检索结果-内蒙古大学图书馆

International Conference on Inventive Computation Technologies (ICICT)

作者： Aditi Barai Manami Das Priyanka Bhowmick Udita Dey Prianka Dey Sagarika Chowdhury Department of Computer Science and Business Systems Narula Institute of Technology Kolkata India Department of Computer Science and Engineering (AI ML) Narula Institute of Technology Kolkata India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Word Sense Disambiguation(WSD) is a Natural Language Processing(NLP) technique that tries to disambiguate ambiguous words by finding the right sense of a word in a particular context. It is a classification task that assists in mapping a word to one or more potential senses based on its sentence. Understanding the intended sense in a particular context is crucial for proper communication and accurate language processing. But WSD is especially crucial in Bengali for a number of reasons: Similar to other Indic languages, Bengali possesses a rich and complex system of word formation. A root word can be modified according to aspects like tense, gender, number, and case. An attempt is made in this working paper where authors will be working on WSD but on the Bengali language, where words have different meanings. The Bengali language has plenty of words with multiple meanings. Even though WSD has been propagated the world over, the language Bengali has a lot of challenges since there are very few resources available and research due to its complex syllable structure.

关键词： Surveys Sensitivity Computational modeling Evaluation models Natural languages Computational efficiency Complexity theory Object recognition Optimization Overfitting

来源：评论

学校读者我要写书评

暂无评论

Stolt Interpolation-Free Range Migration Algorithm for Dynamic-Aperture-Based Computational MIMO Microwave Imaging

引用

IEEE Access 2025年 13卷 83082-83094页

作者： Skouroliakou, Vasiliki García-Fernandez, Maria Álvarez-Narciandi, Guillermo Cotton, Simon Yurduseven, Okan Queen’s University Belfast Centre for Wireless Innovation School of Electronics Electrical Engineering and Computer Science BelfastBT3 9DT United Kingdom University of Oviedo Group of Signal Theory and Communications Department of Electrical Electronic Communications and Systems Engineering Gijón33203 Spain

Computational imaging (CI) techniques realized by dynamic metasurface antennas (DMAs) offer significant advantages in the hardware design reducing the cost of such systems. In this paper, we present a physical layout based solely on DMA panels that can be used to synthesize electrically large apertures suitable for microwave imaging. Although hardware is significantly simplified, the challenge of using CI DMA-based systems presents itself in the signal processing layer. This is because in microwave CI the transfer function of the antennas is used to encode information from the imaged target scene and compress it into a single (or a few) channel(s). As a consequence, real-time Fourier-based image reconstruction algorithms cannot be directly applied because of the nature of the compressed back-scattered signals. In this work, we propose an algorithm that employs a decompression step such that the signal is converted to a suitable form for spatial frequency domain processing. The proposed technique mitigates the challenges of applying the algorithm in the near-field. Crucially, it also eliminates the need for a computationally expensive Stolt interpolation step, which can be a significant bottleneck for conventional Fourier-based image reconstruction algorithms. Numerical and experimental CI results are presented to validate the ability of the proposed system and algorithm to produce reconstructed images of good quality. The benefits of the proposed algorithm in terms of execution time and storage requirements are also explored in this work. © 2013 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

High-Lift Prediction Workshop 5: High-Order Discretization Technology Focus Group Summary

High-Lift Prediction Workshop 5: High-Order Discretization T...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Galbraith, Marshall C. Ruiz-Gironés, Eloi Roca, Xevi Wang, Z.J. Holst, Kevin R. Skaperdas, Vangelis Department of Aeronautics and Astronautics Massachusetts Institute of Technology CambridgeMA02139 United States Applications in Science and Engineering Barcelona Supercomputing Center - BSC Barcelona Spain Department of Aerospace Engineering University of Kansas LawrenceKS66045 United States Electrical Engineering and Computer Science University of Tennessee KnoxvilleTN37996 United States Customer Service BETA CAE Systems Thessaloniki Greece

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

This paper summarizes the High-Order Technical Focus Group (HO-TFG) submissions forthe 5th AIAA High-Lift Prediction Workshop (HLPW-5). The goal of the workshop was to assess the state-of-the-art in mesh generation and computational fluid dynamics software for predicting peak lift of transport aircraft with flaps and slats deployed. Numerous geometric build ups of the Common Research Model High-Lift (CRM-HL) variant and Reynolds number considerations served as the primary focus of the workshop, and a simple wing-body variant of the CRM-HL was used as a verification test case. The HO-TFG was tasked with generating high-order curved meshes for these complex geometries, and computing high-order solutions using both Reynolds Averaged Navier-Stokes (RANS) and scale resolving Large Eddy Simulation(LES) formulations. While participation in the HO-TFG was limited, the effort produced curved meshes on highly-complex geometric configurations and computational results from two participants. The LES results demonstrate the potential for producing results comparable to 2nd-order accurate methods, but with fewer degrees of freedom. The RANS submission for this workshop does not demonstrate a benefit over 2nd-order schemes. However, the authors will argue a lack of understanding for optimal mesh distributions for high-order methods is the cause for the limited benefits observed for the RANS results. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Reynolds number

来源：评论

学校读者我要写书评

暂无评论

Biomedical Text Summarization for Medical Insights

Biomedical Text Summarization for Medical Insights

引用

International Conference on Trends in Electronics and Informatics (ICEI)

作者： Neha Shree N Jothish Kumar M School of Computer Science Engineering and Information Systems VIT Vellore Vellore Tamil Nadu India Department of Smart Computing School of Computer Science Engineering and Information Systems VIT Vellore Vellore Tamil Nadu India

ISBN: (数字)9798331544607

ISBN: (纸本)9798331544614

With a vast increase in the present amount of digital information with regards to biomedical research, processing related data in an efficient manner assumes critical importance. This work proposes a hybrid summarization method combining extractive and abstractive techniques with the help of cutting-edge models in NLP. While BERT is used to select the most informative sentences capable of summarizing main ideas in a document, Pegasus has been used to generate smooth, concise summaries for the purpose. The results with the metrics like Cosine Similarity and BERTScore, incorporating precision, recall, and F1 score, show the system proposed performs very well by holding onto the meaning that preserves coherent summaries of high quality on generation. It is of great benefit to researchers as well as professionals regarding rapid extraction from vast amounts of complex data.

关键词： Measurement Biological system modeling Text summarization Transforms Market research Hybrid power systems Data mining Informatics Context modeling Digital information

来源：评论

学校读者我要写书评

暂无评论

A Design of Hybrid Model and Bayesian Neural Networks for Smart Grid Stability Prediction 1

A Design of Hybrid Model and Bayesian Neural Networks for Sm...

引用

1st IEEE International Conference on Smart and Sustainable Developments in Electrical engineering, SSDEE 2025

作者： Hole, Shreyas Rajendra Kolluru, Vinothkumar Salotagi, Shreekant Challagundla, Yagnesh Mungara, Sudeep Sriramkumar, R. Dayananda Sagar University AI & ML Bangalore India Stevens Institute of Technology Department of Data Science HobokenNJ07030 United States Dayananda Sagar University Computer Science & Engineering Bagalore India Herbert Wertheim College of Engineering University of Florida Department of Computer Science GainesvilleFL32611 United States Stevens Institute of Technology Masters in Information Systems HobokenNJ07030 United States

ISBN: (纸本)9798331542108

The latest evolution in power systems, is 'smart grids'that offers real time monitoring, control features as well as effective management of renewable energy sources. Nonetheless, with the increase in the system complexity, the chances for insta- bility also increase and thus it is crucial to forecast the stability accurately for the safety of the grid. Weather it is in terms of Gradient Boosting Tree Algorithm or any other traditional algorithm, these machine learning models are successful in achieving the objectives of the task but they lack a forthcoming metric to assist in high stake situations, uncertainty quantification. The paper is devoted to the analysis of the reliability of smart grid systems based on Bayesian Neural Networks (BNN) taking into account both the reliability of predictive modeling and forecasting uncertainty. The smart grid stability augmented dataset was used to benchmark the efficacy of using BNNs or BNNs combined hybrid models, one with XGBoost, for feature extraction and the other with LightGBM. The present study shows that the BNN used with the above mentioned smart grid system achieved an accuracy of 92% with precision of 0.89, recall of 0.91 and F1 of 0.90. These metrics are appending with the help of the additional features of BNN where they are capable of addressing the key questions around uncertainty and thus the metrics confirming the predictions are quite strong in terms of real-time grid stability evaluation. This article encapsulates a detailed study of BNN architecture, the role of uncertainty in machine learning models and the natural application of such models in the design of dependable and fault-tolerant smart grids. © 2025 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Federated Learning systems for Time-Series Power Consumption Prediction with Multi-Head Embedding Mechanism

arXiv

引用

arXiv 2025年

作者： Syu, Jia-Hao Lin, Jerry Chun-Wei Srivastava, Gautam Yun, Unil Department of Computer Science and Information Engineering National Taiwan University Taiwan Department of Distributed Systems and Informatic Devices Silesian University of Technology Poland Department of Math and Computer Science Brandon University Brandon Canada Department of Computer Science and Engineering Sejong University Korea Republic of

Time-series prediction is increasingly popular in a variety of applications, such as smart factories and smart transportation. Researchers have used various techniques to predict power consumption, but existing models lack discussion of collaborative learning and privacy issues among multiple clients. To address these issues, we propose Multi-Head Heterogeneous Federated Learning (MHHFL) systems that consist of multiple head networks, which independently act as carriers for federated learning. In the federated period, each head network is embedded into 2-dimensional vectors and shared with the centralized source pool. MHHFL then selects appropriate source networks and blends the head networks as knowledge transfer in federated learning. The experimental results show that the proposed MHHFL systems significantly outperform the benchmark and state-of-the-art systems and reduce the prediction error by 24.9% to 94.1%. The ablation studies demonstrate the effectiveness of the proposed mechanisms in the MHHFL (head network embedding and selection mechanisms), which significantly outperforms traditional federated average and random transfer. © 2025, CC BY-NC-SA.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

5DGWO-GAN:A Novel Five-Dimensional Gray Wolf Optimizer for Generative Adversarial Network-Enabled Intrusion Detection in IoT systems

引用

computers, Materials & Continua 2025年第1期82卷 881-911页

作者： Sarvenaz Sadat Khatami Mehrdad Shoeibi Anita Ershadi Oskouei Diego Martín Maral Keramat Dashliboroun Department of Data Science Engineering University of HoustonHoustonTX 77204USA The WPI Business School Worcester Polytechnic InstituteWorcesterMA 01609USA School of Systems and Enterprises Stevens Institute of TechnologyHobokenNJ 07030USA Department of Computer Science Escuela de Ingeniería Informática de SegoviaUniversidad de ValladolidSegovia40005Spain Ernest G.Welch School of Art&Design Georgia State UniversityAtlantaGA 30303USA

The Internet of Things(IoT)is integral to modern infrastructure,enabling connectivity among a wide range of devices from home automation to industrial control *** the exponential increase in data generated by these interconnected devices,robust anomaly detection mechanisms are *** detection in this dynamic environment necessitates methods that can accurately distinguish between normal and anomalous behavior by learning intricate *** paper presents a novel approach utilizing generative adversarial networks(GANs)for anomaly detection in IoT ***,optimizing GANs involves tuning hyper-parameters such as learning rate,batch size,and optimization algorithms,which can be challenging due to the non-convex nature of GAN loss *** address this,we propose a five-dimensional Gray wolf optimizer(5DGWO)to optimize GAN *** 5DGWO introduces two new types of wolves:gamma(γ)for improved exploitation and convergence,and theta(θ)for enhanced exploration and escaping local *** proposed system framework comprises four key stages:1)preprocessing,2)generative model training,3)autoencoder(AE)training,and 4)predictive model *** generative models are utilized to assist the AE training,and the final predictive models(including convolutional neural network(CNN),deep belief network(DBN),recurrent neural network(RNN),random forest(RF),and extreme gradient boosting(XGBoost))are trained using the generated data and AE-encoded *** evaluated the system on three benchmark datasets:NSL-KDD,UNSW-NB15,and *** conducted on diverse IoT datasets show that our method outperforms existing anomaly detection strategies and significantly reduces false *** 5DGWO-GAN-CNNAE exhibits superior performance in various metrics,including accuracy,recall,precision,root mean square error(RMSE),and convergence *** proposed 5DGWO-GAN-CNNAE achieved the lowest RMSE values across the NSL-KDD,UNSW-NB15,and

关键词： Internet of things intrusion detection generative adversarial networks five-dimensional binary gray wolf optimizer deep learning

来源：评论

学校读者我要写书评

暂无评论

Runtime Backdoor Detection for Federated Learning via Representational Dissimilarity Analysis

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Zhang, Xiyue Xue, Xiaoyong Du, Xiaoning Xie, Xiaofei Liu, Yang Sun, Meng University of Oxford Department of Computer Science United Kingdom Peking University Department of Information and Computing Science School of Mathematical Science China Monash University Department of Software Systems and Cybersecurity Australia Singapore Management University School of Computing and Information Systems Singapore Nanyang Technological University School of Computer Science and Engineering Singapore

Federated learning (FL), as a powerful learning paradigm, trains a shared model by aggregating model updates from distributed clients. However, the decoupling of model learning from local data makes FL highly vulnerable to backdoor attacks, where a single compromised client can poison the shared model. While recent progress has been made in backdoor detection, existing methods face challenges with detection accuracy and runtime effectiveness, particularly when dealing with complex model architectures. In this work, we propose a novel approach to detecting malicious clients in an accurate, stable, and efficient manner. Our method utilizes a sampling-based network representation method to quantify dissimilarities between clients, identifying model deviations caused by backdoor injections. We also propose an iterative algorithm to progressively detect and exclude malicious clients as outliers based on these dissimilarity measurements. Evaluations across a range of benchmark tasks demonstrate that our approach outperforms state-of-the-art methods in detection accuracy and defense effectiveness. When deployed for runtime protection, our approach effectively eliminates backdoor injections with marginal overheads. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Inertia Estimation and Validation Using PMU Data and the Swing Equation in Power systems

Real-Time Inertia Estimation and Validation Using PMU Data a...

引用

2025 IEEE Green Technologies Conference, GreenTech 2025

作者： Mhawesh, Mustafa A. Al-Sarray, Muthanna Mccann, Roy University of Arkansas Department of Electrical Engineering and Computer Science FayettevilleAR United States Al-Furat Al-Awsat Technical University Kufa Iraq Operation and Control Office Ministry of Electricity Baghdad Iraq

ISBN: (纸本)9798331520182

This paper presents a method to estimate power system inertia in real-time using Phasor Measurement Unit (PMU) data and the swing equation. Inertia is essential for maintaining power system stability during disturbances. The method calculates both electrical and mechanical power from PMU data and uses this information to estimate inertia by using Matlab. Then it validates the results by comparing calculated values with real measurements of the rate of change of frequency (ROCOF). Further validation is performed using data from a real-world generation trip event. The outcomes show that the proposed method is accurate, with minimal error, making it suitable for real-time applications. © 2025 IEEE.

关键词： Standby power systems

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Various Machine Learning Techniques for Diabetes Prediction

Comparative Study of Various Machine Learning Techniques for...

引用

Artificial Intelligence and Data engineering (AIDE), International Conference on

作者： Jambukeshwar Pujari Ashok Hake Department of Computer Science and Business Systems KIT’s College of Engineering(Autonomous) Kolhapur Maharashtra India

ISBN: (数字)9798331527518

ISBN: (纸本)9798331527525

Diabetes is a pervasive chronic disease affecting millions worldwide, necessitating effective and early prediction to improve patient outcomes and reduce healthcare costs. This study presents a comparative analysis of various machine learning models in prediction of diabetes, with an emphasis on both individual model performance and ensemble methods. Logistic Regression, Random Forest, Decision Tree, Support Vector Machine (SVM), K-Nearest Neighbors, and XGBoost model’s performance are analyzed using a dataset of clinical health indicators. Accuracy, Precision, Recall, and F1-score are the key metrics considered to determine their predictive model performance. Furthermore, a Voting Classifier is implemented to explore whether an ensemble of models can outperform individual algorithms in terms of predictive accuracy and *** of the experimental results indicate that the XGBoost model and the Voting Classifier provide superior accuracy and reliability, making them effective tools for early-stage diabetes prediction. This research highlights the potential of machine learning in healthcare and suggests a promising approach to predictive modeling for diabetes diagnosis.

关键词： Support vector machines Analytical models Accuracy Machine learning algorithms Predictive models Diabetes Ensemble learning Random forests Tuning Diseases

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：