检索结果-内蒙古大学图书馆

INFLUENCE OF THE DISCRETIZATION STEP ON THE POSITIVITY OF CONFORMABLE FRACTIONAL LINEAR SYSTEMS

UPB Scientific Bulletin, Series A: applied mathematics and Physics 2023年第1期85卷 77-86页

作者： Benuettou, Kamel Ghezzar, Mohammed Amine Bougada, Djillali Abdelhamid Ibn Badis University Mostaganem ACSY Team-Laboratory of Pure and Applied Math-ematics Department of Mathematics and Computer Science Faculty SEI BP 227/118 Mostaganem27000 Algeria National Higher School of Mathematics ACSY Team-Laboratory of Pure and Applied Mathematics Algeria

The effectiveness of this work lies in the influence of the discretization step on the positivity of the one-dimensional conformable fractional linear systems. A piecewise constant approximation method which converts a continuous fractional order derivative into a discrete time equation is presented as an alternative approach. It aims at investigating whether, how and when this step affects the positive continuous times models. To accomplish this research, a new test was developed and implemented in which the positivity conditions of the considered system was examined both before and after being exposed to the sampling step. i.e., under which conditions the one-dimensional discrete-time linear system obtained by discretization from the one-dimensional continuous time linear systems will be also positive if the one-dimensional continuous time linear system is positive. The new method presented is suggested to test the influence of the discretization step on the positivity of this class of systems. Finally, we discuss some numerical examples to illustrate the validity of the provided results. © 2023, Politechnica University of Bucharest. All rights reserved.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

FisherMask: Enhancing Neural Network Labeling Efficiency in Image Classification Using Fisher Information

FisherMask: Enhancing Neural Network Labeling Efficiency in ...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Gul, Shreen Elmahallawy, Mohamed Madria, Sanjay Tripathy, Ardhendu Missouri University of Science and Technology Computer Science Department RollaMO65401 United States Washington State University School of Engineering & Applied Sciences RichlandWA99354 United States

ISBN: (纸本)9798350362480

Deep learning (DL) models are popular across various domains due to their remarkable performance and efficiency. However, their effectiveness relies heavily on large amounts of labeled data, which are often time-consuming and labor-intensive to generate manually. To overcome this challenge, it is essential to develop strategies that reduce reliance on extensive labeled data while preserving model performance. In this paper, we propose FisherMask, a Fisher information-based active learning (AL) approach that identifies key network parameters by masking them based on their Fisher information values. FisherMask enhances batch AL by using Fisher information to select the most critical parameters, allowing the identification of the most impactful samples during AL training. Moreover, Fisher information possesses favorable statistical properties, offering valuable insights into model behavior and providing a better understanding of the performance characteristics within the AL pipeline. Our extensive experiments demonstrate that FisherMask significantly outperforms state-of-the-art methods on diverse datasets, including CIFAR-10 and FashionMNIST, especially under imbalanced settings. These improvements lead to substantial gains in labeling efficiency. Hence serving as an effective tool to measure the sensitivity of model parameters to data samples. Our code is available at https://***/sgchr273/FisherMask. © 2024 IEEE.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

Scaling LLM-Based Knowledge Graph Generation: A Case Study of Italian Geopolitical News

Scaling LLM-Based Knowledge Graph Generation: A Case Study o...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Russo, Diego Orlando, Gian Marco Romano, Antonio Riccio, Giuseppe La Gatta, Valerio Postiglione, Marco Moscato, Vincenzo University of Naples Federico II Department of Electrical Engineering and Information Technology via Claudio 21 80125 Naples Italy Northwestern University Department of Computer Science McCormick School of Engineering and Applied Science 2233 Tech Dr Evanston IL 60208 United States

ISBN: (纸本)9798350362480

Geopolitical news provides vast amounts of information essential for understanding international relations and political events. However, organizing this information into a coherent, structured format poses challenges due to the complexity and dynamic nature of the domain. This paper introduces a scalable system leveraging Large Language Models to build continuously updated Knowledge Graphs from Italian geopolitical news. The system features a modular architecture, including a Collector Node for scalable article extraction, a Redis-based reliable queue to manage large-scale data ingestion, and a Named Entity Recognition/Relation Extraction Engine to standardize entity-relation triples. The framework addresses key challenges, such as continuous updating and hallucination mitigation, ensuring the reliability of the graph. Our evaluations demonstrate significant improvements in scalability, uniformity of extracted triples, and graph accuracy, making this architecture particularly suitable for real-time geopolitical analysis. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Collaborative MAC Protocol Design for Enhanced Network Lifetime in Mobile Ad Hoc Networks 6

Collaborative MAC Protocol Design for Enhanced Network Lifet...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Verma, Sanjeev Kumar Singh, Digvijay Raghav, Yogita Yashveer Hemelatha, S. Kannimuthu, S. Banchhor, Chitrakant O. Invertis University Department of Applied Sciences Bareilly India School of Engineering and Computer Dev Bhoomi Uttarakhand University Uttarakhand India K. R. Mangalam University Department of Computer Science & Engineering Gurugram India Karpagam College of Engineering Department of Computer Science Engineering Coimbatore India Karpagam College of Engineering Department of Information Technology Coimbatore India Vishwakarma Institute of Information Technology Pune India

ISBN: (纸本)9798350304480

Cdma has a huge opportunity to boost the transmission within mobile devices by using surrounding stations to description method that was overheard in order to obtain place a priority. An effective Competitive Middle Authorization (Colloidal carrier) strategy is required to handle the complex data transmission dynamics brought on by transmitting and to capitalize on the advantages of such collaboration. In this article, we present the De las technique, a unique inter Distributing Fuel Position CMAC etiquette for Cellular Advertisements (MANETs). Enhancing MANET functionality in terms of networking longevity and clean energy is the design goal of Donde. The electricity generation of the receive amplification and transmission hardware is taken into consideration in this article using an actual energy usage model. The optimal relay is chosen using a dispersed power best relay technique known that considers young and motivated individual and gps data. Additionally, a cutting-edge benefit for the organization vector configuration is offered to adapt to the changing transmitted strength of the supply and relayed stations with the aim of increasing routing. By using a thorough dynamic simulation, we demonstrate how the planned De su significantly increases networks lifespan in a variety of situations, including those with high electrical energy demand. © 2023 IEEE.

关键词： CC CD-MAC CMAC DCF GPS and PDA MAC Protocol Designs MANET Utility-Based Best Relay Selection WMN

来源：评论

学校读者我要写书评

暂无评论

Cat Swarm with Fuzzy Cognitive Maps for Automated Soil Classification

引用

computer Systems science & engineering 2023年第2期44卷 1419-1432页

作者： Ashit Kumar Dutta Yasser Albagory Manal Al Faraj Majed Alsanea Abdul Rahaman Wahab Sait Department of Computer Science and Information Systems College of Applied SciencesAlMaarefa UniversityAd DiriyahRiyadh13713Kingdom of Saudi Arabia Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Kingdom of Saudi Arabia Department of Computing Arabeast CollegesRiyadh11583Kingdom of Saudi Arabia Department of Archives and Communication King Faisal UniversityAl AhsaHofuf31982Kingdom of Saudi Arabia

Accurate soil prediction is a vital parameter involved to decide appro-priate crop,which is commonly carried out by the *** an auto-mated soil prediction tool helps to considerably improve the efﬁcacy of the *** the same time,fuzzy logic(FL)approaches can be used for the design of predictive models,particularly,Fuzzy Cognitive Maps(FCMs)have involved the concept of uncertainty representation and cognitive *** other words,the FCM is an integration of the recurrent neural network(RNN)and FL involved in the knowledge engineering *** this aspect,this paper introduces effective fuzzy cognitive maps with cat swarm optimization for automated soil classiﬁca-tion(FCMCSO-ASC)*** goal of the FCMCSO-ASC technique is to identify and categorize seven different types of *** accomplish this,the FCMCSO-ASC technique incorporates local diagonal extrema pattern(LDEP)as a feature extractor for producing a collection of feature *** addition,the FCMCSO model is applied for soil classiﬁcation and the weight values of the FCM model are optimally adjusted by the use of CSO *** exam-ining the enhanced soil classiﬁcation outcomes of the FCMCSO-ASC technique,a series of simulations were carried out on benchmark dataset and the experimen-tal outcomes reported the enhanced performance of the FCMCSO-ASC technique over the recent techniques with maximum accuracy of 96.84%.

关键词： Soil classiﬁcation intelligent models fuzzy cognitive maps cat swarm optimization fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Air Quality Image Classification using Ensemble Based Transfer Learning Techniques

Air Quality Image Classification using Ensemble Based Transf...

引用

International Conference on computer Vision and Internet of Things 2023, ICCVIoT 2023

作者： Saradha, S. Kumar, M. Praveen Asha, J. Saranya, R. Santhoshkumar, S.P. Department of Computer Science and Engineering Sri Eshwar College of Engineering Tamil Nadu Coimbatore India PSG Institute of Technology and Applied Research Neelambur Coimbatore India Department of Computer Science and Engineering Karpagam Academy of Higher Education Coimbatore India Department of Information Technology Rathinam Technical Campus Coimbatore India

ISBN: (纸本)9781839539848

In recent years, research has focused on the efficacy of neural networks, Learning by Transfer (TL), and Ensemble Learning (EL) techniques in image processing. Ensemble approaches, when employed on image classification tasks improve the overall predictive performance and robustness. This work examines the studies related to ensemble approach and applies the same for the classification of images based on different air pollution levels. The proposed research work uses three Convolution Neural Networks (CNN) models namely VGG, MobileNet, and EfficientNet and ensembles them using stacking technique for air quality image classification. The results exhibited in the suggested model generated an overall classification accuracy of 95%. © The Institution of engineering & Technology 2023.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Survey of Crop Identification Using Hyperspectral Satellite Images 1

Survey of Crop Identification Using Hyperspectral Satellite ...

引用

1st IEEE International Conference on Contemporary Computing and Communications, InC4 2023

作者： Premakar, Monica Doss, Srinath Hiran, Kamal Kant Azteca University Department of Computer Science and IT Mexico United States Botho University Faculty of Engineering and Technology Botswana Symbiosis University of Applied Sciences School of Computer Science and IT Indore India

ISBN: (纸本)9798350335774

Hyperspectral images have a lot of spatial and spectral information, which makes them great for fine crop classification and detection. The hyperspectral remote sensing is more capable than panchromatic remote sensing of obtaining the spectral characteristics and their differences with greater precision. One of the most crucial methods for classifying crops is to make use of remote sensing technology to advance agricultural development. This survey is focusing on the review of various techniques implemented in 25 research papers. The crop identification performance metrics, techniques, published year, dataset used, and tools used are reviewed in this survey. Also, the research gaps and issues in the existing researches are discussed, which offers the ideas for developing new techniques for crop identification. © 2023 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Single-Timescale Multi-Sequence Stochastic Approximation Without Fixed Point Smoothness: Theories and Applications

引用

IEEE Transactions on Signal Processing 2025年 73卷 1939-1953页

作者： Huang, Yue Wu, Zhaoxian Ma, Shiqian Ling, Qing Sun Yat-Sen University School of Computer Science and Engineering Guangdong Provincial Key Laboratory of Computational Science Guangzhou510006 China Rice University Department of Computational Applied Mathematics and Operations Research Houston77251 United States Pazhou Lab Guangzhou510275 China

Stochastic approximation (SA) that involves multiple coupled sequences, also known as multiple-sequence SA (MSSA), finds diverse applications in the fields of signal processing and machine learning. However, existing theoretical understandings of MSSA are limited: the multi-timescale analysis implies a slow convergence rate, whereas the single-timescale analysis relies on a stringent fixed point smoothness assumption. In this paper, we establish tighter single-timescale analysis for MSSA, without assuming smoothness of the fixed points. Our theoretical findings reveal that, when all involved operators are strongly monotone, MSSA converges at a rate of O˜(K−1), where K denotes the total number of iterations. When all involved operators are strongly monotone except for the main one, MSSA converges at a rate of O(K− 1/2 ). These rates align with the ones established for single-sequence SA. Applying our novel theoretical findings to bilevel optimization and communication-efficient distributed learning offers relaxed assumptions and/or simpler algorithms with performance guarantees, as validated by numerical experiments. © 1991-2012 IEEE.

关键词： Approximation theory

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Farm Irrigation: A Smart IoT-based Solution for Water Conservation in Agriculture 3

Revolutionizing Farm Irrigation: A Smart IoT-based Solution ...

引用

3rd International Conference on Innovative Sustainable Computational Technologies, CISCT 2023

作者： Mahalakshmi, G. Pandiaraja, P. Apirajitha, P.S. Punitha, S. Soujanya, T. Stephan, Thompson Anna University Department of Information Science and Technology Chennai600025 India M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamil Nadu Karur639113 India Department of Computer Science Engineering Tamil Nadu Chennai602117 India Graphic Era Deemed to Be University Department of Computer Science Engineering Uttarakhand Dehradun248002 India School of Agriculture SR University Telangana Warangal506371 India M. S. Ramaiah University of Applied Sciences Department of Computer Science and Engineering Karnataka Bangalore560054 India

ISBN: (纸本)9798350303360

Agriculture motor and pipe control system deploys innovative technology-based IoT platform to reduced water wastage in the agriculture field. Mobile application interfaced with the microcontroller. A mobile application is developed for the user to control a motor in smart way. The user will control motor in android application. There are many options provided by motor on and off, the user switches on the motor either automatically or manually. This operation performed in a motor can be operated and connected to an android application. In a microcontroller, a timer can be set based on user's desire. Here, the motor will operate based on option user can control, the microcontroller checks moisture and temperature present in the land, based on that water will flow to the land. Another option is that when the farm contains high yield crops when this motor will run three times longer than the other to increase water flow. The main motive of this proposed system is to provides a smart motor for farmers to reduce water flow in farming land. Thus, the objective of this work which is to check both moisture and temperature level of the land based on that water will flows. Hence it can reduce water wastage and manpower. © 2023 IEEE.

关键词： Agriculture

来源：评论

学校读者我要写书评

暂无评论

Confidence Trigger Detection: Accelerating Real-Time Tracking-by-Detection Systems 5

Confidence Trigger Detection: Accelerating Real-Time Trackin...

引用

5th International Conference on Electronic Communication and Artificial Intelligence, ICECAI 2024

作者： Ding, Zhicheng Lai, Zhixin Li, Siyang Li, Panfeng Yang, Qikai Wong, Edward Fu Foundation School of Engineering and Applied Science Columbia University New York United States Cornell University Department of Computer Science Ithaca United States Lubin School of Business Pace University New York United States University of Michigan Department of Electrical and Computer Engineering Ann Arbor United States University of Illinois Urbana-Champaign Department of Computer Science Urbana United States Tandon School of Engineering New York University Brooklyn United States

ISBN: (纸本)9798350386943

Real-time object tracking necessitates a delicate balance between speed and accuracy, a challenge exacerbated by the computational demands of deep learning methods. In this paper, we introduce Confidence-Triggered Detection (CTD), a novel approach that strategically skips object detection for frames exhibiting high similarity, leveraging tracker confidence scores. CTD not only enhances tracking speed but also preserves accuracy, surpassing existing tracking algorithms. Through extensive evaluation across various tracker confidence thresholds, we identify an optimal trade-off between tracking speed and accuracy, providing crucial insights for parameter fine-tuning and enhancing CTD's practicality in real-world scenarios. Furthermore, our experiments across diverse detection models underscore the robustness and versatility of the CTD framework, demonstrating its potential to enable real-time tracking in resource-constrained environments. © 2024 IEEE.

关键词： Object detection

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：