检索结果-内蒙古大学图书馆

28th European Wireless Conference, EW 2023

作者： Nunavath, Nikhitha Garbugli, Andrea Nande, Swaraj Shekhar Foschini, Luca Bassoli, Riccardo Fitzek, Frank H.P. The Deutsche Telekom Institute of Communication Technology Faculty of Electrical and Computer Engineering Technische Universität Dresden Dresden Germany Cluster of Excellence Dresden Germany research group Technische Universität Dresden Dresden Germany The Department of Computer Science and Engineering University of Bologna Italy

ISBN: (纸本)9783800762262

In the context of 6G architecture development, the concept of a softwarized (orchestration) continuum is a key pillar. Nevertheless, achieving complete softwarization of network functionalities, tasks, and operations presents inherent challenges, leading to critical trade-offs and limitations. This article explores a novel approach to address these issues by integrating quantum technologies and the Physical Layer Service Integration (PLSI) paradigm. Specifically, we propose the formulation and analysis of network synchronization as a quantum PLSI problem. Our study evaluates synchronization time offset in both conventional Precision Time Protocol (PTP) and quantum-based approaches within the network. We investigate the impact of various network conditions on the precision of PTP synchronization, ranging from nanoseconds under ideal circumstances to microseconds when utilizing virtual network devices. Further, we perform a simulation to generate frequency-entangled photon pairs to access nonlocal temporal correlations and calculate the time offsets. Our findings reveal that entanglement-based PLSI for network synchronization achieves precision at the picosecond level. These results emphasises the high precision achievable by interpreting the network synchronisation problem in the perspective of PLSI and not as a service of the softwarized continuum. © VDE VERLAG GMBH - Berlin - Offenbach.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

A Low Complexity ML-Based Methods for Malware Classification

引用

computers, Materials & Continua 2024年第9期80卷 4833-4857页

作者： Mahmoud E.Farfoura Ahmad Alkhatib Deema Mohammed Alsekait Mohammad Alshinwan Sahar A.El-Rahman Didi Rosiyadi Diaa Salama Abd Elminaam Cybersecurity Department Al-Zaytoonah University of JordanAmman11733Jordan Department of Computer Science and Information Technology Applied CollegePrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Faculty of Information Technology Applied Science Private UniversityAmman11931Jordan Computer Systems Program-Electrical Engineering Department Faculty of Engineering-ShoubraBenha UniversityCairo11629Egypt Research Center for Artificial Intelligence and Cybersecurity Electronics and Informatics OrganizationNational Research and Innovation Agency(BRIN)KST Samaun SamadikunBandung40135Republic of Indonesia Jadara Research Center Jadara UniversityIrbid21110Jordan MEU Research Unit Middle East UniversityAmman11831Jordan

The article describes a new method for malware classification,based on a Machine Learning(ML)model architecture specifically designed for malware detection,enabling real-time and accurate malware *** an innovative feature dimensionality reduction technique called the Interpolation-based Feature Dimensionality Reduction Technique(IFDRT),the authors have significantly reduced the feature space while retaining critical information necessary for malware *** technique optimizes the model’s performance and reduces computational *** proposed method is demonstrated by applying it to the BODMAS malware dataset,which contains 57,293 malware samples and 77,142 benign samples,each with a 2381-feature *** the IFDRT method,the dataset is transformed,reducing the number of features while maintaining essential data for accurate *** evaluation results show outstanding performance,with an F1 score of 0.984 and a high accuracy of 98.5%using only two reduced *** demonstrates the method’s ability to classify malware samples accurately while minimizing processing *** method allows for improving computational efficiency by reducing the feature space,which decreases the memory and time requirements for training and *** new method’s effectiveness is confirmed by the calculations,which indicate significant improvements in malware classification accuracy and *** research results enhance existing malware detection techniques and can be applied in various cybersecurity applications,including real-timemalware detection on resource-constrained *** and scientific contribution lie in the development of the IFDRT method,which provides a robust and efficient solution for feature reduction in ML-based malware classification,paving the way for more effective and scalable cybersecurity measures.

关键词： Malware detection ML-based models dimensionality reduction feature engineering

来源：评论

学校读者我要写书评

暂无评论

Instance segmentation based precise object detection in UAV Images using Mask R-CNN

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2023年第6期7卷 12-19页

作者： Kumar, R. Senthil Barnwal, Rajesh P. Department of Computer Science with Cognitive Systems Dr. N.G.P. Arts and Science College Coimbatore India Information Technology Group CSIR-Central Mechanical Engineering Research Institute Durgapur India

Object detection plays a vital role in remote-sensing datasets which trains the image or things and helps in classifying the images into their classes. Instance segmentation is the avant-garde technique used for object detection in Deep Learning. There are many instance segmentation models which can produce significant results. Object detection, segmentation, and RGB analysis in images taken from Unmanned Aerial Vehicles (UAV) are difficult with the desired level of performance. Instance segmentation is a powerful method that extracts each object and its location with the predicted label for pixels in the input image. In this paper, a study has been carried out on the implementation of Mask R-CNN for instance segmentation with different optimization algorithms to obtain a more accurate result for UAV images. The training has been carried out with Mask R-CNN for object detection using ResNet50 and ResNet101 as the backbone. After extensive experiments, it has been observed that the optimization algorithm plays a vital role in the overall computational process and can improve the accuracy level with a reduction in the training/validation loss. The experiment has been conducted on publicly available UAV datasets. The paper further presents the results in terms of different performance parameters © 2023, International Journal of Systematic Innovation. All Rights Reserved.

关键词： Deep learning Instance Segmentation Mask R-CNN Optimization algorithm UAV Images

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of the Impact of Using Oriented Steel in Proportion to Segmentation on Core Loss of AC Electric Machine Stator

Experimental Evaluation of the Impact of Using Oriented Stee...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Khoshoo, Bhuvan Aggarwal, Anmol Agapiou, John Foster, Shanelle N. Michigan State University Department of Electrical & Computer Engineering East LansingMI United States General Motors PontiacMI United States General Motors Manufacturing Systems Research Laboratory WarrenMI United States

ISBN: (纸本)9798350376067

The strategic incorporation of oriented steel in a segmented stator AC electric machine has the potential to enhance machine performance by reducing core losses compared to a machine designed with non-oriented steel. However, the introduction of cut-edges and the stress on individual segments resulting from segmented stator construction may have unintended consequences. Despite several attempts to assess the impact of cut-edges or oriented steel on core losses in segmented stators, the literature lacks an analysis of the loss separation between tooth and back-iron components using manufactured stators. This gap in understanding prevents a comprehensive assessment of the true impact of using oriented steel in segmented stator construction for core loss improvement. In this work, the loss of each tooth and back-iron segment is calculated by conducting experiments with three different electromagnetic devices, specifically H-shaped steel laminations. By comparing the results from three manufactured stators, we elucidate the influence of oriented steel in proportion to the segmented stator construction. © 2024 IEEE.

关键词： Stators

来源：评论

学校读者我要写书评

暂无评论

Wind Turbines Analysis and Analytics of Power Generation by using Long Short Term Memory 5

Wind Turbines Analysis and Analytics of Power Generation by ...

引用

5th International Youth Conference on Radio Electronics, electrical and Power engineering, REEPE 2023

作者： Nagy, Shady A. Yousef, Ziad O. Tolba, Mohamed A. German University Faculty of Engineering Mathematics Department Cairo Egypt Fayoum University Faculty of Engineering Computer and Systems Department Fayoum Egypt National Research University MPEI Electrical Power Systems Department Moscow Russia Egyptian Atomic Energy Authority Nuclear Research Center Reactors Department Cairo Egypt

ISBN: (纸本)9798350399523

In this paper, the study of the behavior of wind turbines and its power generation in Germany that an important source for renewable energy is investigated. This work develops a deep learning recurrent neural model that depends on time series modeling to predict the power generation of wind turbines (WT) in every ten mins in a daily basis, and seasonal behavior. The proposed model uses previous historical power data from the turbines and the dependency of short-term points and long-term behavior that common in time series with its probabilistic behavior. However, WT power generation depends on wind speed, torque, gearbox state, temperature that are highly correlated to power generated and WT state in generation, but time series modeling uses the historical previous power generated only to forecast the future behavior that behaves in a pattern similar to the previous corresponding time frame. The comprehensive analysis is implemented to evaluate the suggested model with previous data and then forecast the power generated in the last months of the year. © 2023 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Site-Specific Ultra-Low-Sidelobe Phased Array Topologies for Sparse Areas of Particular Shape 52

Site-Specific Ultra-Low-Sidelobe Phased Array Topologies for...

引用

52nd European Microwave Conference, EuMC 2022

作者： Aslan, Yanki Delft University of Technology Microwave Sensing Signals and Systems Group Faculty of Electrical Engineering Mathematics and Computer Science Department of Microelectronics Delft Netherlands

ISBN: (数字)9782874870699

ISBN: (纸本)9782874870699

Optimal design of uniformly-fed aperiodic millimeter-wave phased array topologies for site-specific and quasi interference-free operation is presented. Several use cases with different number of line-of-sight cells in the close vicinity of the base station, and for various widths and shapes of the cells, are analyzed. The arrays are synthesized by applying an iterative convex optimization technique. The simulation results of 256-element arrays indicate strong intra-cell and inter-cell isolation with around -40 dB maximal side lobe level. The proposed technique is found to be especially useful in the application scenarios supporting sparsely distributed narrow communication cells. © 2022 European Microwave Association (EuMA).

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Learning Using Nonlinear Dependence

arXiv

引用

arXiv 2025年

作者： Sepanj, M. Hadi Ghojogh, Benyamin Fieguth, Paul Vision and Image Processing Group Systems Design Engineering University of Waterloo ON Canada Department of Electrical and Computer Engineering University of Waterloo ON Canada

Self-supervised learning has gained significant attention in contemporary applications, particularly due to the scarcity of labeled data. While existing SSL methodologies primarily address feature variance and linear correlations, they often neglect the intricate relations between samples and the nonlinear dependencies inherent in complex data. In this paper, we introduce Correlation-Dependence Self-Supervised Learning (CDSSL), a novel framework that unifies and extends existing SSL paradigms by integrating both linear correlations and nonlinear dependencies, encapsulating sample-wise and feature-wise interactions. Our approach incorporates the Hilbert-Schmidt Independence Criterion (HSIC) to robustly capture nonlinear dependencies within a Reproducing Kernel Hilbert Space, enriching representation learning. Experimental evaluations on diverse benchmarks demonstrate the efficacy of CDSSL in improving representation quality. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Android-Based Visualization of Vehicle Trip Data for Accident Reconstruction

Android-Based Visualization of Vehicle Trip Data for Acciden...

引用

International Conference on electrical engineering and Informatics (ICELTICs)

作者： Ahmad Mufadhdhal Alkifani Maya Fitria Muhammad Daffa Adrian Sitorus T. Muhammad Caesar Maulana Humaira Rahmad Dawood Department of Electrical and Computer Engineering Universitas Syiah Kuala Interactive Intelligent Systems Research Group Universitas Syiah Kuala Banda Aceh Indonesia

ISBN: (数字)9798350366822

ISBN: (纸本)9798350366839

Vehicle traffic accident investigations often depend on eyewitness testimony, which can be unreliable, especially in remote areas where no closed circuit television (CCTV) footage is available. A mobile data logger was developed, equipped with a range of sensors, including an accelerometer and gyroscope, to collect and store data related to vehicle movements. An additional Flutter-driven program was developed to extract and visualize data from the mobile logger, and thus improve the accuracy of accident detection and allow incidents to be rebuilt. These programs were subjected to black-box testing, which produced results consistent with the anticipated outcomes for both the recording and data visualization tests. The data visualization application was subjected to testing using the system usability scale (SUS) technique and obtained a score of 89.5, corresponding to an A grade, the highest possible score of the 5 grade levels.

关键词： Visualization Data visualization Closed box Recording Sensors Gyroscopes Usability Vehicle dynamics Accidents Testing

来源：评论

学校读者我要写书评

暂无评论

Co-Sense: Internet of Things Multi-Sensor Vehicle Trip Data Recorder

Co-Sense: Internet of Things Multi-Sensor Vehicle Trip Data ...

引用

International Conference on Informatics and Computing (ICIC)

作者： Muhammad Daffa Adrian Sitorus T. Muhammad Caesar Maulana Humaira Maya Fitria Ahmad Mufadhdhal Alkifani Rahmad Dawood Department of Electrical and Computer Engineering Universitas Syiah Kuala Interactive Intelligent Systems Research Group Universitas Syiah Kuala Banda Aceh Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

Accident identification requires a detailed account of an accident and its cause. These accounts are typically based on unreliable eyewitness testimony. The Co-Sense system, designed to improve analysis of accidents, records vehicle data including tilt, location, speed, and distance information to an object using GPS, gyroscope, and ultrasonic sensors. With an ESP32 microcontroller and a Raspberry Pi 4, Co-Sense is an Internet of Things system that expands on earlier research by adopting an alternative connectivity method, enhancing scalability, using an alternative data acquisition procedure, integrating with external platforms, and enhancing system usability. The results of a field test indicate that Co-Sense efficiently records information, stores it, and transmits it to a mobile phone. The gyroscope, ultrasonic sensor, and GPS module exhibit error rates of 0.85%, 1.82%, and 10.12%, respectively, when detecting vehicle speed.

关键词： Microcontrollers Acoustics Sensor systems Mobile handsets Sensors Gyroscopes Internet of Things Accidents Global Positioning System Automotive engineering

来源：评论

学校读者我要写书评

暂无评论

Opportunities, Progress and Challenges in Active Heatsink Antenna Arrays for 5G and Beyond 52

Opportunities, Progress and Challenges in Active Heatsink An...

引用

52nd European Microwave Conference, EuMC 2022

ISBN: (数字)9782874870699

ISBN: (纸本)9782874870699

The conventional air and liquid cooling based thermal management strategies in mm-wave active phased arrays are illustrated with several examples from the literature. The key role of antenna engineers in electronics thermal management is discussed. The intriguing concept of using the antennas as auxiliary heat dissipators is recapitulated with a focus on the past and recent developments. The multiphysics (electromagnetic and thermal) modeling and design approaches of such dual function antennas are outlined. Some of the future multidisciplinary research challenges in heatsink antennas are identified. © 2022 European Microwave Association (EuMA).

关键词： Millimeter waves

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：