检索结果-内蒙古大学图书馆

IEEE Open Journal of Vehicular technology 2021年 2卷 17-44页

作者： Nguyen, Duc Minh Kishk, Mustafa A. Alouini, Mohamed-Slim Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia

With the increasing demand for greener and more energy efficient transportation solutions, electric vehicles (EVs) have emerged to be the future of transportation across the globe. However, currently, one of the biggest bottlenecks of EVs is the battery. Small batteries limit the EVs driving range, while big batteries are expensive and not environmentally friendly. One potential solution to this challenge is the deployment of charging roads, i.e., dynamic wireless charging systems installed under the roads that enable EVs to be charged while driving. In this paper, we use tools from stochastic geometry to establish a framework that enables evaluating the performance of charging roads deployment in metropolitan cities. We first present the course of actions that a driver should take when driving from a random source to a random destination in order to maximize dynamic charging during the trip. Next, we analyze the distribution of the distance to the nearest charging road. This distribution is vital for studying multiple performance metrics such as the trip efficiency, which we define as the fraction of the total trip spent on charging roads. Next, we derive the probability that a given trip passes through at least one charging road. The derived probability distributions can be used to assist urban planners and policy makers in designing the deployment plans of dynamic wireless charging systems. In addition, they can also be used by drivers and automobile manufacturers in choosing the best driving routes given the road conditions and level of energy of EV battery. © 2020 IEEE.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Advancing ECT Imaging: Residual UNet Deep Neural Network Approach 1st

Advancing ECT Imaging: Residual UNet Deep Neural Network App...

引用

1st International Conference on Intelligent Systems, Blockchain, and Communication Technologies, ISBCom 2024

作者： Deabes, Wael Khalifa, Fahmi Abdel-Hakim, Alaa E. Bouazza, Kheir Eddine Computational Engineering Mathematical Sciences Department Texas A&M University SA San AntonioTX78224 United States Electrical and Computer Engineering Department Morgan State University BaltimoreMD21251 United States Computer Science Department in Jamoum Umm Al-Qura University Makkah Saudi Arabia Computer and Information Science Division Higher Colleges of Technology Abu Dhabi United Arab Emirates

ISBN: (纸本)9783031823763

Recently, there has been significant progress in Electrical Capacitance Tomography (ECT) image reconstruction, yet there remains room for enhancing both speed and quality in these reconstructions. Deep Learning (DL) offers a promising avenue due to its capacity to handle intricate nonlinear functions. This study introduces DL-based ECT image reconstruction model based on Residual UNet and termed as ECT_ResUNet. A sizable dataset containing permittivity distribution and corresponding capacitance measurements was created to train and evaluate the proposed model. The ECT_ResUNet processes modulated capacitance vectors, representing them as 66×66 images. The model’s effectiveness and practicality were assessed using unseen samples, demonstrating precise image reconstruction with an average Image Error (IE) of 0.0918 and Correlation Coefficient (CC) of 0.9527. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Efficient Lane Detection based on Feature Aggregation for Advanced Driver Assistance Systems

Efficient Lane Detection based on Feature Aggregation for Ad...

引用

2023 International Conference on Advanced Robotics and Intelligent Systems, ARIS 2023

作者： Jhong, Sin-Ye Ko, Ching-Hsiang Su, Yi-Feng Hua, Kai-Lung Chen, Yung-Yao National Cheng Kung University Dept. of Engineering Science Tainan Taiwan National Taiwan University of Science and Technology Dept. of Electronic and Computer Engineering Taipei Taiwan Automotive Research and Testing Center Research and Development Division Changhua Taiwan National Taiwan University of Science and Technology Dept. of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350302714

As we enter the era of smart cars and electric vehicles, the significance of autonomous driving systems, especially crucial components like lane detection technology, increases dramatically. However, advanced solutions often face daunting challenges, especially under adverse environmental and lighting conditions, yielding varying detection results. This variability prompts automakers to enforce numerous restrictions on auxiliary functions, often deterring potential customers from upgrading relevant services. This study addresses these limitations and introduces a sophisticated deep learning-based lane detection model to supersede existing technologies. The model fuses an efficient feature extraction network with a Recurrent Feature-Shift Aggregator (RESA) and a Bilateral Up-Sampling Decoder (BUSD). These elements work harmoniously, enabling enhanced global information extraction and fortifying detection capability under challenging conditions. The methodology of this study is segregated into three parts: Efficient Backbone and Neck for feature extraction, Global Feature Enhancement Decoder for maximizing feature map details, and the actual implementation of a Lane Assist System. These modules collectively help us calculate high-accuracy lane coordinates, thereby overcoming the limitations of previous lane detection methods. Following the successful creation and validation of the model, the study extends the implementation to the Hexagon vehicle control platform, where the Lane Departure and Lane Keeping assistance systems are deployed. The proposed technology is validated through rigorous experiments and analyses, utilizing the highly recognized TuSimple dataset, custom-collected Taiwanese scene data, and actual road tests. Results illustrate high and consistent detection performance under diverse environmental conditions, validating the technology's effectiveness and feasibility. © 2023 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

VAE-KRnet and its Applications to Variational Bayes

引用

Communications in Computational Physics 2022年第4期31卷 1049-1082页

作者： Xiaoliang Wan Shuangqing Wei Department of Mathematics Center for Computation and TechnologyLouisiana State UniversityBaton Rouge 70803USA Division of Electrical&Computer Engineering Louisiana State UniversityBaton Rouge 70803USA

In this work,we have proposed a generative model,called VAE-KRnet,for density estimation or approximation,which combines the canonical variational autoencoder(VAE)with our recently developed flow-based generativemodel,called *** is used as a dimension reduction technique to capture the latent space,and KRnet is used to model the distribution of the latent *** a linear model between the data and the latent variable,we show that VAE-KRnet can be more effective and robust than the canonical ***-KRnet can be used as a density model to approximate either data distribution or an arbitrary probability density function(PDF)known up to a ***-KRnet is flexible in terms of *** the number of dimensions is relatively small,KRnet can effectively approximate the distribution in terms of the original random *** high-dimensional cases,we may use VAE-KRnet to incorporate dimension *** important application of VAE-KRnet is the variational Bayes for the approximation of the posterior *** variational Bayes approaches are usually based on the minimization of the Kullback-Leibler(KL)divergence between the model and the *** highdimensional distributions,it is very challenging to construct an accurate densitymodel due to the curse of dimensionality,where extra assumptions are often introduced for *** instance,the classical mean-field approach assumes mutual independence between dimensions,which often yields an underestimated variance due to *** alleviate this issue,we include into the loss the maximization of the mutual information between the latent random variable and the original random variable,which helps keep more information from the region of low density such that the estimation of variance is *** experiments have been presented to demonstrate the effectiveness of our model.

关键词： Deep learning variational Bayes uncertainty quantification Bayesian inverse problems generative modeling

来源：评论

学校读者我要写书评

暂无评论

Piezoelectric Transformer using bulk PZT & Fused Quartz for RF Ion Accelerators

Piezoelectric Transformer using bulk PZT & Fused Quartz for ...

引用

2023 IEEE International Ultrasonics Symposium, IUS 2023

作者： Garud, Meera Hou, Yuetao Ji, Qing Schenkel, Thomas Afridi, Khurram Khan Lal, Amit Cornell University Electrical and Computer Engineering IthacaNY United States Lawrence Berkeley National Laboratory Accelerator Technology and Applied Physics Division BerkeleyCA United States

ISBN: (纸本)9798350346459

In order to miniaturize ion accelerators for MeV-class ions suitable for fusion or ion implantation, high RF voltages of 1-5 kV at RF frequencies of 10-15 MHz are required. In this paper, we present a piezoelectric transformer (PT) design that can be integrated into PCBs that can be assembled into ion accelerator assemblies. The PT designs utilize vibrational mode shapes and multilayer piezoelectric plate stacking, with the secondary side plates further segmented, connected in series to develop higher voltages into a capacitive load of the ion to fabricate the transformers, making them compatible with PCB accelerators. PZT-841 plates were used as piezoelectric material, and a high-Q fused quartz plates served as an electrical insulator while mechanically coupling mechanical motion between the primary and secondary PZT plates. An open-circuit voltage gain of 5.2 at 7.9 MHz was achieved from a prototype with a planar form factor of 0.9 mm and an area of 6x5 mm2 © 2023 IEEE.

关键词： Ions

来源：评论

学校读者我要写书评

暂无评论

Inscribing or Circumscribing a Histogon to a Convex Polygon 42

Inscribing or Circumscribing a Histogon to a Convex Polygon

引用

42nd IARCS Annual Conference on Foundations of Software technology and Theoretical computer Science, FSTTCS 2022

作者： Chung, Jaehoon Bae, Sang Won Shin, Chan-Su Yoon, Sang Duk Ahn, Hee-Kap Department of Computer Science and Engineering Pohang University of Science and Technology Korea Republic of Division of Computer Science and Engineering Kyonggi University Suwon Korea Republic of Division of Computer Engineering Hankuk University of Foreign Studies Seoul Korea Republic of Department of Service and Design Engineering SungShin Women's University Seoul Korea Republic of Graduate School of Artificial Intelligence Department of Computer Science and Engineering Pohang University of Science and Technology Korea Republic of

ISBN: (纸本)9783959772617

We consider two optimization problems of approximating a convex polygon, one by a largest inscribed histogon and the other by a smallest circumscribed histogon. An axis-aligned histogon is an axis-aligned rectilinear polygon such that every horizontal edge has an integer length. A histogon of orientation θ is a copy of an axis-aligned histogon rotated by θ in counterclockwise direction. The goal is to find a largest inscribed histogon and a smallest circumscribed histogon over all orientations in [0, π). Depending on whether the horizontal width of a histogon is predetermined or not, we consider several different versions of the problem and present exact algorithms. These optimization problems belong to shape analysis, classification, and simplification, and they have applications in various cost-optimization problems. © Jaehoon Chung, Sang Won Bae, Chan-Su Shin, Sang Duk Yoon, and Hee-Kap Ahn;licensed under Creative Commons License CC-BY 4.0.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Classification of Cotton Fabric, Pineapple Fabric and Cotton Pineapple Blend Fabric with VGG16 using Keras 15

Classification of Cotton Fabric, Pineapple Fabric and Cotton...

引用

15th IEEE International Conference on Humanoid, Nanotechnology, Information technology, Communication and Control, Environment, and Management, HNICEM 2023

作者： Villaverde, Jocelyn F. Ferrer, Marlou D. MacAbeo, Julia Alexandra T. Masilungan-Manuel, Joanna Tess Mapua University Department of Electrical Electronics and Computer Engineering Manila Philippines Philippine Textile Research Institute Research and Development Division Department of Science and Technology Taguig City Philippines

ISBN: (纸本)9798350381177

Plant leaves represent valuable raw materials for fabric production, offering an eco-friendly alternative to traditional textiles. Converting these leaves into fibers opens opportunities for versatile textile applications. Traditionally, fabric classification relied heavily on manual, time-consuming microscopic analysis of fiber composition and texture, imposing limitations on efficiency and scalability. To address this challenge, the researchers developed a robust computer Vision System on Raspberry Pi, capable of accurately classifying cotton, pineapple, and pineapple-cotton fabrics. Leveraging the powerful machine learning libraries, Tensorflow and Keras, the researchers utilized the VGG16 model, training and fine-tuning it for specialized fabric classification tasks. Notably, the VGG16 model came pretrained with weights from the ImageNet dataset, further enhancing its performance. The dataset comprised 300 images, with equal representation from cotton, pineapple, and cotton-pineapple blend fabrics. These images underwent comprehensive image pre-preprocessing, utilizing techniques such as flipping, adjusting brightness and contrast, and color augmentation. The results of this study are highly promising, with the system achieving an impressive overall accuracy rate of 91.11%. This research not only showcases the system's proficiency in fabric classification but also highlights its potential for practical applications in real-world fabric classification scenarios. © 2023 IEEE.

关键词： Cotton

来源：评论

学校读者我要写书评

暂无评论

Development of Healthcare Monitoring System with Pollution Control in Industrial Sectors Using the Internet of Things 5

Development of Healthcare Monitoring System with Pollution C...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Rajeswari, N Raja Arunkumar, G. Vadivu, M Senthil Gupta, Manish Sethuraman, R. Rajkumar, M. Saveetha Engineering College Department of Mechanical Engineering Tamil Nadu Chennai India Madanapalle Institute of Technology and Science Department of Computer Science and Engineering Andhra Pradesh Madanapalle India Sona College of Technology Department of Electronics and Communication Engineering Tamil Nadu Salem India Lovely Professional University Division of Research and Development Punjab Phagwara India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India School of Information Technology & Engineering Vellore Institute of Technology Vit University Department of Smart Computing Tamil Nadu Vellore India

ISBN: (纸本)9798350321425

Rapid improvement in industrialization and urbanization leads to various impacts on environmental conditions. This leads to a rise in pollution that causes various constraints on human health. Earlier prediction and maintenance of pollution is the solution to obtain a greener ecosystem. This is done through machine learning techniques adopting the Internet of Things. The Internet of Things helps to obtain a smarter environment through real-time monitoring with the control system. Thus machine learning helps to analyze the amount of toxic substances that are emitted from the industries and recorded periodically. They are represented as online controlling and monitoring systems. The sensors and actuators with control devices are used to record the external environmental conditions. The prior intimation of the healthcare is monitored appropriately and intimated to solve earlier. The classification and detection of infections and diseases are done through image processing techniques. Thus the proposed system helps to obtain automatic detection of healthcare and pollution detection systems through machine learning with computational systems. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on Small Satellites: Services and Applications 1

引用

International Conference on Small Satellites , ICSS 2022

作者： Kumar, Rajeev Popli, Renu Chauhan, Ruby Kansal, Isha Garg, Atul Rani, Poonam Singh, Daljeet Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India Department of Computer Engineering National Institute of Technology Kurukshetra Haryana Kurukshetra India University Institute of Engineering and Technology Kurukshetra University Kurukshetra India Centre for Space Research Division of Research and Development Lovely Professional University Punjab Phagwara India

ISBN: (数字)9789811976988

ISBN: (纸本)9789811976971

Paradigm shift of large satellite to small satellite can be seen in last few decades due to highly increase in applications of small satellites. Due to the revolutionary growth in the technology and availability of Commercial Off the Shelf (COTS) product, it is possible to produce very small but powerful hardware components which are capable of surviving in the dynamic conditions of outer space. However, this is quite challenging task to deploy these small satellites in the harsh space environment. This paper presents various issues and challenges involved in the operation of small satellites and categorization of satellites based on applications is provided. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Nanosatellites

来源：评论

学校读者我要写书评

暂无评论

Be Careful With Writing Perturbations: This Could Be a Trigger of Textual Backdoor Attacks 9

Be Careful With Writing Perturbations: This Could Be a Trigg...

引用

9th IEEE Smart World Congress, SWC 2023

作者： Yang, Shufan Li, Qianmu Wang, Pengchuan Lian, Zhichao Hou, Jun Rao, Ya Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing China Nanjing Vocational University of Industry Technology School of Social Science Nanjing China Nanjing University of Science and Technology Information Construction and Management Division Nanjing China

ISBN: (纸本)9798350319804

Recent research has shown that large natural language processing (NLP) models have been vulnerable to a security threat called backdoor attacks. The current privately-triggered backdoor attack achieves the attack target by modifying the label of the poisoned data to a specified label. Still, the result often ignores the consistency of the sample semantics and the label, thus failing to achieve stealthy attacks on system users and system deployers. To address this issue, we use human-written text perturbations, which are less likely to be detected as machine-manipulation and removed by defense systems, as a backdoor trigger and apply a mild adversarial perturbation to the poisoned samples before implanting the backdoor, thereby addressing the semantic inconsistency caused by modifying the labels of the poisoned data. Furthermore, we use learnable backdoor triggers to improve the stealth of backdoor attacks while avoiding the conflict between textual adversarial perturbations and backdoor implantation. Experiments show that our attack achieves close to 100% attack success rates on SST-2, OLID and AG's News datasets without affecting the utility of existing NLP models. © 2023 IEEE.

关键词： natural language processing (NLP) models textual backdoor attacks

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：