检索结果-内蒙古大学图书馆

Data-driven modeling of power system dynamics:Challenges,state of the art,and future work

iEnergy 2023年第3期2卷 200-221页

作者： Heqing Huang Yuzhang Lin Yifan Zhou Yue Zhao Peng Zhang Lingling Fan Department of Electrical and Computer Engineering University of Massachusetts LowellLowellMA 01852USA Department of Electrical and Computer Engineering Stony Brook UniversityStony BrookNY 11794USA Interdisciplinary Science Department Brookhaven National LaboratoryUptonNY 11973USA Department of Electrical and Computer Engineering University of South FloridaTampaFL 33620USA

With the continual deployment of power-electronics-interfaced renewable energy resources,increasing privacy concerns due to deregulation of electricity markets,and the diversification of demand-side activities,traditional knowledge-based power system dynamic modeling methods are faced with unprecedented ***-driven modeling has been increasingly studied in recent years because of its lesser need for prior knowledge,higher capability of handling large-scale systems,and better adaptability to variations of system operating *** paper discusses about the motivations and the generalized process of datadriven modeling,and provides a comprehensive overview of various state-of-the-art techniques and *** also comparatively presents the advantages and disadvantages of these methods and provides insight into outstanding challenges and possible research directions for the future.

关键词： Data-driven modeling machine learning model construction parameter identification power system dynamics system identification

来源：评论

学校读者我要写书评

暂无评论

A Framework for Scalable Object Storage and Retrieval Considering Privacy Concerns: A Case Study on the Signature Detection 9

A Framework for Scalable Object Storage and Retrieval Consid...

引用

9th International Conference on Web Research, ICWR 2023

作者： Khomami, Mohammad Mehdi Daliri Saghiri, Ali Mohammad Rezvanian, Alireza Meybodi, Mohammad Reza Computer Engineering Amirkabir University of Technology Soft Computing Laboratory Department Tehran Iran University of Science and Culture Department of Computer Engineering Tehran Iran

ISBN: (纸本)9798350399691

Nowadays, we are faced with a huge amount of private data generated in different ecosystems, including the Internet of Things, social networks, peer-to-peer networks, and e-commerce, to mention a few. The performance of traditional object storage and retrieval systems concerning response time is going to be degraded by a drastic increase in generated data. This problem becomes more challenging when a specific private object should be found. To address the mentioned problem, this paper suggests scalable object storage and retrieval. To do this, three well-known methods, content-addressable networks from peer-to-peer systems, vector space model from information retrieval systems, and siamese neural networks from neural networks theory, are involved in a framework to bring a scalable system to solve the mentioned problems. The suggested framework is unique to the best of our knowledge because there is no fusion among mentioned fields reported so far. A case study on signature detection is also conducted to evaluate the proposed framework. The results show that, compared to a centralized system, the proposed framework significantly decreases the response time for detecting a signature while maintaining the same accuracy. In addition, the proposed mechanism does not require the private objects to be sent to a central entity, which helps to alleviate privacy concerns. © 2023 IEEE.

关键词： Peer to peer networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multi-Target Surveillance and Tracking Algorithm for Collaborative Drones in IoT Environment 1

Enhanced Multi-Target Surveillance and Tracking Algorithm fo...

引用

1st International Conference on Engineering and Advanced Technology, ICEEAT 2023

作者： Zahia, Mabrek Brahim, Farou Zineddine, Kouahla Hamid, Seridi University 8 Mai 1945 LabStic Laboratory Department of Computer Science Guelma Algeria

ISBN: (纸本)9798350383485

In the realm of IoT-enabled surveillance systems, drones play a pivotal role in detecting and tracking suspects within defined areas. However, a significant challenge arises when a single drone identifies multiple suspects concurrently, leading to the inability to effectively track all targets simultaneously. To address this limitation, this paper introduces a collaborative algorithm designed to enhance multi-target surveillance and tracking in such environments. The algorithm fosters cooperation among drones by dynamically selecting suitable assisting drones to engage in the tracking process. When a drone identifies multiple suspects, it transmits relevant information, including positional data and imagery, to the base station. Subsequently, the algorithm orchestrates the assignment of new tracking missions to assisting drones, enabling them to effectively follow the additional targets. This paper elucidates the algorithm's intricate workings, elucidates its integration within the IoT-based surveillance system architecture, and presents the empirical results of its implementation. Through experimental evaluation, we demonstrate the algorithm's efficacy in improving tracking accuracy, mission success rate, and resource utilization. The proposed solution holds the potential to revolutionize multi-target tracking capabilities in IoT-driven surveillance scenarios, offering a tangible advancement in collaborative drone operations. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Extending OpenStack Monasca for Predictive Elasticity Control

引用

Big Data Mining and Analytics 2024年第2期7卷 315-339页

作者： Giacomo Lanciano Filippo Galli Tommaso Cucinotta Davide Bacciu Andrea Passarella Scuola Normale Superiore Pisa 56126Italy the Real-Time Systems Laboratory(RETIS) TelecommunicationsComputer Engineeringand Photonics Institute(TeCIP)Scuola Superiore Sant’AnnaPisa 56127Italy Department of Computer Science University of PisaPisa 56127Italy National Research Council Pisa56127Italy

Traditional auto-scaling approaches are conceived as reactive automations,typically triggered when predefined thresholds are breached by resource consumption *** such rules at scale is cumbersome,especially when resources require non-negligible time to be *** paper introduces an architecture for predictive cloud operations,which enables orchestrators to apply time-series forecasting techniques to estimate the evolution of relevant metrics and take decisions based on the predicted state of the *** this way,they can anticipate load peaks and trigger appropriate scaling actions in advance,such that new resources are available when *** proposed architecture is implemented in OpenStack,extending the monitoring capabilities of Monasca by injecting short-term forecasts of standard *** use our architecture to implement predictive scaling policies leveraging on linear regression,autoregressive integrated moving average,feed-forward,and recurrent neural networks(RNN).Then,we evaluate their performance on a synthetic workload,comparing them to those of a traditional *** assess the ability of the different models to generalize to unseen patterns,we also evaluate them on traces from a real content delivery network(CDN)*** particular,the RNN model exhibites the best overall performance in terms of prediction error,observed client-side response latency,and forecasting *** implementation of our architecture is open-source.

关键词： OpenStack monitoring elasticity control auto-scaling predictive operations Monasca

来源：评论

学校读者我要写书评

暂无评论

A privacy-preserving approach for detecting smishing attacks using federated deep learning

引用

International Journal of Information Technology (Singapore) 2025年第1期17卷 547-553页

作者： Remmide, Mohamed Abdelkarim Boumahdi, Fatima Ilhem, Bousmaha Boustia, Narhimene LRDSI Laboratory Department of Computer Science Faculty of Sciences University of Blida 1 Blida Algeria Electronics Department Faculty of Technology University of Blida 1 Blida Algeria

Smishing is a type of social engineering attack that involves sending fraudulent SMS messages to trick recipients into revealing sensitive information. In recent years, it has become a significant threat to mobile communications. In this study, we introduce a novel smishing detection method based on federated learning, which is a decentralized approach ensuring data privacy. We develop a robust detection model within a federated learning framework based on deep learning methods such as Long Short-Term Memory (LSTM) and Bidirectional LSTM (Bi-LSTM). Our experiments show that the federated learning method using Bi-LSTM achieves an accuracy of 88.78%, highlighting its effectiveness in tackling smishing detection while preserving user privacy. This approach not only offers a promising solution to smishing attacks but also lays the groundwork for future research in mobile security and privacy-preserving machine learning. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Bi-LSTM Data privacy Federated learning Smishin detection Social engineering

来源：评论

学校读者我要写书评

暂无评论

Kolmogorov-Smirnov based method for detecting black hole attack in vehicular ad-hoc networks

Kolmogorov-Smirnov based method for detecting black hole att...

引用

2023 International Symposium on Green Technologies and Applications, ISGTA 2023

作者： Cherkaoui, Badreddine Houssaini, Mohammed-Alamine El Kasri, Mohammed Beni-Hssane, Abderrahim Erritali, Mohammed LAROSERI Laboratory Mathematics and Computer Science Department High School of Technology Chouaïb Doukkali University Sidi Bennour Morocco ESEF Chouaib Doukkali University El Jadida Morocco LAROSERI Laboratory Computer Science Department Facultyof Sciences Chouaïb Doukkali University El Jadida Morocco TIAD Laboratory Computer science department Sciences and Technics Faculty University of Sultan Moulay Slimane Béni-Mellal Morocco

The security of ad hoc networks continues to pose a major challenge in today's digital age. Threatened by unscrupulous users, especially in decentralized and open architectures, ad-hoc vehicular networks make protection against malicious attacks a difficult task. Vehicular networks, a specific subset of ad hoc networks, inherit security vulnerabilities from their parent network. One of the best-documented attacks is the black hole, in which a malicious user attempts to manipulate the routing mechanism to gain unauthorized access to the route, then intercepts and discards data packets. The result is an interruption of service to the intended recipient. In our research, we propose a black hole attack detection system based on the Kolmogorov-Smirnov statistical method. This system is designed to identify communication disruptions caused by such attacks without requiring structural modifications to the routing protocol. The results show that the proposed method can detect the presence of the attack by monitoring network activity. The results are tested and validated using SUMO (Simulation of Urban MObility) to generate microscopic road traffic, and NS-2 (Network Simulator) to generate network communication. © 2024 The Authors. Published by ELSEVIER B.V.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Challenges and future directions of secure federated learning:a survey

引用

Frontiers of computer science 2022年第5期16卷 173-180页

作者： Kaiyue ZHANG Xuan SONG Chenhan ZHANG Shui YU Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Faculty of Engineering and Information Technology University of Technology SydneySydney 2007Australia SUSTech-UTokyo Joint Research Center on Super Smart City Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China

Federated learning came into being with the increasing concern of privacy security,as people’s sensitive information is being exposed under the era of big *** is an algorithm that does not collect users’raw data,but aggregates model parameters from each client and therefore protects user’s ***,due to the inherent distributed nature of federated learning,it is more vulnerable under attacks since users may upload malicious data to break down the federated learning *** addition,some recent studies have shown that attackers can recover information merely from ***,there is still lots of room to improve the current federated learning *** this survey,we give a brief review of the state-of-the-art federated learning techniques and detailedly discuss the improvement of federated *** open issues and existing solutions in federated learning are *** also point out the future research directions of federated learning.

关键词： federated learning privacy protection security

来源：评论

学校读者我要写书评

暂无评论

Terrorism Attack Classification Using Machine Learning: The Effectiveness of Using Textual Features Extracted from GTD Dataset

引用

computer Modeling in Engineering & sciences 2024年第2期138卷 1427-1467页

作者： Mohammed Abdalsalam Chunlin Li Abdelghani Dahou Natalia Kryvinska School of Computer Science and Technology Wuhan University of TechnologyWuhan430070China LDDI Laboratory Faculty of Science and TechnologyUniversity of Ahmed DRAIAAdrar01000Algeria Information Systems Department Faculty of ManagementComenius UniversityBratislava82005Slovakia

One of the biggest dangers to society today is terrorism, where attacks have become one of the most significantrisks to international peace and national security. Big data, information analysis, and artificial intelligence (AI) havebecome the basis for making strategic decisions in many sensitive areas, such as fraud detection, risk management,medical diagnosis, and counter-terrorism. However, there is still a need to assess how terrorist attacks are related,initiated, and detected. For this purpose, we propose a novel framework for classifying and predicting terroristattacks. The proposed framework posits that neglected text attributes included in the Global Terrorism Database(GTD) can influence the accuracy of the model’s classification of terrorist attacks, where each part of the datacan provide vital information to enrich the ability of classifier learning. Each data point in a multiclass taxonomyhas one or more tags attached to it, referred as “related tags.” We applied machine learning classifiers to classifyterrorist attack incidents obtained from the GTD. A transformer-based technique called DistilBERT extracts andlearns contextual features from text attributes to acquiremore information from text data. The extracted contextualfeatures are combined with the “key features” of the dataset and used to perform the final classification. Thestudy explored different experimental setups with various classifiers to evaluate the model’s performance. Theexperimental results show that the proposed framework outperforms the latest techniques for classifying terroristattacks with an accuracy of 98.7% using a combined feature set and extreme gradient boosting classifier.

关键词： Artificial intelligence machine learning natural language processing data analytic DistilBERT feature extraction terrorism classification GTD dataset

来源：评论

学校读者我要写书评

暂无评论

A Hypothesis Testing-based Framework for Cyber Deception with Sludging 60

A Hypothesis Testing-based Framework for Cyber Deception wit...

引用

60th Annual Allerton Conference on Communication, Control, and Computing, Allerton 2024

作者： Kumar, Abhinav Brahma, Swastik Geng, Baocheng Kamhoua, Charles A. Varshney, Pramod K. University of Cincinnati Department of Computer Science OH United States University of Alabama Department of Computer Science BirminghamAL United States Network Security Branch DEVCOM Army Research Laboratory MD United States Syracuse University Dept. of Electrical Eng. and Computer Science NY United States

ISBN: (纸本)9798331541033

In this paper, we present a novel hypothesis testing framework to model an attacker's decision-making during the reconnaissance phase and employ the framework to design strategic deception strategies that can provide the attacker with optimally falsified information structures. We characterize the criterion for such structures to 'blind' the attacker, i.e., to completely confuse it, as well as the optimal falsification strategy when the attacker cannot be blinded. We also characterize optimal information acquisition costs that can be imposed on the attacker to maximally 'sludge' its decision-making process during the reconnaissance phase. Numerical results have been presented to gain important insights into the developed strategies. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

A Comparison of the Finest Electrical Energy Forecast Models

A Comparison of the Finest Electrical Energy Forecast Models

引用

2023 International Conference on Decision Aid sciences and Applications, DASA 2023

作者： Rania, Farah Brahim, Farou Zineddine, Kouahla Hamid, Seridi University 8 May 1945 LabStic Laboratory Department of Computer Science Guelma Algeria

ISBN: (纸本)9798350342055

Predicting today's utilization of energy will determine how powerful it is in the future. Generators can change their output by foreseeing the demand for electricity. As a result, shortages or overproduction are prevented while resource consumption is optimized. These electrical services may be impacted by the season, the weather, volatility, and other occurrences. Therefore, it is essential for service providers to be able to foresee these situations and have a window of opportunity to take preventative action. The forecasting of electricity load could be demonstrated using a time series prediction problem. Many architectures can contribute in this field to build extremely accurate deep learning models for Short-term Load Forecasting (STLF) in electrical networks. In this paper, the used models are Random Forest, Transformer, Convolutional Neural Network, Linear Regression and Decision Trees. The supplier will choose among this models or combine them to realise an effective prediction. © 2023 IEEE.

关键词： Energy utilization

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：