检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Feng, Hui Guo, Jundong Xu, Haixiang Du, Zhe Zhang, Yingju He, Yijing Cao, Guilin Ge, Shuzhi Sam Key Laboratory of High-Performance Ship Technology Wuhan University of Technology Ministry of Education Wuhan China School of Naval Architecture Ocean and Energy Power Engineering Wuhan University of Technology Wuhan430063 China Wuhan University of Technology China Key Laboratory of High Performance Ship Technology of Ministry of Education Wuhan University of Technology Wuhan430063 China Department of Electrical & Computer Engineering National University of Singapore Singapore117576 Singapore

Smart ships commonly utilize visual measurement units, such as cameras, for environmental perception in the maritime domain, aimed at achieving advanced navigation capabilities. Characterized by the influence of wind, wave, and ocean current, smart ships navigating on maritime environment frequently encounter sway and motion disturbances, which subsequently introduce uncertainties to visual sensors, notably leading to motion blur in captured images. In order to mitigate the detrimental impact of motion blur on the visual obstacle detection algorithm employed in smart ships, we introduce IDD-GAN. Unlike conventional approaches, which treat motion deblurring and object detection as separate tasks, IDD-GAN integrates both processes, enabling end-to-end training and prediction through the use of generative adversarial networks. To address varying scales of motion blur caused by different levels of sensor interference, we have developed a multi-scale deblurring discriminator. Empirical results demonstrate the capability to achieve high-performance objectdetection even under conditions of motion blur. © 2024, The Authors. All rights reserved.

关键词： Ships

来源：评论

学校读者我要写书评

暂无评论

A Rapid GBDT-BiLSTM Based Damage Detection Technique in Bridges using Accurate Parameters

A Rapid GBDT-BiLSTM Based Damage Detection Technique in Brid...

引用

2024 Asian Conference on Intelligent Technologies, ACOIT 2024

作者： Babu, Uppara Raghu Patil, Deepak T. Qasim, Jameela Soni, Mukesh Sharma, Neelam Bhoopathy, V. Srinivasa Ramanujan Institute of Technology Andhra Pradesh Anantapur India Bharati Vidyapeeth College of Architecture University of Mumbai Maharashtra Navi Mumbai India Department of Bridge Engineering School of Civil Engineering Tongji University Shanghai China Department of Research and Development Lovely Professional University Phagwara India Physical Education Department Lovely Professional University Punjab India Department of Computer Science and Engineering Sree Rama Engineering College Tirupathi India

ISBN: (纸本)9798350374933

Conventional methods for diagnosing bridge damage have centred on tracking changes in modal-based Damage Sensitive Features (DSFs), which are strongly related to structural stiffness. Environmental and operational variations, inefficient use of machine learning approaches for damage detection, and an overall reliance on modal-based DSFs are some of the limits and hurdles that the system still faces, despite substantial progress towards practical deployment. According to the proposed method, the initial three steps are data preparation, feature extraction, and model training. In order to identify damage during the preprocessing step, the suggested approach utilises anomaly scores. Features in the time-frequency domain allow for parallel processing of signals in the signal-to-feature extraction pipeline. After the features have been extracted, the data is used to train GBDT-BiLSTM models. The proposed approach achieves better results than the well-known alternatives, GBDT and BiLSTM. © 2024 IEEE.

关键词： Bridges

来源：评论

学校读者我要写书评

暂无评论

Design and Experimental Investigation of Trikarenos: A Fault-Tolerant 28nm RISC-V-based SoC

arXiv

引用

arXiv 2024年

作者： Rogenmoser, Michael Wiese, Philip Forlin, Bruno Endres Gürkaynak, Frank K. Rech, Paolo Menicucci, Alessandra Ottavi, Marco Benini, Luca The Integrated Systems Laboratory ETH Zurich Switzerland The Computer Architecture for Embedded Systems The University of Twente Netherlands The Department of Industrial Engineering The University of Trento Italy The Department of Space Engineering The Delft University of Technology Netherlands The Computer Architecture for Embedded Systems The University of Twente Netherlands The Department of Electronic Engineering The University of Rome Tor Vergata Italy The Integrated Systems Laboratory ETH Zurich Switzerland The Department of Electrical Electronic and Information Engineering The University of Bologna Italy

We present a fault-tolerant by-design RISC-V SoC and experimentally assess it under atmospheric neutrons and 200 MeV protons. The dedicated ECC and Triple-Core Lockstep countermeasures correct most errors, guaranteein... 详细信息

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

An Identity-Based Encryption Method for SDN-Enabled Source Routing Systems

引用

Security and Communication Networks 2022年 2022卷

作者： Alzahrani, Bander Chaudhry, Shehzad Ashraf College of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Department of Computer Engineering Faculty of Engineering and Architecture Istanbul Gelisim University Istanbul Turkey

In this study, we consider endpoints communicating over a software-defined networking (SDN)-based architecture using source routing, i.e., packets are routed through a path selected by the packet sender, and we provide a security solution that enforces the selected path. In particular, our solution allows a sender to select the path that a packet should go through using a constant-size cryptographic construction which is referred to as the authenticator. A recipient can examine an authenticator and verify that the received packet has followed the path selected by the sender. Additionally, any intermediate "programmable"switch can verify whether or not it is included in the path of a packet. Our solution can be used even for paths that include multiple recipients (e.g., multicast paths), as well as multiple parallel paths (e.g., multipath transmissions). We implement our solution by leveraging identity-based encryption (IBE), so it can be used by any sender that knows the identifiers of the links that compose the desired path, i.e., information that the sender usually already knows as part of the source routing protocol. Our solution is realistic since it can be implemented over a variety of platforms with tolerable overhead. © 2022 Bander Alzahrani and Shehzad Ashraf Chaudhry.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

architecture Descriptions Analysis Based on Text Mining and Crawling technology 3

Architecture Descriptions Analysis Based on Text Mining and ...

引用

3rd IEEE International Conference on Frontiers technology of Information and computer, ICFTIC 2021

作者： Zheng, Tong Zhao, Dongmiao Wang, Xingtian Gao, Weijun Miao, Sheng Qingdao University College of Computer Science and Technology Qingdao China Qingdao University of Technology Innovation Institute for Sustainable Maritime Architecture Research and Technology Qingdao China Faculty of Environmental Engineering University of Kitakyushu Kitakyushu Japan Qingdao University of Technology School of Information and Control Engineering Qingdao China

ISBN: (纸本)9781665406055

Nowadays, text mining technology is developed rapidly and employed by various contexts, such as healthcare, public opinion analysis, and document retrieval. Architectural design descriptions usually include large amount of massive text, which means information and knowledge are hidden. Since more and more attention are paid to the sustainable development, this paper research the main building design factors on nature aspect by using text mining. Collecting and processing 41,062 descriptions of architecture projects from website, the frequency of occurrence words with nature aspect are analyzed in 11 architecture categories respectively. The top 100 words of frequency are taken to constitute the word cloud, and the design factors on natural environment aspect could be summarized as area, light, landscape, structure, material, façade, site, water, wind, and view. This will provide architects guidance on dealing with the contradiction between building and nature. It will help us to further explore the relationship between architectural design and natural environment and realize a green and sustainable future. © 2021 IEEE.

关键词： Architectural design

来源：评论

学校读者我要写书评

暂无评论

Employment Data Acquiring Method Based on WeChat Scan Code

Employment Data Acquiring Method Based on WeChat Scan Code

引用

International Conference on Systems and Informatics (ICSAI)

作者： Bianping Su Yunsong Wang Yantao He Longqing Zhang Jiayu He Jieming Lin School of Computer Guangdong University of Science & Technology Dongguan Guangdong China Xi'an International Inland Port Investment and Development Group Co. Ltd. Xi'an Chan-Ba International Port Management Committee Xi'an China School of Science Xi'an University of Architecture and Technology Xi'an Chin

ISBN: (数字)9798331510138

ISBN: (纸本)9798331510145

Based on the current employment situation and methods for obtaining unemployment and employment data in China, a new method for obtaining unemployment and employment data was constructed using the Naive Bayes classification principle in machine learning by WeChat scan data of travelers. This method divides the unemployment or employment status of individuals using prior and posterior probabilities. The evaluation index values of the experimental results on the dataset demonstrate the effectiveness of the method, and the accuracy of determining the employment status of travelers through mobile phone calls has increased by 22.9%. A strategy of data preprocessing combined with this method was proposed for large-scale data and preliminary discussions were conducted. The new method of obtaining unemployment and employment data has opened up new avenues for traditional statistical data acquisition, providing strong intelligent support for the government to dynamically grasp the employment situation in real time.

关键词： Social networking (online) Posterior probability Employment Machine learning Message services Real-time systems Mobile handsets Naive Bayes methods Unemployment Informatics

来源：评论

学校读者我要写书评

暂无评论

Facial Recognition Impact in Smartphone Sector 4

Facial Recognition Impact in Smartphone Sector

引用

4th International Conference on Inventive Research in Computing Applications, ICIRCA 2022

作者： Jha, Amaresh Sudhakar, P. Lokhande, Sharayu Ashish Kumar Ishodzhanova, Galina Venkatrao, K. Zhakupova, Aliya School of Digital Media Journalism & Mass Communication Gd Goenka University India Vignan's Nirula Institute of Technology and Science for Women Department of Ece India Computer Engineering Army Institute of Technology India International Education Corporation Department of Architecture Kazakhstan Srkr Engineering College Department of Ece India International Education Corporation Department of Linguistics Kazakhstan

ISBN: (数字)9781665497077

ISBN: (纸本)9781665497077

In recent times, technological advancement brings many benefits for people and facial recognition technology is one of them. Nowadays, S martphone users increasingly use facial recognition features that help in verifying identity of users for different purposes, for example, accessing their device before making any payment from their phones. This study paper has analysed impact of facial recognition systems in S martphone sectors by discussing its advantages and challenges to understand both its negative and positive impact. Literature review section has provided relevant information on selected topic as it has elaborated that different large organisation have their own face recognition software for Apple, Facebook, and Google. Additionally, it has mentioned that there are two different types of facial recognition software such as camera-based and infrared;however, regarding effectiveness, infrared works more appropriate rather than camera-based recognition technologies. The paper has also elaborated that this technology offers automating time-tracking systems and it has touch less sign options, which help them in limiting physical contact with others. Result of this study showed that facial recognition helps to protect any type of unauthorised access in a Smartphone as well as it could prevent cyber threats by recognising face of S martphone users. Additionally, due to this software's fast identification feature, it could successfully verify faces of people within a few seconds. However, as this software is based on artificial intelligence, unlike other applications, it is highly vulnerable as hackers can hack Smartphones if strong algorithms are more used. Lastly, to prevent this issue a strong AI infrastructure and model security is required in future. © 2022 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Enabling High Capacity Flexible Optical Networks 25

Enabling High Capacity Flexible Optical Networks

引用

25th International Conference on Optical Network Design and Modelling, ONDM 2021

作者： Garcia Gunning, Fatima C. Kaur, Amandeep Estrada, Natalia Canas Raulin, Julie Verbishchuk, Yuliya Sreenan, Cormac J. University College Cork Tyndall National Institute Ireland School of Engineering and Architecture University College Cork Ireland School of Computer Science and Information Technology University College Cork Ireland

ISBN: (纸本)9783903176331

Current bandwidth demands are encouraging the exploration of optical frequency comb generators and flexible modulation formats to enable very high-capacity transmission beyond the C-band, which can be augmented with existing real-time digital electronic signal processing for pre-emphasis and post-impairment compensation at very high clock speeds. But for exploitation and deployment in commercial networks these devices will require support for remote management embedded with service providers' operation and business-support systems. However, installed network management systems must deal with a range of dissimilar network devices. This diversity spans across electronic packet switches, optical circuit switches, and monitoring instrumentation for telemetry, ranging from legacy to state-of-the-art models. Software defined networking (SDN) flexible management approach unlocks exciting possibilities to jointly exploit the full capabilities of digital electronic packet switching and the many degrees of freedom presented by analogue optical EM carriers. In this paper, we will expose some of these possibilities, where these technologies can, through SDN, be reimagined to enable flexible high-capacity systems. We will be revisiting the potential for multi-carrier transmitters, and utilising analogue methods to monitor transmitter performance. We will also show how existing protocols can be used to support both legacy and state-of-the-art SDN-enabled devices, incorporating to management operating systems such as ONOS, showing that a smooth transition to fully automated networks with closed-loop control is now a real prospect. © 2021 IFIP TC6 WG6.10.

关键词： Packet switching

来源：评论

学校读者我要写书评

暂无评论

Comparative Assessment Between Statistical and Soft Computing Methods for Accident Severity Classification

引用

Journal of The Institution of Engineers (India): Series A 2020年第1期101卷 27-40页

作者： Sarkar, Amrita Sarkar, Satyaki Department of Computer Science and Engineering Sarala Birla University Ranchi835103 India Department of Architecture Birla Institute of Technology Mesra Ranchi835215 India

Globally traffic scenario has experienced a vast change over the years as volumes of traffic on urban roads have increased by leaps and bounds. This increase has also marked an increase in the number of road accidents, both fatal and non-fatal. Accident prediction has a significant role in the improvement in traffic safety, and urban traffic management. Different statistical methods and various soft computing techniques are being used for developing accident prediction models. In this study, ensemble ranking method, comprising three filter-based ranking methods such as Information Gain, Gain Ratio, and Symmetric Uncertainty, has been employed to select significant features for prediction of accident severity. Through analysis, eight significant features have been selected for accident severity prediction. These are Annual Average Daily Traffic, Road Width, Percentage of Left-Turn Vehicles, Driver’s Age, Percentage of Right-Turn Vehicles, Types of Vehicles Involved, Spot Speed, and Cause of Accidents. Multiple logistic regression (MLGR) and artificial neural network (ANN) have been applied for accident severity prediction in urban roads. This analysis concludes that ANN model gives more accuracy and minimum errors compared with the MLGR method at the time of severity classification of a vehicular accident. © 2019, The Institution of Engineers (India).

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

How to Evaluate Deep Neural Network Processors: TOPS/W (Alone) Considered Harmful

引用

IEEE Solid-State Circuits Magazine 2020年第3期12卷 28-41页

作者： Sze, Vivienne Chen, Yu-Hsin Yang, Tien-Ju Emer, Joel S. Electrical Engineering and Computer Science Massachusetts Institute of Technology MA United States Facebook United States Architecture Research Group Nvidia United States

A significant amount of specialized hardware has been developed for processing deep neural networks (DNNs) in both academia and industry. This article aims to highlight the key concepts required to evaluate and compare these DNN processors. We discuss existing challenges, such as the flexibility and scalability needed to support a wide range of neural networks, as well as design considerations for both the DNN processors and the DNN models themselves. We also describe specific metrics that can be used to evaluate and compare existing solutions beyond the commonly used tera-operations per second per watt (TOPS/W). This article is based on the tutorial 'How to Understand and Evaluate Deep Learning Processors' that was given at the 2020 International Solid-State Circuits Conference, as well as excerpts from the book, Efficient Processing of Deep Neural Networks [36]. © 2009-2012 IEEE.

关键词： Deep neural networks

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：