检索结果-内蒙古大学图书馆

6G Networking (6GNet), International Conference on

作者： Nurefş an Sertbaş Bü lbü l Orhan Ermis Ş erif Bahtiyar M. Ufuk Ç ağ layan Fatih Alagö z Dept. of Computer Science Universit&#x00E4 t Hamburg Germany IT for Innovative Services LIST Luxembourg Dept. of Computer Eng. Istanbul Technical University Turkey Dept. of Computer Eng. Yasar University Turkey Dept. of Computer Eng. Bogazici University Turkey

Software Defined Networking (SDN) paradigm is the redefinition of conventional networks based on the use of programmable entities together with a clear separation between the data plane and the control plane. The idea behind this new paradigm is to achieve a more flexible network architecture and better management capabilities. However, with all these advantages, it has been experienced that SDNs are open to new security threats and unfortunately, current technologies are not mature enough to overcome those vulnerabilities. As an example, we can consider the detection of the compromised switches in the network. Since switches are programmable entities, in SDN, they are the potential targets for attackers. When a switch is compromised, the attacker can use this switch to deploy incorrect packet forwarding and unsubstantiated packet dropping attacks. Current SDN protocols are not able to detect such kinds of attacks in the network and hence the whole network traffic can be affected in the end. One particular assumption is to use an approach that reflects the trust level of switches in the network for the detection of a compromised one. Therefore, in this paper, we propose Trust Enhanced Security (TES) for routing in SDN. The proposed approach provides three different trust computations to find the most suitable trust level for different states of a network. To show the applicability of the proposed approach, we demonstrate a set of simulations based on the detection of compromised switches. Simulation results show that the proposed model operates effectively to detect and eliminate compromised nodes while selec.ing secure paths.

关键词： 6G mobile communication Protocols Computational modeling Simulation Telec.mmunication traffic Network architecture Routing

来源：评论

学校读者我要写书评

暂无评论

A Framework for Digital Twin Collaboration 24

A Framework for Digital Twin Collaboration

引用

Proceedings of the Winter Simulation Conference

作者： Zheng.hang Hua Karim Djemame Nikos Tziritas Georgios Theodoropoulos Dept. of Computer Science and Eng. Southern University of Science and Technology (SUSTech) Shenzhen CHINA and School of Computing University of Leeds Leeds UK School of Computing University of Leeds Leeds UK Dept. of Informatics and Telecommunications University of Thessaly Lamia GREECE Research Institute of Trustworthy Autonomous Systems (RITAS) SUSTech Shenzhen CHINA and Dept. of Computer Science and Eng. Southern University of Science and Technology (SUSTech) Shenzhen CHINA

ISBN: (纸本)9798331534202

Digital Twins (DTs) have emerged as a powerful tool for modeling Large Complex Systems (LCSs). Their streng.h lies in the detailed virtual models that enable accurate predictions, presenting challeng.s in traditionally centralized approaches due to the immense scale and decentralized ownership of LCSs. This paper proposes a framework that leverages the prevalence of individual DTs within LCSs. By facilitating the exchange of decisions and predictions, this framework fosters collaboration among autonomous DTs, enhancing performance. Additionally, a trust-based mechanism is introduced to improve system robustness against poor decision-making within the collaborative network. The framework's effectiveness is demonstrated in a virtual power plant (VPP) scenario. The evaluation results confirm the system's objectives across various test cases and show scalability for large deployments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cancer Death Cases Forecasting using Supervised Machine Learning 4

Cancer Death Cases Forecasting using Supervised Machine Lear...

引用

4th International Conference on elec.ronics and Sustainable Communication Systems, ICESC 2023

作者： Degadwala, Sheshang Vyas, Dhairya Kothari, Ankita Khunt, Urmila Sigma University Computer Engineering Department Gujarat Vadodara India University of Baroda The Maharaja Sayajirao Gujarat Vadodara India Krishna School of Emerging Technology and Applied Research Kpgu Dept. of Comp. Sci. & Eng. Vadodara India Itm Vocational University Computer Science Engineering Vadodara India

ISBN: (纸本)9798350300093

In India, like in the rest of the world, cancer is a major killer. This research objective is to predict cancer mortality in India, using supervised machine learning methods. Cancer mortality rates in India between 1990 and 2017 are provided by age group, gender, and region using data from the Global Burden of Disease Study. We employ three distinct supervised learning algorithms - linear regression, decision tree regression, and random forest regression - after performing data preprocessing, which includes missing value imputation and feature eng.neering. Using a variety of criteria, we analyze the effectiveness of these models and conclude that the random forest regression model is superior to the other two. The scope of research is provide a long-term prediction of cancer mortality in India using the best model so it will help health department to work on it. Our research has implications for policymakers and healthcare providers in India, where it may inform efforts to reduce cancer rates and improve cancer care. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Machine Learning Methods for Diagnosing Autism Spectrum Disorder Using Multimodal Data: A Survey

Unsupervised Machine Learning Methods for Diagnosing Autism ...

引用

International Conference on Computational science and Computational Intelligence (CSCI)

作者： Antika Roy Pablo Rivas Mahee Noor Tayba Dept. of Computer Science School of Eng. and Computer Science Baylor University Department of Computer Science Baylor University

The neurodevelopmental disorder known as autism spectrum disorder (ASD) is becoming increasingly pervasive worldwide. It can be categorized when a person struggles to interact and communicate socially and also exhibits repetitious behaviors and interests. Although early intervention is crucial and may have long-term advantages in the lives of people with ASD, diagnosing ASD is difficult due to its heterogeneous characteristics and a large number of data from various aspects such as genetic, behavioral, elec.ronic health records, and many other domains. This review paper offers an in-dept. assessment of papers that use the most commonly used unsupervised machine learning techniques in ASD, such as “k-means clustering” and “Hierarchical clustering.” This research aims to identify and highlight the most recent unsupervised machine learning advances in the ASD literature while also attempting to highlight the significant contributions and limits of the selec.ed works to provide insight for future researchers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling Lunar Surface Charging Using Physics-Informed Neural Networks

Modeling Lunar Surface Charging Using Physics-Informed Neura...

引用

IEEE International Conference on Big Data

作者： Niloofar Zendehdel Adib Mosharrof Katherine Delgado Daoru Han Xin Liang Tong Shu Mechanical & Aerospace Eng. Dept. Missouri University of Science & Technology Rolla USA Dept. of Computer Science University of Kentucky Lexington USA Mechanical & Aerospace Engr. Dept. Missouri University of Science & Technology Rolla USA Dept. of Computer Science & Engr. University of North Texas Denton USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Modeling the elec.ric potential profile above the lunar surface is critical for understanding surface charging and interactions with the space environment. Traditional methods like Particle-in-Cell (PIC) simulations are highly accurate but computationally expensive. To address this, we propose a hybrid approach using a Multi-Layer Perceptron (MLP) architecture in both data-driven neural networks and Physics-Informed Neural Networks (PINNs). The PINN component incorporates physical laws directly into the training process, ensuring physical consistency, while the data-driven component captures complex patterns. This combination offers a significant reduction in computational cost compared to PIC methods while maintaining high modeling accuracy. Our results show that the proposed method effectively represents the elec.ric potential profile above the lunar surface, even with limited data.

关键词： elec.ric potential Accuracy Uncertainty Computational modeling Neural networks Moon computer architecture Surface charging Data models Context modeling

来源：评论

学校读者我要写书评

暂无评论

Advanced Solar Power Forecasting: A Hybrid/Ensemble Approach Utilizing Geographic and Meteorological Data

Advanced Solar Power Forecasting: A Hybrid/Ensemble Approach...

引用

Simulation Winter Conference

作者： Mahdi Darvishi Abdolreza Abhari Fac. of Eng. and Architectural Scie. Toronto Metropolitan University Toronto ON CANADA Dept. of Computer Science Eng Toronto Metropolitan University Toronto ON CANADA

ISBN: (数字)9798331534202

ISBN: (纸本)9798331534219

Photovoltaic (PV) systems are pivotal in the global energy transition, where accurate solar power forecasting is critical. Traditional forecasting has leaned heavily on solar irradiance data, yet such reliance carries inherent uncertainties and measurement complexities, presenting significant forecasting challeng.s. This paper introduces a novel hybrid/ensemble model that reduces dependence on solar irradiance data, utilizing geographic, meteorological, and temporal data to predict solar power output. Combining the streng.hs of XGBoost and LightGBM algorithms through a linear regression meta-model, our approach demonstrates improved prediction accuracy, evidenced by a mean absolute error (MAE) of 0.033, and an R-squared value of 0.693. This study advances solar power forecasting, enhancing PV system efficiency, and reliability, and promoting sustainable energy investments.

关键词： Training Solar irradiance Analytical models Adaptation models Accuracy Uncertainty Linear regression Predictive models Reliability Forecasting

来源：评论

学校读者我要写书评

暂无评论

Elasticity Measurements of Expanded Foams using a Collaborative Robotic Arm

arXiv

引用

arXiv 2023年

作者： Beber, Luca Lamon, Edoardo Palopoli, Luigi Fambri, Luca Saveriano, Matteo Fontanelli, Daniele Dept. of Eng. and Computer Science University of Trento Trento Italy Dept. of Industrial Engineering University of Trento Trento Italy

Medical applications of robots are increasingly popular to objectivise and speed up the execution of several types of diagnostic and therapeutic interventions. Particularly important is a class of diagnostic activities that require physical contact between the robotic tool and the human body, such as palpation examinations and ultrasound scans. The practical application of these techniques can greatly benefit from an accurate estimation of the biomechanical properties of the patient's tissues. In this paper, we evaluate the accuracy and precision of a robotic device used for medical purposes in estimating the elastic parameters of different materials. The measurements are evaluated against a ground truth consisting of a set of expanded foam specimens with different elasticity that are characterised using a high-precision device. The experimental results in terms of precision are comparable with the ground truth and suggest future ambitious developments. Copyright © 2023, The Authors. All rights reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

WIP: (Almost) Anywhere Virtual Computing Learning Environment: Student Technology Acceptance

WIP: (Almost) Anywhere Virtual Computing Learning Environmen...

引用

Frontiers in Education (FIE) Conference

作者： Patrick Seeling Michael P. McGarry Department of Computer Science Central Michigan University Mount Pleasant MI USA Dept. of Electrical and Computer Eng. University of Texas at El Paso El Paso TX USA

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This work in progress innovative practice paper details our open source approach, which directly addresses new challeng.s to equitable access and privacy originating from increased technology-driven learning. We provide results from the Technology Acceptance Model's anonymous survey approach for a second-year introductory networking and a fourth-year operating systems course that employed the environment with comparable respondent characteristics. Although perceived ease of use and perceived use are in the middle of possible ranges, we find an interesting reversal for the network course, where student attitudes are low despite high perceptions. Future work will be directed at further refinements of the framework and a more in-dept. evaluation of the privacy concerns that students might have and whether these could be included in the Technology Accentance Model.

关键词： Surveys Privacy Data privacy Technology acceptance model Operating systems Computational modeling Data models

来源：评论

学校读者我要写书评

暂无评论

WIP: From Passive to Passionate: Using Genuine Projects to Motivate Students

WIP: From Passive to Passionate: Using Genuine Projects to M...

引用

Frontiers in Education (FIE) Conference

作者： Michael P. McGarry Patrick Seeling Dept. of Electrical and Computer Eng. University of Texas at El Paso El Paso TX USA Department of Computer Science Central Michigan University Mount Pleasant MI USA

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This innovative practice WIP paper presents our work to increase student motivation and eng.gement using real-world projects. Specifically, we assigned final projects to students that came from a genuine need from our research program on campus. The team projects were assigned in a networking course offered to undergraduate and graduate students. Anecdotally, the students seemed more motivated to complete the projects because they knew the requested designs were novel and provided local utility. Student performance toward project completion was, anecdotally, exceptional compared to traditional projects. We surveyed students to assess their perceptions of their mo-tivation and subsequent eng.gement. The survey results suggest that the students perceived what we also perceived: students had more motivation from these types of projects than the typical contrived recycled projects typically assigned. In this paper, we provide the details behind these projects, how we managed the students to complete them, how we attempted to make the process mirror a commercial environment, and analyze the results of the student survey data. We also outline our experimental design to be executed in future course offerings to better understand how student motivation and eng.gement is affected by these types of projects in comparison with typical contrived recycled projects. Lastly, we outline how we intend to scale up across campuses and to create an experiential learning environment outside of formal course work.

关键词： Surveys Heuristic algorithms Mirrors Particle swarm optimization Logistics

来源：评论

学校读者我要写书评

暂无评论

WIP: Evolution of a Networking Course - Attitude Changes a Decade and a Pandemic Later

WIP: Evolution of a Networking Course - Attitude Changes a D...

引用

Frontiers in Education (FIE) Conference

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This work in progress research paper describes the findings of an anonymous survey modeled after the persistence in eng.neering survey instrument that we conducted a decade apart in 2014 and 2024. Significant changes in the mid-2010s to the mid-2020s have altered course delivery and resulting student perceptions, and we find statistically significant differences for program persistence, student self-perceived performance, perceived course value, course enjoyment, self-perceived learning gains, and self-perceived learning material eng.gement efforts. Interestingly, we did not find significant differences between the two groups with respect to self-reported time spent on different course activities or general student population characteristics, such as self-reported credits, GPA, work hours, or commutes. When considering the averaged changes, we note that students in the more recent blended and virtualized environments exhibit a higher level of persistence than their peers. This showcases the overall increase of blended and decentralized/virtualized instruction having a positive impact on student attitudes based on the feedback collected.

关键词： Surveys Pandemics Instruments Active learning Position measurement Market research

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：