检索结果-内蒙古大学图书馆

IEEE Workshop on High Performance Switching and Routing

作者： Marios Avgeris Meriem Mechennef Aris Leivadeas Ioannis Lambadaris Department of Systems and Computer Engineering Carleton University Ottawa Canada Department of Software and IT Engineering École de Technologie supérieure (ÉTS) Montréal Canada

In the 5G/6G era of networking, computational offloading, i.e., the act of transferring resource-intensive computational tasks to separate external devices in the network proximity, constitutes a paradigm shift for mobile task execution on Edge Computing infrastructures. However, in order to provide firm Quality of Service (QoS) assurances for all the involved users, meticulous planning of the offloading decisions should be made, which potentially involves inter-site task transferring. In this paper, we consider a multi-user, multi-site Multi-Access Edge Computing (MEC) infrastructure, where mobile devices (MDs) can offload their tasks to the available edge sites (ESs). Our goal is to minimize end-to-end delay and energy consumption, which constitute the sum cost of the considered system, and comply with the MDs’ application requirements. To this end, we introduce a two-stage Reinforcement Learning (RL)-based mechanism, where the MDs-to-ES task offloading and the ES-to-ES task transferring decisions are iteratively optimized. The proper operation, effectiveness and efficiency of our proposed offloading mechanism is assessed under various evaluation scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Modeling Functional Requirements From Tacit Knowledge

Towards Modeling Functional Requirements From Tacit Knowledg...

引用

computer Science, computer engineering, & Applied Computing (CSCE), Congress in

作者： Rameen Jafar Maram Fahaad Almufareh Sundas Ashraf Bushra Khan Wasi Haider Butt Mamoona Humayun Department of Computer and Software Engineering National University of Sciences and Technology Pakistan Department of Information Systems College of Computer and Information Sciences Jouf University Sakakah Saudi Arabia

Requirements Elicitation is the process of identifying system needs by talking with stakeholders who have a direct or indirect effect on the requirements. Requirements may be derived from several sources and are one of the most important phases of requirement engineering. We need to perform different elicitation techniques to find out the user's needs. Pre-requirements tracing is the process of determining the origins of a specific demand. Typically, certain needs arise that have no apparent source, but stakeholders will testify to their importance. Such criteria, however, are most likely dependent on tacit or tacit-like information entrenched in the issue domain. Tacit knowledge is one of the most common challenges for requirement analysts. This study contributes to constructing a systematic literature review for exploring multiple ways to model functional requirements using tacit knowledge. We have identified and analyzed 10 studies. In these research papers, different authors have discussed different methods to gather functional requirements from tacit knowledge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Digital Twining of Lithium-ion Battery Management systems: An Extended Kalman Filter for State-of-Charge Estimation in Cloud-platform

Towards Digital Twining of Lithium-ion Battery Management Sy...

引用

IEEE Energy Conversion Congress and Exposition, ECCE

作者： Dominic Karnehm Latha Anekal Akash Samanta Antje Neve Sheldon Williamson Institute of Intelligent Distributed Systems Bundeswehr University Munich Neubiberg Germany Electrical Computer and Software Engineering Ontario Tech University ON Canada

In practice, extended Kalman filter (EKF) is one of the most popular lithium-ion battery (LIB) state of charge (SOC) estimation algorithms in electric vehicles onboard battery management system (BMS). With the increasing necessity of off-loading the computational burden and data storage capacity of onboard BMS, the application of battery digital twin and cloud-BMS are getting popularity. Therefore, to assess the performance of EKF in terms of accuracy, the computational time, and overall request and execution time, an EKF-based SOC estimation method is developed in the cloud platform of Amazon Web Services (AWS). For a specific battery test data set, the cloud-based EKF demonstrated a mean absolute error of 0.00226 and a request time of 0.028s that are highly satisfactory towards developing a digital twin enabled cloud-based BMS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Image Deblurring based on Crosshatch Attention Adversarial Network and Hybrid Loss

Dynamic Image Deblurring based on Crosshatch Attention Adver...

引用

International Conference on Advancements in Computational Sciences (ICACS)

作者： Ummama Aslam Arslan Shaukat Basim Azam Dept. of Computer and Software Engineering College of Electrical and Mechanical Engineering (CEME) National University of Sciences and Technology (NUST) Islamabad Pakistan Institute of Integrated and Intelligent Systems Griffith University Brisbane Australia

Image deblurring techniques that uses deep learning have shown great potential but due to low generalizability, noise immunity and the correlation among different pixels is not addressed in detail that results in unwanted artifact that appears in the deblurred image. To tackle this problem an end-to-end approach is proposed for the recovery of sharp image from blurred one without the estimation of blur kernel. A special type of attention module known as crosshatch attention is used after Residual Block of Generator model for removing noise and for the collection of correlation of different pixels in an image. Hybrid Loss function is defined which focus on different part of image and improve edges and texture details. The performance of the model for deblurring is measured on GoPro dataset. Our proposed model has slightly higher objective and subjective evaluation i-e PSNR, SSIM value and the visual results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Security-Oriented Network Intent Placement using Particle Swarm Optimization

Security-Oriented Network Intent Placement using Particle Sw...

引用

Cyber Security in Networking Conference (CSNet)

作者： Gabriel Landeau Marios Avgeris Aris Leivadeas Ioannis Lambadaris Department of Software and IT Engineering École de technologie supérieure (ÉTS) Montréal Canada Department of Systems and Computer Engineering Carleton University Ottawa Canada

As the network infrastructure grows, its configuration and service provisioning become a tedious process. Accordingly, new paradigms have emerged, such as the Intent-Based Networking (IBN), that envision the automation of the network configuration, while minimizing the human intervention. Specifically, IBN allows users to interact with the network through high-level and declarative requests, called intents, which later can be translated into low-level configurations. IBN can entail different scopes and target network infrastructures, while being domain specific, which can create several challenges in terms of the final activation of the requested intents. To this end, in this paper, we mainly focus on intents that are expressing security and Quality of Service (QoS) network services demands that can be translated into Service Function Chains (SFC) and automatically deployed over a campus network. Our work and depending on the security level expressed in the intent, tries to optimally decide the level of multi-tenancy or complete segregation of the users' services that can be achieved, while satisfying the network provider's objectives. In particular, an artificial intelligence inspired algorithm called Particle Swarm Optimization (PSO) is modeled that automatically tries to find the best placement of the intents, while satisfying the security and QoS requirements of the users issuing the intents.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Realization and Performance Tests of a Dual-Polarization Fiber Optic Gyroscope 8

Realization and Performance Tests of a Dual-Polarization Fib...

引用

8th Symposium on Novel Photoelectronic Detection Technology and Applications

作者： Zhou, Tong Zhu, Lanxin Cao, Yuwen Chen, Yanjun Huang, Huimin Li, Zhengbin School of Software and Microelectronics Peking University Beijing102600 China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Engineering and Computer Science Peking University Beijing100871 China

ISBN: (数字)9781510653122

ISBN: (纸本)9781510653115

Interferometric fiber optical gyroscopes (IFOGs) have become one of the widely used sensors of inertial technology and rotational seismology, owing to their high precision and stability. In recent years, the dual-polarization IFOG, which allows two orthogonal polarization to work simultaneously, has been proved to achieve better measurement performance than the conventional minimum configuration through mutual compensation. In this work, a prototype of dual-polarization fiber-optic gyroscope is designed and realized. Laboratory tests show the self-noise has reached 9 nrad/s/sqrt(Hz) over the frequency from 0.01 to 125 Hz and the angular random walk has achieved 2.6×10-5 deg/sqrt(hr). For an Open-loop IFOG, which does not need a confiscated feedback control system, it avoids the dead-zone of closed-loop IFOG. However, limited by the measurement range, as a result of the periodic and nonlinear response of open-loop demodulation, the scale factor of open-loop IFOG varies around 100~1000 parts per million (ppm) conventionally, which hinders its detection accuracy. In this work, with new measurement extension and linearity compensation methods, the prototype achieves an outstanding precision with scale factor nonlinearity up to 5 ppm within ±10 deg/s, and shows the potential of dual-polarization IFOGs for rotational seismology. © 2022 SPIE

关键词： Seismology

来源：评论

学校读者我要写书评

暂无评论

Forecasting Breakdowns of Electric Motors of a Sugar Factory Using Machine Learning Methods 4

Forecasting Breakdowns of Electric Motors of a Sugar Factory...

引用

4th IEEE KhPI Week on Advanced Technology, KhPI Week 2023

作者： Zaiets, Nataliia Vlasenko, Lidiia Lutska, Nataliia Zhyltsov, Andrii Dept. of Automation and Robotic Systems National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine Dept. of Software Engineering and Cyber Security State University of Trade and Economics Kyiv Ukraine Dept. of Automation and Computer Technologies of Control Systems National University of Food Technologies Kyiv Ukraine Dept. of Electromagnetic Systems The Institute of Electrodynamics The National Academy of Sciences of Ukraine Kyiv Ukraine

ISBN: (纸本)9798350395532

The paper demonstrates the process of developing mathematical models for identifying breakdowns of electric motors using machine learning methods. The authors have developed three mathematical models for identifying breakdowns of electric drives with a power of 55 kW, 1500 rpm on the example of sugar production: model for quadratic discriminant analysis;binary classification decision tree;feedforward neural network model. The best structures and parameters of the models were determined by machine learning methods. The performance of the models on the training and test sets was more than 96% by F-score. It was proposed to use all three models independently for diagnosing breakdowns of electric drives, while the decision maker makes the final decision on the replacement or repair of electrical equipment. This approach is justified and effective because of the diversity of models. The developed models, except for assessing the state of the engine, can also be used for simulation modelling, forecasting, and serve as information support for process operators in organizing equipment maintenance. The availability of real-time information about the state of equipment in production will allow timely repair or replacement of equipment, thereby reducing the risks of stopping production and increasing the resource efficiency of technological processes. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Model Predictive Control for Automated Network Assurance in Intent-Based Networking enabled Service Function Chains

Model Predictive Control for Automated Network Assurance in ...

引用

IEEE Symposium on Network Operations and Management

作者： Marios Avgeris Aris Leivadeas Nikolaos Athanasopoulos Ioannis Lambadaris Matthias Falkner Department of Systems and Computer Engineering Carleton University Ottawa Canada Department of Software and IT Engineering Ácole de technologie supérieure Montreal Canada School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast UK Cisco Systems Ottawa Canada

Recent trends in Network Function Virtualization (NFV) combined with Internet of Things (IoT) and 5G applications have reshaped the network service offering. In particular, Service Function Chains (SFCs) can associate network functions with physical and virtual resources towards providing a complete network service. Concurrently, the management of a continuously expanding network and the fulfillment of the applications’ requirements pave the way for autonomic network solutions. Intent Based Networking (IBN) is a novel paradigm that aims to achieve the automatic orchestration of network services and the assurance of their performance. Accordingly, in this paper, we propose a novel automated network assurance model, based on Model Predictive Control, to guarantee the Quality of Service (QoS) and security requirements of multi-tenant and IBN-enabled SFCs. In this context, corrective decisions are proactively taken, in the form of incoming intent relocations among the SFCs. The results reveal that our model can assure with high probability the application requirements and minimize QoS violations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Silent Killer: Optimizing Backdoor Trigger Yields a Stealthy and Powerful Data Poisoning Attack

SSRN

引用

SSRN 2023年

作者： Lederer, Tzvi Maimon, Gallil Rokach, Lior Software and Information Systems Engineering Ben Gurion University Beer Sheva Israel Computer Science The Hebrew University of Jerusalem Jerusalem Israel

We propose a stealthy and powerful backdoor attack on neural networks based on data poisoning. In contrast to previous attacks, both the poison and the trigger in our method are stealthy. We are able to change the model’s classification of samples from a source class to a target class chosen by the attacker. We do so by using a small number of poisoned training samples with nearly imperceptible perturbations, without changing their labels. At inference time, we use a stealthy perturbation added to the attacked samples as a trigger. This perturbation is crafted as a universal adversarial perturbation (UAP), and the poison is crafted using gradient alignment coupled to this trigger. Our method is highly efficient in crafting time compared to previous methods and requires only a trained surrogate model without additional retraining. Our attack achieves state-of-the-art results in terms of attack success rate while maintaining high accuracy on clean samples. © 2023, The Authors. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

PD-Refiner: An Underlying Surface Inheritance Refiner with Adaptive Edge-Aware Supervision for Point Cloud Denoising 24

PD-Refiner: An Underlying Surface Inheritance Refiner with A...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhang, Chengwei Zhang, Xueyi Yue, Xianghu Lao, Mingrui Jiang, Tao Wang, Jiawei Zhang, Fubo Chen, Longyong National Key Laboratory of Microwave Imaging Aerospace Information Research Institute Chinese Academy of Sciences Beijing China Laboratory for Big Data and Decision National University of Defense Technology Hunan Changsha China Department of Electrical and Computer and Engineering National University of Singapore Singapore Singapore National Key Laboratory of Information Systems Engineering National University of Defense Technology Hunan Changsha China School of Software Engineering Tongji University Shanghai China

ISBN: (纸本)9798400706868

Point clouds from real-world scenarios inevitably contain complex noise, significantly impairing the accuracy of downstream tasks. To tackle this challenge, cascading encoder-decoder architecture has become a conventional technical route to iterative denoise. However, circularly feeding the output of denoiser as its input again involves the re-extraction of underlying surface, leading to unstable denoising process and over-smoothed geometric details. To address these issues, we propose a novel denoising paradigm dubbed PD-Refiner that employs a single encoder to model the underlying surface. Then, we leverage several lightweight hierarchical Underlying Surface Inheritance Refiners (USIRs) to inherit and strengthen it, thereby avoiding the re-extraction from the intermediate point cloud. Furthermore, we design adaptive edge-aware supervision to improve the edge awareness of the USIRs, allowing for the adjustment of the denoising preferences from global structure to local details. The results demonstrate that our method not only achieves state-of-the-art performance in terms of denoising stability and efficacy, but also enhances edge clarity and point cloud uniformity. © 2024 ACM.

关键词： edge-aware supervision

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：