检索结果-内蒙古大学图书馆

2020 International Conference on Electronics, Communications and Information Technology, CECIT 2020

作者： Shang, Mengjun Yin, Longxiang Xu, Ning School of Information Engineering Wuhan University of Technology Wuhan China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China

Nowadays, memristor-based neural network accelerators have been widely studied due to their outstanding performance in massive parallel vector matrix multiplication. However, the memristor is sensitive to temperature and its on/off state operation window can be seriously degraded by the increasing temperature, which may lead to computation failures in memristor -based NN accelerators. In this work, we establish an electro-thermal simulation platform to evaluate the temperature impact on memristor -based NN accelerators. With this platform, we first investigate the impact on computation accuracy with the temperature increase in different NN layers in the accelerators. We then apply a temperature-aware NN weight mapping scheme to the most temperature-sensitive layer and achieve 28.89% improvement in computation accuracy, which only has 0.06% difference with the improvement achieved by applied the mapping scheme to the whole NN model. This finding can help to simplify the temperature-aware hardware optimization design in memristor-based neural network accelerators and reduce the power consumption. © Published under licence by IOP Publishing Ltd.

关键词： Memristors

来源：评论

学校读者我要写书评

暂无评论

Fractional Fourier Transform Aided Computerized Framework for Alcoholism Identification in EEG 11th

Fractional Fourier Transform Aided Computerized Framework fo...

引用

11th International Conference on Health Information Science, HIS 2022

作者： Sadiq, Muhammad Tariq Akbari, Hesam Siuly, Siuly Li, Yan Wen, Paul School of Architecture Technology and Engineering University of Brighton BrightonBN2 4AT United Kingdom Department of Biomedical Engineering Islamic Azad University Tehran*** Iran Institute for Sustainable Industries & Liveable Cities Victoria University MelbourneVIC3011 Australia School of Mathematics Physics and Computing University of Southern Queensland Toowoomba Campus Toowoomba4350 Australia School of Engineering University of Southern Queensland Toowoomba Campus Toowoomba4350 Australia

ISBN: (纸本)9783031206269

Alcoholism has a detrimental impact on brain functioning. Electroencephalogram (EEG) signals are commonly used by clinicians and researchers to quantify and document alcoholic brain activity. Despite widespread attention in these signals, the non-stationarity of physiological EEG signals has complications in alcoholism applications. Fourier Transform have been used to examine stationary signals in a straightforward manner. Non-stationary signal analysis, on the other hand, is unsatisfactory using such an approach because it cannot show the occurrence time of distinct frequency components. Furthermore, it is critical to capture both time and frequency characteristics. To overcome these aforementioned issues in alcoholism EEG signals, a computer-aided diagnosis (CAD) approach is proposed in this study to distinguish between normal and alcoholic subjects. The dataset is first split into multiple EEG signals, and the multiscale principal component analysis approach is used to remove noises. Second, as a novel and powerful feature extraction method for EEG signals, the Fractional Fourier Transform (FrFT) methodology with different coefficients is used. A generalization of the classical Fourier Transform, the FrFT, may reveal the fluctuating frequencies of non-stationary EEG signals. The t-test method is used to evaluate the FrFT derived coefficients as features. Finally, to categorize normal vs alcoholic signals, relevant features are tested on multiple machine learning classifiers accessible in the WEKA platform using a 10-fold cross-validation technique. The obtained results effectively support the usefulness of FrFT coefficients as features. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Blockchain Vulnerabilities and Recent Security Challenges: A Review Paper

Blockchain Vulnerabilities and Recent Security Challenges: A...

引用

Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI), International Conference on

作者： Aysha AlFaw Wael Elmedany Mhd Saeed Sharif College of Information Technology University of Bahrain Sakhir Bahrain School of Architecture Computing and Engineering University of East London London England

ISBN: (纸本)9781665490597

Blockchain is a relatively new technology, a distributed database used for sharing between nodes of computer networks. A blockchain stores all information in automated digital format as a database. Blockchain innovation ensures the accuracy and security of the data record and generates trust without the need for a trusted third party. The objectives of this paper are to determine the security risk of the blockchain systems, analyze the vulnerabilities exploited on the blockchain, and identify recent security challenges that the blockchain faces. This review paper presents some of the previous studies of the security threats that blockchain faces and reviews the security enhancement solutions for blockchain vulnerabilities. There are some studies on blockchain security issues, but there is no systematic examination of the problem, despite the blockchain system’s security threats. An observational research methodology was used in this research. Through this methodology, many research related to blockchain threats and vulnerabilities obtained. The outcomes of this research are to Identify the most important security threats faced by the blockchain and consideration of security recently vulnerabilities. Processes and methods for dealing with security concerns are examined. Intelligent corporate security academic challenges and limitations are covered throughout this review. The goal of this review is to serve as a platform as well as a reference point for future work on blockchain-based security.

关键词： Industries Technological innovation Systematics Non-repudiation Blockchains Peer-to-peer computing Security

来源：评论

学校读者我要写书评

暂无评论

Levelized Cost of Energy for Various Floating Offshore Wind Farm Designs in the Areas Covered by the Spanish Maritime Spatial Planning

SSRN

引用

SSRN 2024年

作者： Thomas, Brieuc Costoya, Xurxo deCastro, M. Iglesias, Gregorio Gómez-Gesteira, M. Campus da Auga Ourense32004 Spain University College Cork School of Engineering and Architecture & MaREI Environmental Research Institute College Road Cork Ireland University of Plymouth School of Engineering Computing and Mathematics Marine Building Drake Circus PlymouthPL4 8AA United Kingdom

Spain took a significant step towards achieving its goal of installing 1 to 3 GW of floating offshore wind capacity by 2030, by implementing Maritime Spatial Planning encompassing 19 designated areas. Therefore, it is essential to calculate the Levelized Cost of Energy for strategically designed wind farms, taking into account the number and capacity of wind turbines. To find the most cost-effective offshore wind energy sites, the optimal combination of rated power and the number of turbines was determined and compared across different locations. This analysis used downscaled wind data from the 6th phase of the Coupled Model Intercomparison Project multi-model ensemble, covering 2025-2049 under the Shared Socioeconomic Pathway 2-4.5 scenario, matching the expected lifespan of wind farms. The results show that the Levelized Cost of Energy is lower for farms with a higher number of wind turbines with increased rated power. The areas located in the Canary Islands exhibit the most economically advantageous prices overall, ranging from 100 to 135 €/MWh. Regions such as Galicia and Cataluña also present a high diversity in prices (105 – 160 €/MWh), while Andalucía shows moderate values (135 – 140 €/MWh). © 2024, The Authors. All rights reserved.

关键词： Offshore wind farms

来源：评论

学校读者我要写书评

暂无评论

A Machine Vision-Based Person Detection under Low-Illuminance Conditions Using High Dynamic Range Imagery for Visual Surveillance System 3

A Machine Vision-Based Person Detection under Low-Illuminanc...

引用

3rd International Conference on Smart Technologies in computing, Electrical and Electronics, ICSTCEE 2022

作者： Susa, Julie Ann B. Militante, Sammy V. Acoba, Aimee G. Evangelista, Ryan Soriente Lacatan, Luisito Lolong Lavina, Charlemagne G. Tanguilig, Bartolome T. Southern Luzon State University Dept. of Computer Engineering Quezon Lucban Philippines College of Engineering and Architecture University of Antique Antique Philippines Technological University of the Philippines Electronics Eng'g Technology Department Manila Philippines School of Graduate Studies Sulu State College Sulu Philippines College of Computing and Engineering Pamantasan Ng Cabuyao Laguna Philippines

ISBN: (纸本)9781665456647

The most difficult component of any computer vision application objects recognition and tracking. Video surveillance is a major study subject in computer vision in a dynamic environment, especially for security purposes. Video surveillance technology is critical in preventing crime, terrorism, and other threats. Several existing technologies can accurately monitor a person's mobility in interior environments. As well as regulated outdoor settings, object recognition and tracking at night, on the other hand, remain significant challenges for visual surveillance. The objects are usually farther away, inconspicuous, and have low brightness against the background. In this paper, detecting objects specifically people under low lighting conditions with the help of deep learning algorithms was used. For applications like in-car cameras and surveillance systems that operate in low light, these algorithms might improve picture identification performance. © 2022 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Reduced Order Modelling of a Reynolds number 106 jet flow using Machine Learning approaches 30

Reduced Order Modelling of a Reynolds number 106 jet flow us...

引用

30th AIAA/CEAS Aeroacoustics Conference, 2024

作者： Murali, A.R. Kennedy, M.L.K. Naghibi, S. Elnaz Jacob, Marc C. Hinkelmann, Reinhard Karabasov, Sergey A. Ecole Centrale de Lyon CNRS Univ Claude Bernard Lyon 1 INSA Lyon Laboratoire de Mécanique des Fluides et d’Acoustique UMR5509 Ecully69130 France Institut für Bauingenieurwesen Technische Universität Berlin Gustav-Meyer-Allee 25 Berlin13355 Germany School of Architecture Computing and Engineering University of East London London United Kingdom Institut für Bauingenieurwesen Technische Universität Berlin Berlin Germany School of Engineering and Material Science Queen Mary University of London London United Kingdom

ISBN: (数字)9781624107207

ISBN: (纸本)9781624107207

The extraction of the most dynamically important coherent flow structures using reduced order models (ROM) is a challenging task in various fluid dynamics applications. In particular, for high-speed round jet flows, the axisymmetric pressure mode of interest is known to bere sponsible for sound radiation at small angles to the jet axis and dominant contribution to the jet noise peak. In this work the axisymmetric pressure mode of the Navier-Stokes solution of a high speed jet flow at low frequency is reconstructed from simulation data using popular Machine Learning (ML) methods, whose output can later be exploited for data-driven design of effective turbulent acoustic source models. The data used as input for the ML techniques are derived from the Large Eddy Simulation database obtained by application of the high-resolution CABARET method accelerated on GPU cards for flow solutions to NASA Small Hot Jet Acoustic Rig(SHJAR) jets. The SHJAR simulation database is fed to Spectral Proper Orthogonal (SPOD), and the resulting time coefficients of the turbulent pressure fluctuations are the targets of the three machine learning methods put to test in this work. The first Machine Learning method used is the Feed-forward Neural Networks technique, which was successfully implemented for a turbulent flow over a plunging aerofoil in the literature. The second method is based on the application of Genetic Programming, which is a symbolic regression method well-known in optimisation research, but it has not been applied for turbulent flow reconstruction before. The third method, commonly known as Echo State Networks (ESNs), is a time series prediction and reconstruction method from the field of Reservoir computing. A report on the attempts to apply these methods for approximation and extrapolation of the turbulent flow signals are discussed. © 2024, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Reynolds number

来源：评论

学校读者我要写书评

暂无评论

Learning Orientation Field for OSM-Guided Autonomous Navigation

arXiv

引用

arXiv 2025年

作者： Huang, Yuming Gao, Wei Zhang, Zhiyuan Ghaffari, Maani Song, Dezhen Xu, Cheng-Zhong Kong, Hui Faculty of Science and Technology University of Macau China School of Computing and Information Systems Singapore Management University Singapore Department of Naval Architecture and Marine Engineering Department of Robotics University of Michigan Ann ArborMI United States United Arab Emirates

OpenStreetMap (OSM) has gained popularity recently in autonomous navigation due to its public accessibility, lower maintenance costs, and broader geographical coverage. However, existing methods often struggle with noisy OSM data and incomplete sensor observations, leading to inaccuracies in trajectory planning. These challenges are particularly evident in complex driving scenarios, such as at intersections or facing occlusions. To address these challenges, we propose a robust and explainable two-stage framework to learn an Orientation Field (OrField) for robot navigation by integrating LiDAR scans and OSM routes. In the first stage, we introduce the novel representation, OrField, which can provide orientations for each grid on the map, reasoning jointly from noisy LiDAR scans and OSM routes. To generate a robust OrField, we train a deep neural network by encoding a versatile initial OrField and output an optimized OrField. Based on OrField, we propose two trajectory planners for OSM-guided robot navigation, called Field-RRT* and Field-Bezier, respectively, in the second stage by improving the Rapidly Exploring Random Tree (RRT) algorithm and Bezier curve to estimate the trajectories. Thanks to the robustness of OrField which captures both global and local information, Field-RRT* and Field-Bezier can generate accurate and reliable trajectories even in challenging conditions. We validate our approach through experiments on the SemanticKITTI dataset and our own campus dataset. The results demonstrate the effectiveness of our method, achieving superior performance in complex and noisy conditions. Our code for network training and real-world deployment is available at https://***/IMRL/OriField. Copyright © 2025, The Authors. All rights reserved.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Adaptive Electric Vehicle Charge Controllers Using Deep Reinforcement Learning for Real-Time Optimization 1

Adaptive Electric Vehicle Charge Controllers Using Deep Rein...

引用

1st International Conference on Advances in Computer Science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Kavitha, N. Bdair, Mohammad Chandrasekar, P. Veerakumar, S. Kumar, M. Hema Kumar, Vinay Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of EEE Tamil Nadu Chennai India School of Architecture Computing & Engineering University of East London London United Kingdom Bannari Amman Institute of Technology Department of EEE Tamil Nadu Erode India Sona College of Technology Department of ECE Tamil Nadu Salem India B N M Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India

ISBN: (纸本)9798331518578

The increasing adoption of electric vehicles necessitates intelligent charging systems to address challenges such as grid overload, renewable energy integration, and user prioritization. This paper presents a new framework in optimizing the efficiency of electric car charging: Hierarchical Multi-Agent Deep Reinforcement Learning. In this architecture, a global coordinator relies on Proximal Policy Optimization to coordinate across stations, and the local agents follow Deep Q-Networks to manage their resources at the station level. Test results: A comparison of the test results with regular methods shows an average waiting time reduced by 30%, a 15% increase in the usage of renewable energy, and a reduction of 22% in the system latency. For grid loads, consistent results from the operation of this architecture ensure that minimal unserved energy demand leads to the balanced serving of loads. This method, therefore, aligns well with sustainable energy goals through simultaneous improvement in effectiveness of charging infrastructure and on the flexible scale of solution. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Bibliographic Exploration of Application of Machine Learning and Artificial Intelligence in Solar Energy

Bibliographic Exploration of Application of Machine Learning...

引用

2024 International Conference on Science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Ajibade, Samuel-Soma M. Bashir, Faizah Mohammed Dodo, Yakubu Aminu Oyebode, Oluwadare Joshua Culpable, Rex V. De La Calzada, Limic M. Adediran, Anthonia Oluwatosin Ajibade, Temiloluwa Iyanuoluwa Sunway University Dept of Computing and Information Systems Selangor Malaysia Istanbul Ticaret Univ Dept of Comp. Engineering Turkey University of Hail Department of Decoration and Interior Design Hail55467 Saudi Arabia Najran University Architectural Engineering Department Najran66426 Saudi Arabia Afe Babalola University Civil and Environmental Engineering Ekiti State Ado-Ekiti Nigeria Cebu Technological University College of Technology Cebu Philippines Cebu Technological University College of Engineering Cebu Philippines Federal University of Uberlandia Faculty of Architecture and Urban Design Brazil Scholar School System Dept of Business Management Birmingham United Kingdom

ISBN: (纸本)9798350358155

Solar energy could mitigate global warming and climate change. Solar energy faces economic, environmental, and technical challenges. Machine learning solves these technical issues. Despite several studies, machine learning in photovoltaics and solar energy is understudied. This study examines publishing patterns and bibliometrics to critically evaluate machine learning applications in photovoltaics and solar energy research. Scopus uses PRISMA. International publishing, citations, and collaboration are high. The Chinese Ministry of Education employs famous scholars like G. E. Georghiou and Haibo Ma. China is most active due to funding schemes like the National Natural Science Foundation and the National Key Research and Development Programme. This study examines publication patterns by country, institution, and funding organisation from 2014 to 2022, spanning topic categories and indicators. Examining author-keyword data to group publishing themes and identify influential journals. Increasing understanding of machine learning applications in photovoltaics and solar energy research. This project will examine the potential for significant development and the hurdles that must be overcome to leverage Cognitive computing's benefits in cancer and tumour research. In response to the rising amount of malware, phishing, and intrusion attacks on global energy and grid infrastructure, photovoltaic and solar energy system cybersecurity may be studied. © 2024 IEEE.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

A new resource index for tidal stream farm sitting in estuarine areas

A new resource index for tidal stream farm sitting in estuar...

引用

International Conference on Clean Electrical Power (ICCEP)

作者： D. M. Fouz R. Carballo I. López B. Álvarez G. Iglesias Departamento de Enxeñaría Agroforestal Universidade de Santiago de Compostela EPSE Lugo Spain School of Engineering Computing and Mathematics University of Plymouth Plymouth UK School of Engineering and Architecture & MaREI Environmental Research Institute University College Cork Cork Ireland

Tidal stream farm sitting in estuarine areas constitutes a complex and iterative process, which is usually subject to a large number of uncertainties. In order to shed light on the site selection procedure, it is necessary to make available reliable metrics and indicators to facilitate the decision-making. To this end, the new Hydrokinetic Energy (HE) index, based on the of the exploitable and reference energy resource concepts, is proposed and applied to a case study in the Shannon Estuary (W Ireland), illustrating its applicability to an informed tidal stream energy site selection.

关键词：

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：