检索结果-内蒙古大学图书馆

Enhanced chaos-based image compression-encryption algorithm utilizing 2D compressive sensing and genetic algorithm optimization

引用

Multimedia Tools and Applications 2024年 1-38页

作者： Nanfak, Arnaud de Dieu Nkapkop, Jean Mvogo Ngono, Joseph Tabekoueng Njitacke, Zeric Lessouga Etoundi, Christophe Magloire Effa, Joseph Yves Laboratory of Electronic Electrical Engineering Automation and Telecommunication National Higher Polytechnic School of Douala University of Douala PO Box 2701 Douala Cameroon Technology and Applied Sciences Laboratory University Institute of Technology University of Douala P.O. Box 8698 Douala Cameroon Applied Computing Laboratory Faculty of Science University of Douala P.O. Box 2701 Douala Cameroon University of Buea P.O. Box 63 Buea Cameroon Department of Physics Faculty of Science University of Ngaoundere P.O. Box 454 Ngaoundere Cameroon

This paper introduces an innovative image compression and encryption algorithm that leverages the genetic algorithm (GA), compressive sensing (CS), and a newly developed hyperchaotic map. In this algorithm, the GA is employed to optimize the compression parameters, including those related to generating the measurement matrix and performing thresholding operation. The optimization objective is centred around on the Peak-Signal-to-Noise-Ratio (PSNR) of the reconstructed image. The encryption part involves employing the Arnold transform and byte-wise XOR operator for confusion and diffusion, respectively. The generation of the measurement matrix and chaotic sequences for encryption is facilitated by a novel two-dimensional fractional-Sine–Cosine (2DFSC) hyperchaotic map introduced in this research. Simulation outcomes demonstrate dynamic parameter values adjustments through optimization, resulting in improved decompression efficiency across different compression rates and image types. Assessment of security and decompression performance confirms the effectiveness of the proposed algorithm, showing a good compression effect, a good reconstruction efficacity even for low compression ratio, good speed and high security compared to some recent similar systems. This work may therefore be suitable to compress and secure data in wireless body area network applications, including those related to the internet of medical things. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Towards Open-Set Document Layout Segmentation Through Class-Specific Prototype Learning

SSRN

引用

SSRN 2023年

作者： Sang, Yuman Yu, Shenbao Zeng, Yifeng Pan, Yinghui Yao, Zhangrui Department of Automation Xiamen University Xiamen China Department of Computer and Information Sciences Northumbria University Newcastle upon Tyne United Kingdom National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Open-set segmentation is an emerging and challenging topic, especially when it is combined with domain-specific tasks. Beyond recognizing known classes, the system needs to reject the unknowns. In this paper, we study the open-set document layout segmentation problem and propose a two-phase framework (OpenDLS) that accurately recognizes pixels in document images from known classes and rejects those from the unknowns. In the first phase, we propose a class-specific prototype learning strategy and design two loss functions for model training. In addition, considering the multifarious appearance of objects, a multi-scale feature fusion module is developed. In the second phase, we propose three rejection rules to detect the pixels that belong to unknown classes. To the best of our knowledge, this is the first work to investigate the open-set document layout segmentation task. Extensive experiments demonstrate the effectiveness of our framework in both known class classification and unknown class identification. © 2023, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

SoftGPT: Learn Goal-Oriented Soft Object Manipulation Skills by Generative Pre-Trained Heterogeneous Graph Transformer

SoftGPT: Learn Goal-Oriented Soft Object Manipulation Skills...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Junjia Liu Zhihao Li Wanyu Lin Sylvain Calinon Kay Chen Tan Fei Chen Department of Mechanical and Automation Engineering T-Stone Robotics Institute The Chinese University of Hong Kong Hong Kong SAR Department of Computing The Hong Kong Polytechnic University Hong Kong SAR Idiap Research Institute Martigny Switzerland

Soft object manipulation tasks in domestic scenes pose a significant challenge for existing robotic skill learning techniques due to their complex dynamics and variable shape characteristics. Since learning new manipulation skills from human demonstration is an effective way for robot applications, developing prior knowledge of the representation and dynamics of soft objects is necessary. In this regard, we propose a pretrained soft object manipulation skill learning model, namely SoftGPT, that is trained using large amounts of exploration data, consisting of a three-dimensional heterogeneous graph representation and a GPT-based dynamics model. For each downstream task, a goal-oriented policy agent is trained to predict the subsequent actions, and SoftGPT generates the consequences of these actions. Integrating these two approaches establishes a thinking process in the robot's mind that provides rollout for facilitating policy learning. Our results demonstrate that leveraging prior knowledge through this thinking process can efficiently learn various soft object manipulation skills, with the potential for direct learning from human demonstrations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A federated learning attack method based on edge collaboration via cloud

A federated learning attack method based on edge collaborati...

引用

作者： Yang, Jie Baker, Thar Gill, Sukhpal Singh Yang, Xiaochuan Han, Weifeng Li, Yuanzhang School of Cyberspace Science and Technology Beijing Institute of Technology Beijing China Department of Computer Science College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom School of Computer Science Beijing Institute of Technology Beijing China School of Mechanical Manufacturing and Automation Engineer of China Railway Tunnel Bureau Group Co. Ltd Henan Zhengzhou China

Federated learning (FL) is widely used in edge-cloud collaborative training due to its distributed architecture and privacy-preserving properties without sharing local data. FLTrust, the most state-of-the-art FL defense method, is a federated learning defense system with trust guidance. However, we found that FLTrust is not very robust. Therefore, in the edge collaboration scenario, we mainly study the poisoning attack on the FLTrust defense system. Due to the aggregation rule, FLTrust, with trust guidance, the model updates of participants with a significant deviation from the root gradient direction will be eliminated, which makes the poisoning effect on the global model not obvious. To solve this problem, under the premise of not being deleted by the FLTrust aggregation rules, we construct malicious model updates that deviate from the trust gradient to the greatest extent to achieve model poisoning attacks. First, we utilize the rotation of high-dimensional vectors around axes to construct malicious vectors with fixed orientations. Second, the malicious vector is constructed by the gradient inversion method to achieve an efficient and fast attack. Finally, a method of optimizing random noise is used to construct a malicious vector with a fixed direction. Experimental results show that our attack method reduces the model accuracy by 20%, severely undermining the usability of the model. Attacks are also successful hundreds of times faster than the FLTrust adaptive attack method. © 2022 John Wiley & Sons Ltd.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Novel Approach for Passive Mixing in Microfluidics Utilizing Porous PDMS Sponge

Novel Approach for Passive Mixing in Microfluidics Utilizing...

引用

Computer Science (COMSCI), International Scientific Conference on

作者： Emil Grigorov Boris Kirov Jordan A. Denev Vassil Galabov German Engineering Education and Industrial Management Technical University of Sofia Sofia Bulgaria Department Industrial Automation Technical University of Sofia Sofia Bulgaria Steinbuch Centre for Computing Karlsruhe Institute of Technology Karlsruhe Germany

Mixing in microfluidic devices has been always a significant challenge due to the small channel dimensions and the strongly laminar flow character of the fluids. However, mixing is an essential process in various biological, chemical and pharma processes. This paper introduces a new approach to passive mixing in microfluidic devices, utilizing a quick and cheap way with a sugar cube as prototype to produce a) porous medium. The authors present experimental and numerical analyses of the method, showing that the efficiency of mixing decreases as the volume flow rates of the fluids increase for flows studied with Re in the range 0,028-0,26. The largest porous mediumtested achieved a maximum mixing efficiency of 98%, suggesting that larger geometries may yield even higher efficiencies. A decrease in mixing efficiency along the length of the sponge with increasing volume flow rates was also observed (experimentally and numerically), possibly due to increased backflow. Despite the complexity of the Polydimethylsiloxan (PDMS) sponge, numerical analysis indicates a linear relationship between pressure drop and Reynolds number.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IoT-based Wireless Sensor Networks for Monitoring Drinking Water Treatment Plants

IoT-based Wireless Sensor Networks for Monitoring Drinking W...

引用

International Workshop on Secure Internet of Things (SIoT)

作者： Luiz Octávio Martini Lima Lucas Carvalho Goncalves Gustavo Campos Menezes Lucas Silva de Oliveira Gleb Wataghin Institute of Physics UNICAMP Campinas SP Brazil Master Degree Program in Automation and Systems CEFET-MG Leopoldina MG Brazil Department of Electronics and Computing CEFET-MG Contagem MG Brazil Department of Mechatronics Engineering CEFET-MG Divinópolis MG Brazil

ISBN: (数字)9798331507466

ISBN: (纸本)9798331507473

The increasing need for efficient monitoring of parameters in challenging industrial environments, such as basic sanitation, has led to the search for integrated and user-friendly solutions that can address specific challenges of this setting. This project aims to develop a solution to meet monitoring requirements in water treatment plants. The proposed solution involves the development of both hardware and software for collecting data from the water treatment process using sensors and transmitting this information to a server structure, database, and communication interface with the cloud-based user. The effectiveness of the proposed device is being evaluated in six water treatment units located in the states of Alagoas, Mato Grosso, Paraná, Rio de Janeiro, and São Paulo. Preliminary results indicate that the proposed solution is capable of monitoring the variables involved in the water flocculation stage and generating a comprehensive set of information about the process over time.

关键词： Cloud computing Chemical sensors Wireless sensor networks User interfaces Hardware Software Sensors Social Internet of Things Servers Monitoring

来源：评论

学校读者我要写书评

暂无评论

Multi-Label Classification with Label Clusters

Research Square

引用

Research Square 2023年

作者： Gatto, Elaine Cecília Ferrandin, Mauri Cerri, Ricardo Department of Computer Science Federal University of São Carlos SP São Carlos13565-905 Brazil Department of Control Automation and Computing Engineering Federal University of Santa Catarina SC Blumenau89036-002 Brazil

Multi-Label Classification is the task of simultaneously predicting a set of labels for an instance. Typically, two approaches are used: global, which trains a single classifier to deal with all classes at once, and local, which divides the problem into many binary problems. In both approaches, learning label correlations is still an open issue. In this paper, we propose a method to cluster the label space and find partitions of disjoint correlated labels called hybrid partition, which can be considered in-between the local and global, combining the benefits of both. Our proposal entails: i) clustering the label space based on label correlations;ii) generating and validating the resulting hybrid partitions;iii) selecting the optimal partitions between them;and iv) evaluating their performances. Since we are also interested in analyzing how hybrid partitions are close to the best possible partitions, we compared our results with the ones obtained using partitions found by an oracle, an exhaustive, and a random search. The oracle and exhaustive strategies generate all possible label partitions for a dataset. While the oracle chooses the best one based on the test set alone, the exhaustive choices are based on validation. Experiments on eight well-known multi-label datasets revealed that both our proposal and the random partitions achieve superior or competitive results compared with the others. This indicates that the conventional global and local approaches may not accurately account for label correlations, requiring significant improvements. In this case, clustering the label space can be a solution. © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

LXL: LiDAR Excluded Lean 3D Object Detection with 4D Imaging Radar and Camera Fusion

LXL: LiDAR Excluded Lean 3D Object Detection with 4D Imaging...

引用

IEEE Symposium on Intelligent Vehicle

作者： Weiyi Xiong Jianan Liu Tao Huang Qing-Long Han Yuxuan Xia Bing Zhu School of Automation Science and Electrical Engineering Beihang University Beijing P.R. China Vitalent Consulting Gothenburg Sweden College of Science and Engineering James Cook University Cairns QLD Australia School of Science Computing and Engineering Technologies Swinburne University of Technology Melbourne VIC Australia Department of Electrical Engineering Chalmers University of Technology Gothenburg Sweden

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

As an emerging technology and a relatively affordable device, the 4D imaging radar has already been confirmed effective in performing 3D object detection in autonomous driving [1] . Nevertheless, the sparsity and noisiness of 4D radar point clouds hinder further performance improvement, and in-depth studies about its fusion with other modalities are lacking. On the other hand, as a new image view transformation strategy, sampling has been applied in a few image-based detectors and shown to outperform the widely applied depth-based splatting proposed in Lift-Splat-Shoot (LSS) [2] , even without image depth prediction [3] . However, the potential of sampling is not fully unleashed. As a result, this paper investigates the sampling strategy on the camera and 4D imaging radar fusion-based 3D object detection. In the proposed LiDAR Excluded Lean (LXL) model, predicted image depth distribution maps and radar 3D occupancy grids are generated from image perspective view (PV) features and radar bird’s eye view (BEV) features, respectively. They are sent to the core of LXL, called radar occupancy-assisted depth-based sampling , to aid image view transformation.

关键词： Performance evaluation Point cloud compression Solid modeling Three-dimensional displays Laser radar Radar detection Object detection

来源：评论

学校读者我要写书评

暂无评论

Complex Permeability Determination for EE Core Based on Flexible PCB Fixture and Magnetic Flux Path Length Analysis

Complex Permeability Determination for EE Core Based on Flex...

引用

China Power Supply Society Electromagnetic Compatibility Conference (CPEMC)

作者： Huamin Jie Zhenyu Zhao Yongqi Chang Changdong Wang Shiqi Jiang Richard Xian-Ke Gao Kye Yak See School of Electrical and Electronic Engineering Nanyang Technological University Singapore Singapore Department of Electrical and Computer Engineering National Univeristy of Singapore Singapore Singapore Department of Control Science and Engineering Harbin Institute of Technology Harbin China School of Electronics and Information Engineering Harbin Institute of Technology Harbin China School of Electrical Engineering and Automation Harbin Institute of Technology Harbin China A*STAR Institute of High Performance Computing Singapore Singapore

ISBN: (数字)9798331509552

ISBN: (纸本)9798331509569

The complex permeability of magnetic cores acts as a vital factor in electromagnetic interference (EMI) filtering choke design and optimization. Many efforts have been reported for toroid cores, but fewer target those with other shapes, such as EE, EI, UU, and UI cores. Owing to their commonly used in planar EMI filters, determining the complex permeability of them is of significance. Targeting EE cores, this paper presents a flexible printed circuit board (PCB)-based fixture adapter tailored designed for performing the measurement, while the corresponding core permeability can be calculated through magnetic flux path length analysis. The experiments validate the effectiveness and accuracy of the proposed methods, spanning a wide frequency range up to 120 MHz.

关键词： Magnetic flux Accuracy Flexible printed circuits Magnetic cores Fixtures Electromagnetic interference Permeability measurement Length measurement Permeability Inductors

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient and Latency-Aware Task Offloading for Industrial Cloud-Edge Systems with Heterogeneous CPUs and GPUs

引用

IEEE Internet of Things Journal 2025年

作者： Zhai, Jiahui Bi, Jing Yuan, Haitao Zhang, Jia Buyya, Rajkumar Beijing University of Technology College of Computer Science Beijing100124 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China Southern Methodist University Department of Computer Science DallasTX75206 United States Lab School of Computing and Information Systems MelbourneVIC3010 Australia

The unprecedented prosperity of the Industrial Internet of Things has significantly driven the transition from traditional manufacturing to intelligent one. In industrial environments, resource-constrained industrial equipments (IEs) often fail to meet the diverse demands of numerous compute-intensive and latency-sensitive tasks. Mobile edge computing has emerged as an innovative paradigm to reduce latency and energy consumption for IEs. However, the increasing number of IEs in industrial settings relies on heterogeneous platforms integrated with different processing units, i.e., CPUs and GPUs. To address this challenge, we propose a software-defined networking-based equipment-edge-cloud architecture with three-stage heterogeneous computing. This architecture accurately models the multi-task processing of both scientific and concurrent workflows in real industrial environments. We formulate a joint optimization problem to simultaneously minimize task completion time and energy consumption for IEs. To solve this problem, we design an Improved Two-stage Multi-Objective Evolutionary Algorithm (IT-MOEA). IT-MOEA employs a novel multi-objective grey wolf optimizer based on manta ray foraging and associative learning to accelerate convergence in the early evolution stages and adopts a diversity-enhancing immune algorithm to enhance diversity in the later stages. Simulation results with various benchmarks demonstrate that IT-MOEA outperforms several state-of-the-art single-objective optimization algorithms by an average of 24.7% and multi-objective algorithms by 41.0% in terms of delay and energy consumption. © 2025 IEEE.

关键词： Mobile edge computing

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：