检索结果-内蒙古大学图书馆

2024 IEEE PES Innovative Smart Grid Technologies Europe Conference, ISGT EUROPE 2024

作者： Ascher, Dominik Albayrak, Sahin Technical University of Berlin Faculty of Electrical Engineering and Computer Science Berlin10587 Germany

ISBN: (纸本)9789531842976

Distributed energy resources (DER), renewable energy sources (RES) and electric vehicles (EV) pose considerable challenges with respect to their efficient integration within the power system. Operation and control strategies for energy management systems (EMS) and charging station management systems (CSMS) are required to be highly adaptable and able to rapidly incorporate information received about power system supplies and demands to maintain efficient system operation. Here, information integration and monitoring is particularly crucial in use cases such as smart charging of EV and vehicle-to-grid (V2G) interactions. For this, standardization is a key challenge, as communication standards such as OCPP and EEBus facilitate interoperability, as well as monitoring and controlling aligned devices using shared data models and protocols. In this work, a data-driven architecture for integrated and adaptive charging and energy management is presented, which allows for mapping of logical system states and actions to concrete protocol data models. Based on actual and predicted information received with respect to system state, control strategies can be derived and adapted during run-time to address changed system requirements, behavior or system topologies of DER and charging stations (CS). © 2024 IEEE.

关键词： data-driven architecture energy management ICT smart charging

来源：评论

学校读者我要写书评

暂无评论

RobustFace: a novel image restoration technique for face adversarial robustness improvement

引用

Multimedia Tools and Applications 2025年第11期84卷 8965-8993页

作者： Sadu, Chiranjeevi Das, Pradip K. Yannam, V Ramanjaneyulu Nayyar, Anand Department of Computer Science and Engineering RGUKT Nuzvid Andhra Pradesh Nuzvid India Department of Computer Science and Engineering IIT Guwahati Assam Guwahati India School of Technology Woxsen University Telangana Hyderabad India Graduate School Faculty of Information Technology Duy Tan University Da Nang550000 Viet Nam

Machine Learning (ML) models, particularly Deep Learning (DL), have made rapid progress and achieved significant milestones across various applications, including numerous safety-critical contexts. However, these models have recently been discovered to be susceptible to adversarial attacks, which are well-crafted input images. The primary objective of this paper is to propose a novel methodology titled "RobustFace", which is based on deep image restoration networks, that significantly improves the facial adversarial robustness of various image-classification models. Adversarial images are created using the Private Fast Gradient Sign Method (P-FGSM), StyleGAN and Fast Landmark Manipulation (FLM) methods. The adversarial images are then enhanced using deep image restoration networks to bring back them into the original space. The encoded weighted local magnitude patterns (WLMP) are extracted and provided to different types of classifiers to detect facial adversarial images from the clean images. The effectiveness of RobustFace has been demonstrated on two real-world datasets and experimental outcomes show that it significantly improves facial adversarial robustness on all evaluating classifiers. It improves the highest classification accuracy from 98.75% to 99.00% on P-FGSM attacks, from 77.94% to 85.25% on adversarial attacks generated by StyleGAN and from 65.52% to 69.50% for FLM attacks. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Incentivizing Recycling Behavior: Repro-A Reward Based CNN-Enabled Framework for Smart Waste Collection

Incentivizing Recycling Behavior: Repro-A Reward Based CNN-E...

引用

2024 International Conference on engineering and Computing, ICECT 2024

作者： Irfan, Haider Arshad, Usama Anwer, Hammad Ghulam Ishaq Khan Institute of Engineering Sciences and Technology Faculty of Computer Science and Engineering Topi Pakistan

ISBN: (纸本)9798350349719

Efficient waste management together with certain measures to promote the recycling process are essential for over-coming global environmental issues. In this study, we describe Repro an app, which is targeted at transforming how we collect waste and recycle by integrating CNN technology and a reward-based system. Users, with the Repro app, take pictures of any trash they discard and rely on the underlying CNN model to identify the type of trash correctly. If a user's trash accumulation reaches beyond a given limit the system sends a notification to the trash collectors via the riders app to direct for a timely waste collection. User tokens are provided to users after trash collection, which can be redeemed within the Repro app for various product items and coupons. Moreover, this motivating approach encourages responsible waste management which goes along with the development of environmental custodianship among users. We describe the technical implementation of the CNN-based framework, assess the performance of the level of waste classification accuracy, and predict the behavioral implications of the reward system on recycling behavior. The study illustrates that Repro is a scalable solution for smarter waste collection and recycling endeavors, consequently creating a more eco-minded and sustainable environment. © 2024 IEEE.

关键词： Waste management

来源：评论

学校读者我要写书评

暂无评论

A Review of Blockchain-Based E-Voting Systems: Comparative Analysis and Findings

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第23期17卷 49-67页

作者： Fatih, Rabia Arezki, Sara Gadi, Taoufiq Faculty of Sciences and Techniques Mathematics Computer Science and Engineering Sciences Laboratory Hassan first University of Settat Settat Morocco

The emergence of blockchain has ushered in a significant transformation in information systems research. Blockchain’s key pillars such as decentralization, immutability, and transparency have paved the path for extensive exploration in various research domains. This particular study is focused on electronic voting, aiming to improve voting procedures by making better use of the benefits offered by blockchain technology. Through a comprehensive review of existing literature, we highlight the potential benefits of blockchain-based electronic voting systems such as transparency, security, and efficiency. However, several challenges, such as scalability, personal data confidentiality, and ensuring robust identity verification, persist. Addressing these issues is necessary to unlock the full potential of blockchain-based electronic voting systems, thereby fostering the development of trustworthy election systems in the future. © 2023 by the authors of this article. Published under CC-BY. All Rights Reserved.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A Novel Genetic Algorithm Based Timetable Generator for Optimized University Timetable Solution

A Novel Genetic Algorithm Based Timetable Generator for Opti...

引用

2024 International Conference on engineering and Computing, ICECT 2024

作者： Khan, Ali Hasan Imtiaz, Talha Ghulam Ishaq Khan Institute of Engineering Sciences and Technology Faculty of Computer Science and Engineering Topi Pakistan

ISBN: (纸本)9798350349719

In educational institutes, efficient timetable generation is critical for optimizing resource utilization and fostering a conducive learning environment. Timetable challenges, such as clashes among faculty schedules and lack of real-Time updates, underscore the need for innovative solutions in the field. The problem lies in addressing clashes, transparency issues, and inflexibility in manual scheduling systems, leading to disruptions and impacting both students and faculty. We employed a genetic algorithm, combining one-point crossover and mutation operations, to iteratively evolve and adapt timetables to enhances genetic diversity, addresses scheduling conflicts, and promotes the creation of optimal timetables. The results exhibit dynamic and evolving timetables that prioritize efficiency, clash prevention, and overall optimization. The significance lies in fostering an environment conducive to effective teaching and learning, emphasizing fairness, adaptability, and overall well-being. Our work introduces a genetic algorithm-based methodology that not only addresses existing challenges in educational timetable generation but also significantly contributes to fostering a more efficient, transparent, and adaptable scheduling system. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Solving 100-Digit Challenge with Score 100 by Extended Running Time and Parallel Benchmarking 17

Solving 100-Digit Challenge with Score 100 by Extended Runni...

引用

17th International Symposium on Operational Research in Slovenia, SOR 2023

作者： Zamuda, Aleš University of Maribor Faculty of Electrical Engineering and Computer Science Slovenia

ISBN: (纸本)9789616165617

This paper assesses Distance-based Success History Differential Evolution for 100-Digit Challenge and Numerical Optimization Scenarios (DISHchain3e+12). DISHchain3e+12 algorithm is based on DISH algorithm, using a Differential Evolution (DE) parameters control mechanism based on Euclidean distance between trial and parent in a search space to weigh Lehmer means in scaling and crossover historical parameter memories. In this paper, the maximum number of fitness evaluations and initial population size parameters are tailored in the DISHchain3e+12 algorithm per problem, since the benchmark used allows tuning up to two of the same parameters independently for each problem. © Proceedings of the 17th International Symposium on Operational Research in Slovenia, SOR 2023. All rights reserved.

关键词： Population statistics

来源：评论

学校读者我要写书评

暂无评论

Empowering Education through EERP: A Customizable Educational VR Escape Room Platform

Empowering Education through EERP: A Customizable Educationa...

引用

2023 IEEE International Symposium on Mixed and Augmented Reality Adjunct, ISMAR-Adjunct 2023

作者： Darejeh, Ali Faculty of Engineering Unsw School of Computer Science Sydney Australia

ISBN: (纸本)9798350328912

Efficient programming learning necessitates practical knowledge, creativity, and problem-solving skills. However, current methods often disregard these crucial elements, focusing solely on coding principles. As a result, student engagement is compromised. To mitigate this, game-based learning, especially through virtual reality, proves effective in enhancing outcomes and motivation. Addressing this gap, we have developed a pioneering VR-based escape room platform for learning programming. This innovation empowers educators to tailor rooms and puzzles to their curriculum, while its multiplayer feature fosters collaboration, intensifying the learning journey. By seamlessly integrating immersive learning with personalized content, our platform can revolutionize programming education. © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning Network for Attack Detection in Cloud Environment Using Bot-IoT Dataset 4

Hybrid Deep Learning Network for Attack Detection in Cloud E...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Arunprakash, T. Shree Venkateshwara Hi - Tech Engineering College Faculty of Computer Science and Engineering Tamilnadu Erode India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529635

The rapid development of new emerging computing technologies has prompted many enterprises to outsource their data and computational needs. Such services must always adhere to safety standards that include privacy, accessibility, and integrity;therefore, an extremely secure infrastructure is among the most critical features of cloud computing environments. By comprehending malware activity across its entire behavioral spectrum, conventional security measures are significantly surpassed. A hybrid Deep Learning (DL) model, Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU), is proposed for detecting attacks in cloud data. The BoT-IoT dataset is used to validate the solution by characterizing various types of malicious behaviors. The proposed model is compared with traditional Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) models in terms of performance reliability and execution time. Achieving a maximum accuracy of 98.8% and detecting attacks in just 11 seconds, the hybrid DL model demonstrates promising potential for enhancing security monitoring and identifying malicious behavior. © 2024 IEEE.

关键词： Bot (Internet)

来源：评论

学校读者我要写书评

暂无评论

Enhancing Biomedical Literature Analysis to Predict Drug Interactions Using Multi Criteria Decision Making and LSTM-CNN Model

Enhancing Biomedical Literature Analysis to Predict Drug Int...

引用

2023 International Conference on System, Computation, Automation and Networking, ICSCAN 2023

作者： Sankaran, A. Sathiyamurthy, K. Puducherry Technological University Dept. of Computer Science and Engineering India Puducherry Technological University Faculty of Computer Science and Engineering India

ISBN: (纸本)9798350315127

The extraction of information from unstructured text has become a crucial task in the biomedical literature field. Specifically, the analysis of various relationships such as Drug Food, Drug Disease, Drug non-prescription and Drug Drug interactions has gained significant importance. To accomplish this, a combination of Multi Criteria Decision Making (MCDM) and machine learning techniques has been employed. A dataset has been curated and utilized to train a model based on Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN). The trained model enables accurate predictions and identification of relevant information pertaining to drug interactions in biomedical literature. This approach enhances the understanding and knowledge extraction from vast amounts of unstructured text data, leading to improved insights and potential advancements in the field of biomedical research. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

RUSAS: Roman Urdu Sentiment Analysis System

引用

computers, Materials & Continua 2024年第4期79卷 1463-1480页

作者： Kazim Jawad Muhammad Ahmad Majdah Alvi Muhammad Bux Alvi Faculty of Computer Science and Engineering Frankfurt University of Applied SciencesFrankfurt am Main60318Germany Technical Writer and Researcher Proteus Technologies LLCIslamabad04405Pakistan Faculty of Engineering The Islamia University of BahawalpurBahawalpur63100Pakistan

Sentiment analysis, the meta field of Natural Language Processing (NLP), attempts to analyze and identify thesentiments in the opinionated text data. People share their judgments, reactions, and feedback on the internetusing various languages. Urdu is one of them, and it is frequently used worldwide. Urdu-speaking people prefer tocommunicate on social media in Roman Urdu (RU), an English scripting style with the Urdu language *** have developed versatile lexical resources for features-rich comprehensive languages, but limitedlinguistic resources are available to facilitate the sentiment classification of Roman Urdu. This effort encompassesextracting subjective expressions in Roman Urdu and determining the implied opinionated text polarity. Theprimary sources of the dataset are Daraz (an e-commerce platform), Google Maps, and the manual effort. Thecontributions of this study include a Bilingual Roman Urdu Language Detector (BRULD) and a Roman UrduSpelling Checker (RUSC). These integrated modules accept the user input, detect the text language, correct thespellings, categorize the sentiments, and return the input sentence’s orientation with a sentiment intensity *** developed system gains strength with each input experience gradually. The results show that the languagedetector gives an accuracy of 97.1% on a close domain dataset, with an overall sentiment classification accuracy of94.3%.

关键词： Roman Urdu sentiment analysis Roman Urdu language detector Roman Urdu spelling checker flask

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：