检索结果-内蒙古大学图书馆

Supervised deep learning for content-aware image retargeting with Fourier Convolutions

Multimedia Tools and Applications 2024年第36期83卷 83611-83627页

作者： Givkashi, MohammadHossein Naderi, MohammadReza Karimi, Nader Shirani, Shahram Samavi, Shadrokh Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan84156-83111 Iran Department of Electrical and Computer Engineering McMaster University HamiltonONL8S 4L8 Canada Computer Science Department Seattle University SeattleWA98122 United States

Image retargeting aims to alter the size of the image with attention to the contents. One of the main obstacles to training deep learning models for image retargeting is the need for a vast labeled dataset. Labeled datasets are unavailable for training deep learning models in the image retargeting tasks. As a result, we present a new supervised approach for training deep learning models. We use the original images as ground truth and create inputs for the model by resizing and cropping the original images. A second challenge is generating different image sizes in inference time. However, normal convolutional neural networks cannot generate images of different sizes than the input image. To address this issue, we introduced a new method for supervised learning. In our approach, a mask is generated to show the desired size and location of the object. Then the mask and the input image are fed to the network. Comparing image retargeting methods and our proposed method demonstrates the model’s ability to produce high-quality retargeted images. Afterward, we compute the image quality assessment score for each output image based on different techniques and illustrate the effectiveness of our approach. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Leveraging machine learning and blockchain in E-commerce and beyond: benefits, models, and application

引用

Discover Artificial Intelligence 2023年第1期3卷 3页

作者： Jebamikyous, Hrag Li, Menglu Suhas, Yoga Kashef, Rasha Electrical Computer and Biomedical Engineering Department Toronto Metropolitan University Toronto Canada

Blockchain technology (BT) allows market participants to keep track of digital transactions without central recordkeeping. The features of blockchain, including decentralization, persistency, and attack resistance, allow data security and privacy. Machine learning (ML) involves the analytical platform on a massive amount of data to provide precise decisions. Since data reliability, integration, and data security are crucial in machine learning, the emergence of blockchain technology and machine learning has become a unique, most disruptive, and trending research in the last few years, achieving comparable and precise performance. The combination of blockchain and machine learning (BT–ML) has been applied across different applications to assist decision-makers in retrieving valuable data insights while preserving privacy and integration. This paper summarizes the state-of-the-art research in combing BT and ML in e-commerce and other various applications, including healthcare, smart transportation, and the Internet of Things (IoT). The challenges and benefits of integrating machine learning and blockchain technologies are outlined in the paper. We also discuss the advantages and limitations of current algorithms in the BT–ML integration. This paper provides a roadmap for researchers to pave the way for current and future research directions in combing the BT and ML research areas. © The Author(s) 2023.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Investigation on compressed air energy storage system for efficient utilisation of renewable power sources

引用

International Journal of Power and Energy Conversion 2024年第3期15卷 281-293页

作者： Karthika, J. Annamalai, T. Kumar, P. Veera Sanjeeva Olana, Firew Dereje Rasu, N. Govindha Department of Electrical and Electronics Engineering Sri Krishna College of Engineering and Technology Kuniamuthur Coimbatore641008 India Department of Electrical and Electronics Engineering Sri Venkateswara College of Engineering Tamil Nadu Sriperumbudur602117 India Department of Mechanical Engineering Annamacharya Institute of Technology and Sciences Andhra Pradesh Rajampet516126 India Department of Electrical and Computer Engineering Mattu University Post-318 Mattu Ethiopia School of Mechanical Engineering Vellore Institute of Technology Vellore India

In recent years, emerging nations have shifted their focus to renewable energy sources for electricity production. This shift has happened in both industrialised and underdeveloped countries. The percentage of electricity produced overall in most developed countries that originates from renewable sources of energy is rising significantly. Currently, the grid is going through a number of modifications to improve its intelligence and stability. These adjustments are becoming more pronounced. Although there are many various types of storage systems available, the CAES system is the most appropriate for large-capacity storage that is ideal for grid integration. However, the overall roundtrip efficiency is less than that of a pumped hydro storage system when it comes to large-scale renewable energy storage. © 2024 Inderscience Enterprises Ltd.

关键词： Compressors

来源：评论

学校读者我要写书评

暂无评论

Using of metasurface lens and particle swarm optimisation for enhancement of parameters of a pyramidal horn antenna

引用

Australian Journal of electrical and Electronics engineering 2023年第1期20卷 85-94页

作者： Abdollahi, Nasrin Mohajeri, Farzad School of Electrical and Computer Engineering Shiraz University/Communication Department Shiraz Iran

In this article, a lens is applied to reduce the horn antenna’s Side Lobe Level (SLL) based on controlling the phase and amplitude distribution of the electromagnetic fields over the aperture of the horn antenna in the X band (8−12 GHz) for radar applications. By locating the metasurface lens inside the standard X band pyramidal horn, the SLL is decreased by 4–15 dB in E-plane and 0.8–7 dB in H-plane. The measured results with metasurface lenses demonstrate the reduction of SLL over the entire bandwidth. Good agreement between measurement and simulation results shows the tapering of field distribution over the aperture of the horn antenna. ©, Engineers Australia.

关键词： Horn antennas

来源：评论

学校读者我要写书评

暂无评论

Physics-informed transient stability assessment of microgrids

引用

iEnergy 2023年第3期2卷 231-239页

作者： Priyanka Mishra Peng Zhang Department of Electrical and Computer Engineering Stony Brook UniversityNY 11794USA

With the integration of a voltage source converter(VSC),having variable internal voltages and source impedance,in a microgrid with high resistance to reactance ratio of short lines,angle-based transient stability techniques may find *** such a situation,the Lyapunov function can be a viable option for transient stability assessment(TSA)of such a VSC-interfaced ***,the determination of the Lyapunov function with the classical method is very challenging for a microgrid with converter controller *** overcome such challenges,this paper develops a physics-informed,Lyapunov function-based TSA framework for VSC-interfaced *** method uses the physics involved and the initial and boundary conditions of the system in learning the Lyapunov *** method is tested and validated under faults,droop-coefficient changes,generator outages,and load shedding on a small grid-connected microgrid and the CIGRE microgrid.

关键词： Physics-informed neural network Lyapunov function voltage source converter transient stability assessment microgrid

来源：评论

学校读者我要写书评

暂无评论

Minimum and maximum packets’ delays determination for communication flows’ delays jitters computation

引用

Australian Journal of electrical and Electronics engineering 2023年第1期20卷 27-34页

作者： Eyinagho, Monday Ofori Electrical and Computer Engineering Department Afe Babalola University Ado-Ekiti Nigeria

Delay Jitter is a communication networks’ performance issue which occurs when the delays’ of the packets of a traffic stream that has traversed from a transmitter to a receiver are different. Jitter is measured in terms of the difference between a minimum and a maximum value of delay. A large and unaccounted for, value of delay jitter is a problem for some time sensitive applications, for example, real-time audio/video. Delay Jitter is eliminated in some applications by the delayed-playback approach. But this approach requires that the maximum and minimum packets’ delay of a flow should be known in advance. However, it is challenging to a priori know a flow’s minimum and maximum packets’ delays. In this paper, the derivation of simple, practically applicable formulas that can be used to compute the minimum and maximum packets’ delays of a flow, with a view to accounting for, and mitigating the effects of delays’ jitters is reported. The maximum delay value that is obtained with the formulas is compared with three maximum delay values of models that were reported in the literature. The comparison indicates that the formulas that are reported in this paper are superior in terms of practical reality and applicability. ©, Engineers Australia.

关键词： Jitter

来源：评论

学校读者我要写书评

暂无评论

Efficient Algorithms for Attributed Graph Alignment With Vanishing Edge Correlation

引用

IEEE Transactions on Information Theory 2025年第6期71卷 4556-4580页

作者： Wang, Ziao Wang, Weina Wang, Lele The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada University of Michigan Department of Electrical and Computer Engineering Ann ArborMI48109 United States Carnegie Mellon University Computer Science Department PittsburghPA15213 United States

Graph alignment refers to the task of finding the vertex correspondence between two correlated graphs of n vertices. Extensive study has been done on polynomial time algorithms for the graph alignment problem under the Erdős–Rényi graph pair model, where the two graphs are Erdős–Rényi graphs with edge probability qu , correlated under certain vertex correspondence. To achieve exact recovery of the correspondence, all existing algorithms at least require the edge correlation coefficient ρu between the two graphs to be non-vanishing as n → ∞. Moreover, it is conjectured that no polynomial-time algorithm can achieve exact recovery under vanishing edge correlation ρu u ≥ n−Θ(1). We identify a local tree structure, which incorporates one layer of user information and one layer of attribute information, and apply the subgraph counting technique to such structures. A polynomial-time algorithm is proposed that recovers the vertex correspondence for most of the vertices, and then refines the output to achieve exact recovery. The consideration of attribute information is motivated by real-world applications like LinkedIn and Twitter, where user attributes like birthplace and education background can aid alignment. © 1963-2012 IEEE.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

Vision-based Markerless Robot-to-robot Relative Pose Estimation Using RGB-D Data

引用

Journal of Institute of Control, Robotics and Systems 2023年第6期29卷 495-503页

作者： Kim, Joo-Hyun Kim, Kwang-Ki Department of Electrical and Computer Engineering Inha University Incheon22212 Korea Republic of

In this paper, a vision-based robot-to-robot relative pose estimation method is proposed for markerless wheeled mobile robots using an RGB-D camera. The proposed method comprises three parts: (i) object detection using a machine vision technique with RGB data, (ii) relative position estimation averaging over the point cloud with outlier rejection, and (iii) relative orientation estimation using point cloud scan matching through iterative closest point (ICP) methods. The neighboring or target robots are detected using YOLOv3-tiny so that the position of the robot can be determined in pixel coordinates. To estimate the 3D position of the target robot in the camera coordinates of the ego-robot, the object detection results are used along with the depth information and the precalibrated pinhole camera model. To estimate the orientation of the target robot, a point cloud is generated using the depth image, downsampled, and then used for scan matching by using ICP methods. For experimental verification, the proposed relative pose estimation method was implemented as a robot operating system package and tested on a small-scale differential-driving wheeled mobile robot, TurtleBot3;the estimation results were compared with the ground truth in real-world environments. © ICROS 2023.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Direct-Write Shielded Cables for Improved Signal Integrity

IEEE Journal on Flexible Electronics

引用

IEEE Journal on Flexible Electronics 2023年第6期2卷 481-485页

作者： Klein-Hitpass, Achim Kidmose, Preben Agarwala, Shweta Aarhus University Department of Electrical and Computer Engineering Aarhus8200 Denmark

Direct-writing techniques of printed electronics (PEs) have great potential within flexible electronics and allow to fabricate circuits on double curved surfaces. In sensor applications, it is often necessary to protect the electrical connections between the sensor and the electrical instrumentation against electromagnetic interference (EMI). This is commonly achieved by shielding the interconnects. In this work, we focused on fabrication of a shielded cable structure for low-frequency signal integrity in high-precision sensor applications. Semiprinted samples, with only some of the layers printed were measured to have an average signal layer resistivity of 3.93m and an insulation resistivity of 5.25 Gm. Fully printed (FP) samples had an average signal layer resistivity of 6.72m and an insulation resistivity of 14.7 Gm. The printed samples demonstrated shielding effectiveness (SE) of -69 dB down to -86 dB. Based on signal-shield capacitance ranging from 85 to 467 pF, the -3 dB cut-off frequency of the signal transfer function ranged from 0.5 to 2.6 kHz. In summary, we demonstrate for the first time a printed coaxial-cable-like structure for lowfrequencies between 1 Hz and 10 kHz. © 2022 IEEE.

关键词： 3D printing

来源：评论

学校读者我要写书评

暂无评论

Body Area Network: Connecting and powering things together around the human body

引用

IEEE Solid-State Circuits Magazine 2023年第2期15卷 49-58页

作者： Yoo, Jerald National University of Singapore Department of Electrical and Computer Engineering Singapore117583 Singapore

A body area network (BAN) provides connectivity and power among on-body/in-body sensors and is an attractive means for realizing the 'human intranet' for health-care, medical, or multimedia applications around the human body [1], [2]. As shown in Figure 1, compared to a WLAN or a wireless personal area network (WPAN), it targets a much smaller range (∼2 m) with greater energy efficiency. © 2009-2012 IEEE.

关键词： Intranets

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：