检索结果-内蒙古大学图书馆

Collaborative learning-based inter-dependent task dispatching and co-location in an integrated edge computing system

引用

Digital Communications and Networks 2024年第6期10卷 1837-1850页

作者： Uchechukwu Awada Jiankang Zhang Sheng Chen Shuangzhi Li Shouyi Yang School of Software Henan Institute of Science and TechnologyXinxiang 453003China School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou 450001China Department of Computing and Informatics Bournemouth UniversityPoole BH125BBUK School of Electronics and Computer Science University of SouthamptonSouthampton SO171BJUK Faculty of Information Science and Engineering Ocean University of ChinaQingdao 266100China

Recently,several edge deployment types,such as on-premise edge clusters,Unmanned Aerial Vehicles(UAV)-attached edge devices,telecommunication base stations installed with edge clusters,etc.,are being deployed to enable faster response time for latency-sensitive *** fundamental problem is where and how to offload and schedule multi-dependent tasks so as to minimize their collective execution time and to achieve high resource *** approaches randomly dispatch tasks naively to available edge nodes without considering the resource demands of tasks,inter-dependencies of tasks and edge resource *** approaches can result in the longer waiting time for tasks due to insufficient resource availability or dependency support,as well as provider ***,we present Edge Colla,which is based on the integration of edge resources running across multi-edge *** Colla leverages learning techniques to intelligently dispatch multidependent tasks,and a variant bin-packing optimization method to co-locate these tasks firmly on available nodes to optimally utilize *** experiments on real-world datasets from Alibaba on task dependencies show that our approach can achieve optimal performance than the baseline schemes.

关键词： Edge computing Collaborative learning Resource utilization Execution time Edge federation Gang scheduling

来源：评论

学校读者我要写书评

暂无评论

ChatGPT-based Recommendations for Personalized Content Creation and Instructional Design with a Tailored Prompt Generator

ChatGPT-based Recommendations for Personalized Content Creat...

引用

Foundation and Large Language Models (FLLM), International Conference on

作者： Akrivi Krouska Christos Troussas Ioannis Voyiatzis Phivos Mylonas Cleo Sgouropoulou Department of Informatics and Computer Engineering University of West Attica Egaleo Greece

ISBN: (数字)9798350354799

ISBN: (纸本)9798350354805

Recent advancements in Artificial Intelligence (AI) have significantly influenced educational innovations, making learning environments more sophisticated with personalized learning, tailored feedback, and learning analytics. Among these advancements, Generative AI, namely ChatGPT, has emerged as a powerful tool in education. ChatGPT's ability to generate human-like content in real-time can assist educators with course design and educational material creation, allowing for enhanced instructional strategies without starting from scratch. Moreover, integrating ChatGPT into the recommendation process offers superior understanding of user needs and delivery of context-aware recommendations. In view of the above, this paper explores the integration of ChatGPT with a tailored prompt generator within an intelligent authoring system to offer effective recommendations for personalized content creation and instructional design. The system was evaluated and compared to its conversional version where instructors manually use ChatGPT. The findings indicate significant improvements in system usability, content quality, personalization, and time and effort savings, demonstrating the effectiveness of the proposed approach.

关键词： Technological innovation Authoring systems Large language models Education Learning (artificial intelligence) Chatbots Generators Real-time systems Usability Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Designing Secured Cafe Network with Security Awareness Domain and Resource (SADAR) by Simulation using Cisco Packet Tracer 22

Designing Secured Cafe Network with Security Awareness Domai...

引用

10th International Conference on computer and Communications Management, ICCCM 2022

作者： Lubis, Muharman Lubis, Arif Ridho Department of Information System Telkom University Indonesia Department of Computer Engineering and Informatics Politeknik Negeri Medan Indonesia

ISBN: (纸本)9781450396349

computer networking has a huge part of life today, which its participation not only in one side of life but in almost all aspects of life, especially in the fields of education, organization and business. The purpose of a computer network related to connecting every device for providing information and data services through the borderless concept of anytime, anywhere and anyone. On the other hand, the use of a network in the business sector is very critical and fundamental to assist the implementation in the respect of accelerate growth and reducing cost. In this case, the network in the cafe not only become the secondary service to the customer but also enable the business to be sustained, which many customers browse and utilize Internet during their visit, also cafe's effort to broaden the range of its business. Despite, the accessibility become widespread to the network, but at some point, the demand for Internet access in cafe such as for gaming, accompanying and streaming remain huge. Thus, this study want to design a computer network using the Cisco Packet Tracer software through the concept of SADAR (security awareness domain and resource) in order to increase security compliance. This study also utilized and configure VLAN and DHCP connected to gigabit Ethernet as standard, while the testing will used PING and TRACEROUTE in order for mapping as desired. © 2022 ACM.

关键词： Network management

来源：评论

学校读者我要写书评

暂无评论

Evaluating ChatGPT-driven Automated Test Generation for Personalized Programming Education

Evaluating ChatGPT-driven Automated Test Generation for Pers...

引用

Foundation and Large Language Models (FLLM), International Conference on

作者： Christos Troussas Christos Papakostas Akrivi Krouska Phivos Mylonas Cleo Sgouropoulou Department of Informatics and Computer Engineering University of West Attica Egaleo Greece

ISBN: (数字)9798350354799

ISBN: (纸本)9798350354805

Large Language Models (LLMs), such as ChatGPT, hold immense potential to irrevocably influence the dimension of educational technology by providing empowerment for personalized learning experiences. This paper covers the integration of ChatGPT into existing eLearning platforms toward supporting Java programming education. Using artificial intelligence-based capabilities of ChatGPT in natural language processing, our software enables instructors to generate individual module assessments tailored to a student's profile with unprecedented ease. Evaluation of the effectiveness and efficiency of the system was performed by a comprehensive review of the system, obtaining feedback from instructors and students, and analyzing test performance metrics. The evaluation showed that most teachers found the system very user friendly, with significant savings in time for test creation. Satisfaction related to personalized tests designed by ChatGPT was also adequate, and the average scores achieved on test cases set by ChatGPT were relatively high compared to those manually curated. Results underline the potential of ChatGPT-driven automated test generation for enhancing personalized programming education on eLearning platforms, making available tailored assessment, by consideration of individual needs of students, and increased learning outcomes and efficiency.

关键词： Java Electronic learning Accuracy Large language models Chatbots Question generation Software Test pattern generators Programming profession Testing

来源：评论

学校读者我要写书评

暂无评论

Distributed Denial of Service (DDoS) Mitigation: Security Awareness Domain and Resources (SADAR) 22

Distributed Denial of Service (DDoS) Mitigation: Security Aw...

引用

10th International Conference on computer and Communications Management, ICCCM 2022

作者： Hidayat, Taufik Safar Fadillah, Yoga Lubis, Muharman Lubis, Arif Ridho Department of Information System Telkom University Indonesia Department of Computer Engineering and Informatics Politeknik Negeri Medan Indonesia

ISBN: (纸本)9781450396349

Information security is a constantly evolving field to safeguard confidentiality, integrity and assets with defensive measures should be developed and planned to improve information security. Therefore, it is very important for a company to update its security system and defense techniques from attacks that occur. Furthermore, Distributed Denial of Service (DDoS) attack is a major threat that can disrupt and hinder legitimate service requests on a network. They were first reported in 1996 and until now the complexity and sophistication of these attacks is increasing, which are usually used to force a site or service to go offline, that is, by passing high data traffic until the server cannot work. Meanwhile, In August 2021, Microsoft claimed to have succeeded in overcoming the largest DDoS attack reaching 2 TBps. Moreover, with the increasing number of DDoS attacks, a mitigation scenario is needed to deal with the complexity and technical development of this DDoS. In the network world, detecting a DDoS somehow, is extremely difficult because the attempt should distinguish between normal traffic and DDoS attacks. Thus, some recommended security solutions will be compiled in this paper to deliver solution involving the mitigation. © 2022 ACM.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Improving Prediction of Need for Mechanical Ventilation using Cross-Attention 46

Improving Prediction of Need for Mechanical Ventilation usin...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Mohanty, Anwesh Shashikumar, Supreeth P. Lam, Jonathan Y. Nemati, Shamim University of California San Diego Department of Computer Science and Engineering La Jolla United States University of California San Diego Division of Biomedical Informatics La Jolla United States

ISBN: (纸本)9798350371499

In the intensive care unit, the capability to predict the need for mechanical ventilation (MV) facilitates more timely interventions to improve patient outcomes. Recent works have demonstrated good performance in this task utilizing machine learning models. This paper explores the novel application of a deep learning model with multi-head attention (FFNN-MHA) to make more accurate MV predictions and reduce false positives by learning personalized contextual information of individual patients. Utilizing the publicly available MIMIC-IV dataset, FFNN-MHA demonstrates an improvement of 0.0379 in AUC and a 17.8% decrease in false positives compared to baseline models such as feed-forward neural networks. Our results highlight the potential of the FFNN-MHA model as an effective tool for accurate prediction of the need for mechanical ventilation in critical care settings. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Personalized Hint Delivery in Multimedia Learning Environments Using Learning Styles: An Integrated Approach with Artificial Neural Networks and Weighted Sum Model

Personalized Hint Delivery in Multimedia Learning Environmen...

引用

International Workshop on Semantic Media Adaptation and Personalization (SMAP)

作者： Christos Troussas Akrivi Krouska Christos Papakostas Phivos Mylonas Cleo Sgouropoulou Department of Informatics and Computer Engineering University of West Attica Egaleo Greece

ISBN: (数字)9798331504502

ISBN: (纸本)9798331504519

This paper introduces a novel multimedia learning environment designed to support holistic learning of web development. ANNs and the WSM model have been adopted to implement the framework of the VARK learning style model in order to dynamically provide personalized educational hints that assist learners to overcome difficulties and deepen their understanding, thus acquiring a higher level of knowledge in a more general and effective way. In our approach, hints are not an adjunct but a core feature of the learning process, dynamically tailored to each learner in their time of need. An ANN combined with a WSM collaborates to achieve optimal delivery of these hints, ensuring they are timely and context-aware according to the learning styles of individual students defined by the VARK model. Students receive the best possible guidance to make learning much more effective. A structured questionnaire-based evaluation followed by statistical hypothesis testing showed promising results for the efficacy of this multimedia learning environment.

关键词： Adaptation models Computational modeling Learning (artificial intelligence) Artificial neural networks Educational technology Weighted sum model Testing Context modeling

来源：评论

学校读者我要写书评

暂无评论

Investigating the Role of Digital Escape Rooms in Enhancing Educational Outcomes through Game-Based Learning

Investigating the Role of Digital Escape Rooms in Enhancing ...

引用

South Eastern European Design Automation, computer engineering, computer Networks and Social Media Conference (SEEDA-CECNSM)

作者： Panagiota Zachari Christos Papakostas Christos Troussas Akrivi Krouska Phivos Mylonas Cleo Sgouropoulou Department of Informatics and Computer Engineering University of West Attica Egaleo Greece

ISBN: (数字)9798331504489

ISBN: (纸本)9798331504496

This research investigates the integration of a Digital Educational Escape Room in teaching fifth-grade history. The study explores how the Digital Educational Escape Room can enhance student engagement, collaboration, and learning outcomes. The game is designed to improve students’ understanding specifically of Justinian’s reign. It aligns with the Bloom’s taxonomy and involves six interactive puzzles that cater to various learning styles, including visual, auditory, and kinesthetic. The adapted evaluation framework assesses four critical dimensions: learning and training, system, user experience, and affective dimension. Forty-four fifth-grade students participated, engaging in the activities designed to improve their understanding of the history topic of Justinian’s reign. Results indicated significant improvements in students’ historical knowledge, critical thinking, and teamwork. Students reported high satisfaction levels and positive emotional engagement, despite encountering some technical issues. By integrating game-based learning with digital technology, digital escape rooms offer a promising alternative to traditional teaching methods, potentially transforming the educational experience for primary school students.

关键词： Training Visualization Social networking (online) Taxonomy Transforms Games User experience Teamwork History Noise level

来源：评论

学校读者我要写书评

暂无评论

How Lasers Exploit Photoacoustic and Photoelectric Phenomena to Inject Signals into MEMS Microphones

引用

Journal of Hardware and Systems Security 2025年 1-17页

作者： Cyr, Benjamin Sumaria, Vedant Long, Yan Tadigadapa, Srinivas Sugawara, Takeshi Fu, Kevin Computer Science and Engineering University of Michigan Ann Arbor USA Electrical & Computer Engineering Northeastern University Boston USA Department of Informatics The University of Electro-Communications Tokyo Japan

An amplitude-modulated laser can be used to generate false, yet coherent acoustic signals on the outputs of MEMS microphones. While this vulnerability has ramifications on the security of cyber-physical systems that trust these microphones, the physical explanation of this effect remained a mystery. Without an understanding of the physical phenomena contributing to this signal injection, it is difficult to design effective and reliable defenses. In this work, we show the degree to which the mechanisms of thermoelastic bending, thermal diffusion, and photocurrent generation are used to inject signals into MEMS microphones. We provide models for each of these mechanisms, develop a procedure to empirically determine their relative contributions, and highlight the effects on eight commercial MEMS microphones. We accomplish this with a precise setup to isolate each mechanism using several laser wavelengths and a vacuum chamber. The results indicate that the injected signal on the microphone is dependent on the wavelength of the incoming light. Shorter wavelengths (such as a 450 nm blue laser) exploit photoacoustic effects, and the periodic heating and expansion of air is the dominant factor in seven of eight sample microphones. Longer wavelengths (such as a 904 nm infrared laser) exploit photoelectric effects on the sensitive ASIC, generating signals that are between 2x and 100x stronger than photoacoustic signals in six of eight sample microphones. This understanding of the physical causality of laser signal injection leads to recommendations for future laser-resistant microphone designs. These include adding light-blocking structures at the system or device level, improving to glob top application, and adding simple light or temperature sensors for injection detection. Based on the fundamental causality, we also suggest potential vulnerabilities within other sensors with similar characteristics to MEMS microphones, such as conventional microphones, ultrasonic

关键词：

来源：评论

学校读者我要写书评

暂无评论

Circumstance Evaluation Using Extreme Value Analysis on Charging Station Data: The Case of DEI Blue in Greece 14th

Circumstance Evaluation Using Extreme Value Analysis on Cha...

引用

14th International Conference on Information, Intelligence, Systems, and Applications, IISA 2023

作者： Panagoulias, Dimitrios P. Sarmas, Elissaios Marinakis, Vangelis Tsihrintzis, George A. Department of Informatics University of Piraeus Piraeus18534 Greece Decision Support Systems Lab School of Electrical and Computer Engineering National Technical University of Athens Zografou-Athens15773 Greece

ISBN: (纸本)9783031674259

We apply Extreme Value Analysis on sets of Electric Vehicle (EV) charging data with the goal to extract indications in the data of future trends in the demand for EV charging. The datasets have been provided by DEI blue, a service designed to provide integrated e-mobility solutions to individuals, companies and public administration throughout Greece. Eventhough the data are limited as they have been collected during a period of only twelve months, our analysis still reveals trends in the data highlighting a probable seasonality. The seasonality is observed during periods of extreme heat, regional population mobility and incoming visitors. These occurrences impact technical aspects of battery efficiency, grid capacity and a shift of behavioural usage patterns. Our findings cannot be ignored by policy makers as they are expected to intensify in the years to come due to the fast-rising number of EVs in use. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Electrification

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：