检索结果-内蒙古大学图书馆

Blackout Mitigation via Physics-Guided RL

IEEE Transactions on Power systems 2025年第3期40卷 2363-2375页

作者： Dwivedi, Anmol Paternain, Santiago Tajer, Ali Rensselaer Polytechnic Institute Electrical Computer and Systems Engineering Department TroyNY12180 United States

This paper considers the sequential design of remedial control actions in response to system anomalies to prevent blackouts. A physics-guided reinforcement learning (RL) framework is designed to identify effective sequences of real-time remedial look-ahead decisions accounting for the long-term impact on the system's stability. The paper considers a space of control actions involving both discrete-valued transmission line-switching decisions (line reconnections and removals) and continuous-valued generator adjustments. To identify an effective blackout mitigation policy, a physics-guided approach is designed that uses power-flow sensitivity factors associated with the power transmission network to guide the RL exploration during agent training. Comprehensive empirical evaluations using the open-source Grid2Op platform demonstrate the notable advantages of incorporating physical signals into RL decisions, establishing the gains of the proposed physics-guided approach compared to its black-box counterparts. One important observation is that strategically removing transmission lines, in conjunction with multiple real-time generator adjustments, often renders effective long-term decisions that are likely to prevent or delay blackouts. © 1969-2012 IEEE.

关键词： Electric load flow

来源：评论

学校读者我要写书评

暂无评论

A sentiment analysis of the Ukraine-Russia War tweets using knowledge graph convolutional networks

引用

International Journal of Information Technology (Singapore) 2025年 1-18页

作者： Menaouer, Brahami Fairouz, Safa Meriem, Mohammed Boulekbachi Mohammed, Sabri Nada, Matta LABAB Laboratory Computer Systems Engineering Department National Polytechnic School of Oran Oran Algeria Computer Systems Engineering Department National Polytechnic School of Oran Oran Algeria TechCICO Laboratory University of Technology of Troyes Troyes France

Nowadays, social networks play a critical role in online social discourse, particularly during major events such as elections, health crises, and wars. Furthermore, individuals have spent significant time on social networks that consume news and express their opinions and viewpoints on various topics, namely, the Russia-Ukraine War. The Ukraine-Russia War is one of the most complicated and unfortunate events of this decade, with many aspects to be considered to have an informed opinion. For this reason, sentiment analysis research can be useful in analyzing sentiments or opinions about the Ukraine-Russia war, such as Twitter (X) posts. In this study, we propose a new deep learning-based sentiment classification model called "Knowledge Graph Convolutional Networks" that predicts and analyzes sentiments concerning the Russia-Ukraine war. There were 500,000 tweets collected in total, however only 410,428 were left for sentiment analysis after cleaning, lemmatization stemming, and deleting duplicate tweets. Results show that "war", "people", "world", "putin", "energy", "gas", "weapon", and "peace" were some of the most frequently occurring words in the tweets. The main aim of this work is to develop a robust system that provides an understanding of public sentiment towards the Russia-Ukraine war on the X platform. Experimental results demonstrate that it is possible to obtain more accurate sentiment classification results by the proposed method. They also have managerial, economic, and research implications. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Classification Decision support systems Graph Convolutional Networks (GCN) Knowledge graph Knowledge management Opinion mining Twitter sentiment analysis Ukraine-Russia War

来源：评论

学校读者我要写书评

暂无评论

Generalized Two-Point Visual Control Model of Human Steering for Accurate State Estimation1

引用

ASME Letters in Dynamic systems and Control 2025年第1期5卷 011004页

作者： Mai, Rene E. Sears, Katherine Roessling, Grace Julius, Agung Mishra, Sandipan Department of Mechanical Aerospace and Nuclear Engineering Rensselaer Polytechnic Institute TroyNY12180 United States Department of Cognitive Science Rensselaer Polytechnic Institute TroyNY12180 United States Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute TroyNY12180 United States

We derive and validate a generalization of the two-point visual control model, an accepted cognitive science model for human steering behavior. The generalized model is needed as current steering models are either insufficiently accurate or too complex for online state estimation. We demonstrate that the generalized model replicates specific human steering behavior with high precision (85% reduction in modeling error) and integrate this model into a human-as-advisor framework where human steering inputs are used for state estimation. As a benchmark study, we use this framework to decipher ambiguous lane markings represented by biased lateral position measurements. We demonstrate that, with the generalized model, the state estimator can accurately estimate the true vehicle state, providing lateral state estimates with under 0.15 m error across participants. However, without the generalized model, the estimator cannot accurately estimate the vehicle's lateral state. © 2024 by ASME.

关键词： Man machine systems

来源：评论

学校读者我要写书评

暂无评论

IMPROVEMENT OF THE ACO ALGORITHM FOR INTELLIGENT TASK SCHEDULING IN CLOUD systems

引用

Scalable Computing 2025年第2期26卷 531-539页

作者： DJEBBAR, ESMA INSAF BELALEM, GHALEM Department of Computer Science Systems Engineering National Polytechnic School of Oran-Maurie Audin Oran Algeria Department of Computer Science University of Oran1-Ahmed Ben Bella Algeria

Cloud computing involves accessing and using computing resources, such as servers, storage, and software applications, over the Internet, enabling scalable access on demand. Cloud computing systems are becoming an essential platform for scientific applications. They enable task scheduling and IT resource allocation. When these resources are not enough to meet demand, planning techniques are necessary. We propose to apply an improved ACO algorithm for intelligent task scheduling and appropriate resource allocation in a cloud environment. This work proposes a modified version of the ACO algorithm that can quickly converge to the best solution to further optimize the total response time, the average response time and the total execution cost. The algorithm suggested based on artificial intelligence application of enhanced ACO is compared with the classical ACO algorithm using Cloudsim simulator. The results obtained after the experiments and simulation are very encouraging to adopt this technique. © (2025), (West University of Timisoara). All rights reserved.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Nanoimprint lithography-assisted block copolymer self-assembly for hyperfine fabrication of magnetic patterns based on L10-FePt nanoparticles

引用

Science China Chemistry 2025年第5期68卷 2027-2034页

作者： Jie Zhang Yi Chen Guijun Li Zelin Sun Zhengong Meng Wai-Yeung Wong Department of Applied Biology and Chemical Technology and Research Institute for Smart Energy The Hong Kong Polytechnic University The Hong Kong Polytechnic University Shenzhen Research Institute Division of Integrative Systems and Design and Department of Electronic and Computer EngineeringThe Hong Kong University of Science and Technology School of Flexible Electronics (Future Technology) and Institute of Advanced Materials (IAM) Nanjing Tech University

L10-FePt-type bit-patterned media has provided a promising alternative for ultrahigh-density magnetic recording systems in the current digital era, but rapid fabrication of magnetic patterns with hyperfine bit islands is still challenging, especially with the target for miniaturization and scalable production simultaneously. Herein, Fe,Pt-containing block copolymers were utilized as single-source precursors for solution-processable patterning and subsequent generation of the demanding magnetic FePt dots by in situ pyrolysis. High-throughput nanoimprint lithography was initially employed to fabricate the predefined bit cells precisely,and then the intrinsic self-assembly of phase-separated block copolymers further drove the formation of accurate bit *** from the synergistic effect of top-down lithographic approach and bottom-up self-assembly, the customizable patterns could be achieved for large-scale mass production in targeted areas, but high-density isolated dots could also be accurately aligned along the patterned features after subsequent self-assembly. This reliable strategy would provide a good avenue to precisely construct ultrahigh-density magnetic data storage devices.

关键词： organometallic precursor magnetic nanoparticles block copolymer self-assembly nanoimprint lithography

来源：评论

学校读者我要写书评

暂无评论

Enhancing Weakly-Supervised Video Anomaly Detection With Temporal Constraints

引用

IEEE Access 2025年 13卷 70882-70894页

作者： Caetano, Francisco Carvalho, Pedro Mastralexi, Christina Cardoso, Jaime S. INESC TEC Institute for Systems and Computer Engineering Technology and Science Porto4200-465 Portugal Porto4200-465 Portugal Polytechnic of Porto ISEP Porto4249-015 Portugal

Anomaly Detection has been a significant field in Machine Learning since it began gaining traction. In the context of computer Vision, the increased interest is notorious as it enables the development of video processing models for different tasks without the need for a cumbersome effort with the annotation of possible events, that may be under represented. From the predominant strategies, weakly and semi-supervised, the former has demonstrated potential to achieve a higher score in its analysis, adding to its flexibility. This work shows that using temporal ranking constraints for Multiple Instance Learning can increase the performance of these models, allowing the focus on the most informative instances. Moreover, the results suggest that altering the ranking process to include information about adjacent instances generates best-performing models. © 2013 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Efficient Cloud-Sourced Transport Mode Detection Using Trajectory Data: A Semi-Supervised Asynchronous Federated Learning Approach

引用

IEEE Internet of Things Journal 2025年第9期12卷 11841-11857页

作者： Yang, Ningkang Lu, Qing-Long Yamnenko, Iuliia Antoniou, Constantinos Technical University of Munich Department of Transportation Systems Engineering Munich85748 Germany National University of Singapore Department of Civil and Environmental Engineering Lower Kent Ridge Road Singapore Department of Electronic Devices and Systems National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute Kyiv03056 Ukraine

The Internet of Things enables collaborative efforts in pattern recognition tasks within intelligent transportation systems, such as transport mode detection (TMD). However, collecting individual trajectories, like GPS records, typically involves privacy issues. To address this, federated learning (FL) frameworks have recently been applied. In such frameworks, users retain their private client datasets and are responsible for training local models. Only the updated client model parameters are sent to a central server, where these parameters are aggregated to update a global model. Then, the server broadcasts the updated global model to all users for the next round of local training. In this way, users can contribute to the global model without sharing private data. However, traditional FL frameworks are inefficient as the server has to wait for multiple users to upload their model parameters for synchronous parameter aggregation and consistency updates. This process also faces risks from unreliable clients. Furthermore, private client datasets are often unlabeled, posing challenges for local model training. Therefore, this article proposes a semi-supervised asynchronous FL framework for both point-level and segment-level TMDs. Specifically, the proposed framework incorporates model splitting techniques, model shift penalties, and entropy-based aggregation strategies to address model complexity, model drift, and data imbalance, respectively. Moreover, a CNN-based deep learning model with multiple encoders is proposed, and a pseudo-labeling-based approach is applied to utilize unlabeled datasets. The case study demonstrates that the proposed model achieves satisfactory performance on a real-world dataset, and the proposed FL framework is robust under varying hyperparameter configurations. © 2014 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Med-DDoS-SDN: A Kafka Streams-Based Distributed Approach for Protecting Healthcare SDN Environments Against DDoS Attacks

Med-DDoS-SDN: A Kafka Streams-Based Distributed Approach for...

引用

Congress on Smart Computing Technologies, CSCT 2023

作者： Kaur, Amandeep Krishna, C. Rama Patil, Nilesh Vishwasrao Department of Computer Science and Engineering National Institute of Technical Teachers Training and Research Chandigarh India Department of Computer Engineering Government Polytechnic Chhatrapati Sambhaji Nagar Aurangabad India

ISBN: (纸本)9789819780952

The healthcare sector, dealing with vast and sensitive data, faces an ever-expanding need for efficient data management and security. Automated healthcare devices generate crucial information, and Software-Defined Networking (SDN) has become integral to healthcare systems due to resource efficiency, robust monitoring, and centralized control. However, in this data-centric environment, SDNs are vulnerable to various cyber threats, including Distributed Denial of Service (DDoS) attacks and probing attempts. These attacks can harm network performance, potentially endangering lives, especially with the rise of portable healthcare integrating mobile services and programmable devices. This article proposes a Kafka Streams-based distributed approach to protect SDN-based healthcare systems from DDoS attacks, named Med-DDoS-SDN. The Med-DDoS-SDN comprises two modules: (i) Real-time Attack Traffic Classification Module (RACM) and (ii) Preprocessed Data Storage Module (PDSM). The RACM categorizes incoming network traffic into four real-time classes. PDSM collects 21 essential features with outcomes into the Hadoop Distributed File System (HDFS) to maintain the classification model with the range samples. Med-DDoS-SDN is formulated and verified using the CICDDoS2019 dataset. The average classification accuracy of the distributed Med-DDoS-SDN solution stands at 92.75%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Wavelet-Enhanced Deep Learning Ensemble for Accurate Stock Market Forecasting: A case study of Nifty 50 Index

引用

IEEE Access 2025年 13卷 87036-87047页

作者： Singh, Priya Jha, Manoj Patel, Harshita Maulana Azad National Institute of Technology Department of Mathematics Bioinformatics & Computer Applications Bhopal 462003 India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India

Portfolio theory underpins portfolio management, a much-researched yet uncharted field. Stock market prediction is a challenging and essential endeavour in financial research, owing to the nonlinear, volatile, and stochastic characteristics of financial time series data. Conventional statistical techniques often fall short to encapsulate complex interdependencies, resulting in diminished predictive accuracy. This research proposes an ensemble model that integrates Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and Temporal Convolutional Networks (TCN) for effective stock market prediction. The Nifty 50 index dataset is utilized for the empirical evidences. Wavelet-based denoising is utilised as a preprocessing measure to mitigate the intrinsic noise in stock market data. The model’s efficacy is assessed utilising error metrics, such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). The five-fold cross-validation is utilized to establish the robustness of the models. Furthermore, we ascertain the statistical significance of performance enhancements by parametric t-tests, including normality assessments via the Shapiro-Wilk test. Moreover, current state-of-the-art models advocates in favour of proposed study. © 2013 IEEE.

关键词： CNN Ensemble learning LSTM Random Forest Statistical Analysis Stock Market TCN

来源：评论

学校读者我要写书评

暂无评论

Intelligent Cyber Defense: Leveraging LLMs for Real-Time Threat Detection and Analysis 21st

Intelligent Cyber Defense: Leveraging LLMs for Real-Time Th...

引用

21st European, Mediterranean, and Middle Eastern Conference on Information systems, EMCIS 2024

作者： Kakoulli, Elena Zacharioudakis, Eleftherios Evripidou, Salomi Intelligent Systems Laboratory Department of Computer Science Neapolis University Pafos Pafos Cyprus Electrical Engineering and Computer Engineering and Informatics Cyprus University of Technology Limassol Cyprus National Technical University of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Kyiv Ukraine

ISBN: (纸本)9783031813214

This paper reviews the application of Large Language Models (LLMs) in addressing the growing sophistication of cybersecurity threats. By evaluating numerous studies, we delineate the role of LLMs in improving the detection, analysis, and response to cyber threats in real-time. Our findings demonstrate that LLMs significantly enhance the efficiency and accuracy of cybersecurity measures compared to traditional models. However, their deployment in cybersecurity frameworks involves critical considerations around ethics, privacy, and security. This review provides a succinct overview of LLMs’ current capabilities and practical implementations within the cybersecurity landscape, identifies research gaps, and suggests future research directions. The insights presented here highlight the vital contribution of LLMs to the advancement of cybersecurity solutions and adapting to evolving threat environments. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Cyber attacks

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：