检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks (IJCNN)

作者： Ye Wei He Haitao Gerald Schaefer Zhigang Ji Yifan Wang Hui Fang Department of Computer Science Loughborough University Loughborough UK The Alan Turing Institute London UK School of Architecture Building and Civil Engineering Loughborough University Loughborough UK National Key Laboratory of Science and Technology on Micro/Nano Fabrication Shanghai Jiao Tong University Shanghai China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Traffic forecasting, crucial for intelligent transport systems, faces significant challenges from distribution shifts due to the dynamic nature of traffic patterns. Although normalisation approaches have been proposed to address distribution shifts in other time-series forecasting tasks such as predicting electricity consumption load prediction or influenza-like illness patient number estimation, they fall short in handling the complex spatial and temporal shifts in traffic data. In this paper, we propose a novel memory-facilitated joint-space shift adaptation framework, ST-Align, to address this problem in traffic forecasting. ST-Align comprises two key components targeting the input and latent space, respectively: a memory-based data alignment module in the input space, and an end-to-end memory network structure dedicated to alignment within the latent space. This joint-space design enables our ST-Align framework to effectively capture and adapt to dynamic distribution shifts in both spatial and temporal dimensions, thus enhancing model performance. Extensive experiments on various real-world datasets and prediction backbones convincingly demonstrate the robustness and generalisability of our method.

关键词： Adaptation models Electricity Neural networks Estimation Traffic control Robustness Forecasting

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of a real-time onboard system for a stratospheric balloon mission using commercial off-the-self components and a model-based approach

arXiv

引用

arXiv 2024年

作者： Pérez-Muñoz, Ángel-Grover Gamazo-Real, Jose-Carlos González-Bárcena, David Zamorano, Juan Universidad Politécnica de Madrid Department of Architecture and Technology of Information Systems ETSI Ingenieros Informáticos Madrid28660 Spain Universidad Politécnica de Madrid Information Systems Department Computer Architecture and Technology Area ETSI Sistemas Informáticos Madrid28031 Spain Universidad Politécnica de Madrid Instituto Universitario de Microgravedad "Ignacio Da Riva" ETSI Aeronáutica y del Espacio Madrid28040 Spain

Stratospheric balloons have emerged as an affordable and flexible alternative to traditional spacecrafts as they are implemented using commercial off-the-shelf (COTS) equipment without following strict methodologies. HERCCULES is a stratospheric balloon mission that aims to characterize the convective heat and radiative environment in the stratosphere. The purpose of this article is to present the HERCCULES onboard software (OBSW) whose design and complexity is comparable to that of satellite systems, since it must control about sixty COTS equipment using a single Raspberry Pi 4B as onboard computer and ensure the real-time requirements. Compared to similar systems, novel contributions are presented as the OBSW is developed following model-based and component-based approaches using the TASTE toolchain from the European Space. © 2024, CC BY.

关键词： Real time systems

来源：评论

学校读者我要写书评

暂无评论

Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation

SSRN

引用

SSRN 2023年

作者： Xiu, Haoyi Liu, Xin Wang, Weimin Kim, Kyoung-Sook Shinohara, Takayuki Chang, Qiong Matsuoka, Masashi Department of Architecture and Building Engineering Tokyo Institute of Technology Tokyo Japan Artificial Intelligence Research Center AIST Tokyo Japan DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China Innovation Technology Office Research Center PASCO Corporation Tokyo Japan Department of Computer Science Tokyo Institute of Technology Tokyo Japan

3D point clouds are discrete samples of continuous surfaces which can be used for various applications. However, the lack of true connectivity information, i.e., edge information, makes point cloud recognition challenging. Recent edge-aware methods incorporate edge modeling into network designs to better describe local structures. Although these methods show that incorporating edge information is beneficial, how edge information helps remains unclear, making it difficult for users to analyze its usefulness. To shed light on this issue, in this study, we propose a new algorithm called Diffusion Unit (DU) that handles edge information in a principled and interpretable manner while providing decent improvement. First, we theoretically show that DU learns to perform task-beneficial edge enhancement and suppression. Second, we experimentally observe and verify the edge enhancement and suppression behavior. Third, we empirically demonstrate that this behavior contributes to performance improvement. Extensive experiments and analyses performed on challenging benchmarks verify the effectiveness of DU. Specifically, our method achieves state-of-the-art performance in object part segmentation using ShapeNet part and scene segmentation using S3DIS. Our source code is available at https://***/martianxiu/DiffusionUnit. © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on Gravity Currents with Internal Strati Cation in Semicircular Channels

SSRN

引用

SSRN 2022年

作者： Chiapponi, Luca Zemach, Tamar Petrolo, Diana Ungarish, Marius Longo, Sandro Department of Engineering and Architecture Università degli Studi di Parma Parco Area delle Scienze 181/A Parma43124 Italy Department of Computer Science Tel-Hai College Tel-Hai 1220800 Israel Department of Computer Science Technion Israel Institute of Technology Haifa32000 Israel

We present an experimental study of gravity currents (GCs) with internal stratification in a semicircular channel in the inertial–buoyancy and Boussinesq regime. Forty tests were performed with a denser volume of fluid (brine advancing in a fresh water ambient fluid) in lock-release. The lock contains an internal stratification, with a layer of density ρL overlain by a layer of density ρU, where ρa U L and ρa is the density of the ambient fluid. The experiments cover both a full depth and a partial depth configuration. The measurements consist of marking the front position of the currents as a function of the time from release, t. Two lateral video-cameras were used to detect the flow profile. Also local instantaneous density and velocity profiles data were collected in a fixed section downstream of the gate, in order to give further details and a better description of the physical phenomenon. The integral data of front speed and current thickness were compared to a theoretical model [1] based on (i) a Boussinesq flow;(ii) large Reynolds number;(iii) current advancing in shallow water conditions;and (iv) negligible ambient fluid dynamics. The system of equations and boundary conditions allows the prediction of the motion of the GC, in particular the position and speed of the nose xN (t) and uN (t). The agreement of theory and experiments is fairly good, especially for the full depth configuration. The partial depth configuration experiments are less accurately reproduced by the theory, and require a correction coefficient of the Froude number at the front, mimicking dissipation and mixing. A thorough investigation was carried out for density profiles, average velocities within the current, and buoyancy fluxes of a turbulent diffusive nature, with a quadrant analysis distinguishing the origin and direction of the fluxes. © 2022, The Authors. All rights reserved.

关键词： Gravity waves

来源：评论

学校读者我要写书评

暂无评论

Directivity Improvement of MIMO Array Antenna using Novel Eight Element Array Configuration

Directivity Improvement of MIMO Array Antenna using Novel Ei...

引用

Advancement in Electronics & Communication Engineering (AECE), International Conference on

作者： Alaa M. Lafta Abdul Razzaq T. Zaboun Shakhlokhon Kosimova Alaa. Shather Hawraa Ali Sabah Haider Alchilibi National University of Science and Technology Dhi Qar Iraq Forensic sciences department Al-Esraa University College Baghdad Iraq Department of Architecture Fergana Polytechnic Institute Fergana Uzbekistan Department of Computer Engineering Technology Al Kitab University Altun Kopru Kirkuk Iraq Medical Laboratory Techniques Department Al-Farahidi University Baghdad Iraq

In this study, the Directivity of the Microstrip Patch MIMO Antenna is a Novel Eight element array configuration in comparison with its performance of a Single element patch antenna. Directivity improvement and Return loss measured for different frequencies and values are compared with a Single element patch antenna. Novel Eight element MIMO array antenna is designed and compared with a Single patch element antenna. In this work, there are two groups (Eight element patch & Single element patch) each consisting of 20 samples with pre-test power or G-power of 80%. The mean Return loss in the Novel eight element MIMO array antenna is -18.39 dB and in the Single element antenna is -15.21 dB. These results showed that the Novel eight element array exhibited a better Directivity improvement (4.483 dB) than the single element antenna (2.261 dB) with the two-tailed significance of (p < 0.05). The Directivity improvement is significantly better for a Novel eight element array antenna when compared with a single element patch antenna.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Critical Analysis on Neural Networks and Deep Learning based Techniques for the Cloud Computing System and its Impact on Industrial Management 5

A Critical Analysis on Neural Networks and Deep Learning bas...

引用

5th International Conference on Contemporary Computing and Informatics, IC3I 2022

作者： Latoria, Akhilesh Joshi, S.K. Priya, A. Chakravarthi, M. Kalyan Chandan, Radha Raman Pant, Bhasker Auro University School of Information Technology Gujarat Surat India Uttaranchal University Uttarakhand Dehradun India School of Architecture KoneruLakshmaiah Educational Foundation Andhra Pradesh Guntur India VIT-AP University School of Electronics Engineering Amaravathi India Department of Computer Science Bachhaon Khushipur UP Varanasi India Graphic Era Deemed to Be University Department of CSE Uttarakhand Dehradun India

ISBN: (纸本)9798350398267

Due to the rising use of the internet for communication, commercial financial transactions, and other purposes, cloud computing is described as a crucial feature that has risen lately. Through network systems, this entails providing a flexible growth of different services. The fog is often used as a concept to describe different *** often trust cloud service providers to store enormous amounts of data and information with the intention of accessing it later. This paper is mainly concerned with doing a critical examination of the usage of supervised learning and deep learning in cloud applications, as well as their effects on production *** businesses are concentrating on using technology to increase returns on investments, assemble vast quantities of data, and archive it securely so that it may be utilised for organisational decision-making. Notwithstanding, they are more concerned with the cost and security of storing the information. so in order to accommodate the customers, the cloud services have used a wide range of approaches, including human brains, supervised learning, advanced analytics, and others. This helps to increase the users' credibility and help them use cloud storage to achieve their *** order to understand the overall efficacy of employing neural networks and advanced learning processes connected to cloud technology, this research is capable of using both secondary and primary information. The efficacy will be assessed by the researchers using correlation matrix and other non-parametric approaches. The conclusion is reached after thorough data examination and interpretation. © 2022 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Growing Aspects of Cyber Security in E-Commerce 4

Growing Aspects of Cyber Security in E-Commerce

引用

4th International Conference on Communication, Information and Computing technology, ICCICT 2021

作者： Bhatia, Nishant Lalitkumar Shukla, Vinod Kumar Punhani, Ritu Dubey, Shish Kumar Bachelor of Information Technology Amity University Dubai United Arab Emirates Department of Engineering and Architecture Amity University Dubai United Arab Emirates Department of Information Technology ASET Amity University Sector – 125 Uttar Pradesh Noida India Department of Computer Science and Engineering Jaipur National University India

ISBN: (纸本)9781665404303

The world is witnessing a transition from in-store shopping to online shopping. E-commerce (Electronic commerce) giants such as Amazon, Alibaba, eBay etc. are leading the way towards this change. Much technological advancement are being made to ease the life of mankind with online shopping being the most notable. E-commerce is known to be a powerful instrument for transformation of business that gives companies the opportunity to upgrade their supply chain operations, improve their network, as well as provide better services to both customers and suppliers. Applying the techniques of online shopping that yield such advantages may not be possible without the presence of a well-organized approach to E-commerce security. Ecommerce organizations such as Amazon and Alibaba have also been using such techniques to ensure data protection. The most common of them all is the One Time Password (OTP), which is sent to a user when they make payments online for identity verification. On the other hand, Alibaba uses a unique Key Management System (KSM) which is a fully managed service that helps customers create, delete, and manage encryption keys to protect data. This system provides availability, reliability and elasticity alongside security and compliance. The paper also explore the importance of different security algorithms in Ecommerce domain. © 2021 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Unveiling Hidden Energy Anomalies: Harnessing Deep Learning to Optimize Energy Management in Sports Facilities

arXiv

引用

arXiv 2024年

作者： Fadli, Fodil Himeur, Yassine Elnour, Mariam Amira, Abbes Department of Architecture & Urban Planning Qatar University Doha Qatar College of Engineering and Information Technology University of Dubai Dubai United Arab Emirates Department of Electrical Engineering Qatar University Doha Qatar Department of Computer Science University of Sharjah United Arab Emirates Institute of Artificial Intelligence De Montfort University Leicester United Kingdom

Anomaly detection in sport facilities has gained significant attention due to its potential to promote energy saving and optimizing operational efficiency. In this research article, we investigate the role of machine learning, particularly deep learning, in anomaly detection for sport facilities. We explore the challenges and perspectives of utilizing deep learning methods for this task, aiming to address the drawbacks and limitations of conventional approaches. Our proposed approach involves feature extraction from the data collected in sport facilities. We present a problem formulation using Deep Feedforward Neural Networks (DFNN) and introduce threshold estimation techniques to identify anomalies effectively. Furthermore, we propose methods to reduce false alarms, ensuring the reliability and accuracy of anomaly detection. To evaluate the effectiveness of our approach, we conduct experiments on aquatic center dataset at Qatar University. The results demonstrate the superiority of our deep learning-based method over conventional techniques, highlighting its potential in real-world applications. Typically, 94.33% accuracy and 92.92% F1-score have been achieved using the proposed scheme. © 2024, CC BY.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Advanced IOT Traffic Light Control System

Advanced IOT Traffic Light Control System

引用

International Conference on Advances in Computational Tools for Engineering Applications, ACTEA

作者： Martin Abou Hamad Antonio El Hajj Roy Abi Zeid Daou Ali Hayek Gaby Abou Haidar Biomedical Technologies Department Faculty of Public Health Lebanese German University Lebanon MART Learning Education and Research Center Lebanon Department of Computer Architecture and System Programming University of Kassel Kassel Germany Engineering Faculty American University of Science and Technology Zahle Lebanon

For several years, traffic congestion has been a major problem in big cities where the number of cars and different means of transportation has been increasing significantly. The problem of congestion is becoming more and more critical, and if not treated smartly this issue will negatively affect drivers by wasting time and fuel gas while waiting for hours in lanes. This paper presents a new and smart way to mitigate this issue in an affordable cost, minimum processing power, and low power consumption. This concept takes into consideration the majority of the cases that may cause congestion and presents a smart and accurate outputs to ease traffic flow leading to the prediction of the peak hours of traffic congestion for smarter control. A model is designed to study the case of a four lanes crossroad with two traffic lights and two LCD monitors. The strategy in reading data is divided into two parts: real data from sensors and pre collected data from google maps to create a kind of a predicted pattern over a certain time interval. The responsiveness of the system is analyzed thoroughly, and the accuracy of all possible cases is carefully considered and evaluated. Each part of the system was tested alone, and the overall system is still in an ongoing testing phase. The results have shown minimum faulty errors and accepted outputs that can lead to safe traffic control decisions. Finally, integrating more IoT devices and sensors between V2V, V2P, V2I with the help of artificial intelligence will definitely optimize this system with higher accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Irreversibility analysis of magnetized flow of engine oil hybrid nanofluid (Ti6Al4V-ZnO/EO) over a stretching surface

引用

Alexandria Engineering Journal 2025年 127卷 214-227页

作者： Hussain, Syed M. Faridi, Aftab Ahmed Ahmad, Hijaz Ali, Kashif Iqbal, Muhammad Rashid Jamshed, Wasim Guedri, Kamel Almaliki, Abdulrazak H. Department of Mathematics Faculty of Science Islamic University of Madinah Madinah42351 Saudi Arabia Department of Mathematics The Islamia University of Bahawalpur Bahawalpur63100 Pakistan Near East University Operational Research Center in Healthcare TRNC Mersin 10 Nicosia99138 Turkey Department of Technical Sciences Western Caspian University Baku1001 Azerbaijan Department of Mathematics College of Science Korea University 145 Anam-ro Seongbuk-gu Seoul02841 Korea Republic of Department of Basic Sciences and Humanities Muhammad Nawaz Sharif University of Engineering and Technology Multan60000 Pakistan Department of Mathematics and Statistics Institute of Southern Punjab Multan32100 Pakistan Islamabad44000 Pakistan College of Engineering Al-Ayen Iraqi University An Nasiriyah64001 Iraq Department of Computer Engineering Biruni University Topkapi Istanbul Turkey Mechanical Engineering Department College of Engineering and Architecture Umm Al-Qura University P. O. Box 5555 Makkah21955 Saudi Arabia Department of Civil Engineering college of Engineering Taif University Taif21944 Saudi Arabia

This article analyzes the irreversibility of hydro-magnetic dynamics of hybridized nanofluid comprising of titanium alloy (Ti6Al4V) and zinc-oxide (ZnO) submerged into engine oil (used as a fuel) through a porous stretching sheet with multipart effects of viscous dissipation and non-uniform heat source. An induced magnetic field exists in the flow field due to the conducting nature of the hybrid nanofluid. The equations of the flow model are transformed by the similarity transformations and then simulated through a numerical scheme constructed with a formulation of central differences that adopts successive over-relaxation methodology. In this thermodynamic system, entropy and Bejan number profiles corresponding to the prominent parameters are simultaneously analysed for both the nanofluid case and hybrid nanofluid case in the Cartesian coordinates. A comparison table is constructed to validate the numerical results with existing literature. The impacts of various parameters on Nusselt number and skin friction coefficient are graphed with reference to the magnetic field parameter. A significant reduction in irreversibility and a remarkable improvement in thermal characteristics of engine oil are observed due to induced magnetism effects. The engine oil hybrid nanofluid (Ti6Al4V-ZnO/EO) exhibits a 13.89 % higher heat transfer rate over a porous stretching surface compared to the engine oil nanofluid (Ti6Al4V/EO). © 2025 The Authors

关键词： Magnetic levitation

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：