representation. Extensive experiments demonstrate that the proposed method outperforms state-of-the-art LBP based and even learning based methods for texture classification.

关键词： texture classification Local Binary Patterns (LBP) Gaussian derivative filter ternary coding

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：