检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zeng, Guangyang Zeng, Qingcheng Li, Xinghan Mu, Biqiang Chen, Jiming Shi, Ling Wu, Junfeng The School of Data Science Chinese University of Hong Kong Shenzhen Shenzhen518172 China The College of Control Science and Engineering The State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix, which is not optimal in the maximum likelihood (ML) sense. In this paper, we dive into the original measurement model with respect to the rotation matrix and normalized translation vector and formulate the ML problem. We then propose a two-step algorithm to solve it: In the first step, we estimate the variance of measurement noises and devise a consistent estimator based on bias elimination;In the second step, we execute a one-step Gauss-Newton iteration on manifold to refine the consistent estimate. We prove that the proposed estimate owns the same asymptotic statistical properties as the ML estimate: The first is consistency, i.e., the estimate converges to the ground truth as the point number increases;The second is asymptotic efficiency, i.e., the mean squared error of the estimate converges to the theoretical lower bound - Cramer-Rao bound. In addition, we show that our algorithm has linear time complexity. These appealing characteristics endow our estimator with a great advantage in the case of dense point correspondences. Experiments on both synthetic data and real images demonstrate that when the point number reaches the order of hundreds, our estimator outperforms the state-of-the-art ones in terms of estimation accuracy and CPU time. Copyright © 2024, The Authors. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

INVARIANCE OF GAUSSIAN RKHSS UNDER KOOPMAN OPERATORS OF STOCHASTIC DIFFERENTIAL EQUATIONS WITH CONSTANT MATRIX COEFFICIENTS

arXiv

引用

arXiv 2024年

作者： Philipp, Friedrich Schaller, Manuel Worthmann, Karl Peitz, Sebastian Nüske, Feliks Technische Universität Ilmenau Institute of Mathematics Weimarer Strasse 25 IlmenauD-98693 Germany Paderborn University Department of Computer Science Data Science for Engineering Germany Max Planck Institute for Dynamics of Complex Technical Systems Magdeburg Germany Freie Universität Berlin Berlin Germany

We consider the Koopman operator semigroup (Kt)t≥0 associated with stochastic differential equations of the form dXt = AXt dt + BdWt with constant matrices A and B and Brownian motion Wt. We prove that the reproducing kernel Hilbert space HC generated by a Gaussian kernel with a positive definite covariance matrix C is invariant under each Koopman operator Kt if the matrices A, B, and C satisfy the following Lyapunov-like matrix inequality: (Equation presented). In this course, we prove a characterization concerning the inclusion HC1 ⊂ HC2 of Gaussian RKHSs for two positive definite matrices C1 and C2. The question of whether the sufficient Lyapunovcondition is also necessary is left as an open problem. © 2024, CC BY.

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks

arXiv

引用

arXiv 2023年

作者： Lin, Zheng Zhu, Guangyu Deng, Yiqin Chen, Xianhao Gao, Yue Huang, Kaibin Fang, Yuguang The Department of Electrical and Electronic Engineering University of Hong Kong Pok Fu Lam Hong Kong The School of Computer Science Fudan University Shanghai200438 China HKU Musketeers Foundation Institute of Data Science University of Hong Kong Pok Fu Lam Hong Kong The Department of Electrical and Computer Engineering University of Florida GainesvilleFL32611 United States The School of Control Science and Engineering Shandong University Shandong Jinan250061 China The Department of Computer Science City University of Hong Kong Kowloon Hong Kong

The increasingly deeper neural networks hinder the democratization of privacy-enhancing distributed learning, such as federated learning (FL), to resource-constrained devices. To overcome this challenge, in this paper, we advocate the integration of edge computing paradigm and parallel split learning (PSL), allowing multiple edge devices to offload substantial training workloads to an edge server via layer-wise model split. By observing that existing PSL schemes incur excessive training latency and large volume of data transmissions, we propose an innovative PSL framework, namely, efficient parallel split learning (EPSL), to accelerate model training. To be specific, EPSL parallelizes client-side model training and reduces the dimension of activations’ gradients for back propagation (BP) via last-layer gradient aggregation, leading to a significant reduction in server-side training and communication latency. Moreover, by considering the heterogeneous channel conditions and computing capabilities at edge devices, we jointly optimize subchannel allocation, power control, and cut layer selection to minimize the per-round latency. Simulation results show that the proposed EPSL framework significantly decreases the training latency needed to achieve a target accuracy compared with the state-of-the-art benchmarks, and the tailored resource management and layer split strategy can considerably reduce latency than the counterpart without optimization. Copyright © 2023, The Authors. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Giant Trevally Optimizer (GTO): Enhancing HVDC Transmission Capacity with Optimized Fault Current Limiters and HVDC Circuit Breaker Parameters

Giant Trevally Optimizer (GTO): Enhancing HVDC Transmission ...

引用

Electronics and Renewable systems (ICEARS), International Conference on

作者： M. Siva Ramkumar Saranya. N Gokul Gopan Rahmath Ulla Baig Josha Daniel S Babu M Department of ECE SNS College of Technology India Department of Artificial Intelligence and Data Science Karpagam College of Engineering India Department of Mechanical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Saveetha University Chennai India Department of Artificial Intelligence and Machine Learning Cambridge Institute of Technology K R Puram Bangalore Department of EEE Hindustan College of Engineering and Technology India Master of Engineering in Embedded Systems Hindusthan College of Engineering and Technology India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

The multi-terminal HVDC system relies heavily on circuit breakers (CBs) and fault current limiters (FCLs) for protection and performance reliability. This research describes a new Giant Trevally optimizer-based strategy for improving the performance of 4-terminal HVDC systems by optimizing crucial circuit breakers and fault current limiters. The proposed method uses time domain estimation to correctly capture fault dynamics, such as traveling waves and reflection coefficients and finds the worst-case fault locations. The multi-objective optimization seeks to optimize the overcurrent, overvoltage handling, fault clearance time, and energy absorption in arresters. This technology provides an effective, dependable protection solution that reduces fault recovery time and increases system stability. The output pulse of the HVDC system shows very low THD results 1.98% for the minimum load condition, 0.87% for median load, and 0.04% for peak load conditions. The results established the simulation of the model in a MATLAB environment.

关键词： HVDC transmission Circuit breakers Stability analysis Circuit faults Fault current limiters Time-domain analysis Protection Voltage control Integrated circuit reliability Optimization

来源：评论

学校读者我要写书评

暂无评论

Polymer dynamics under tension: Mean first passage time for looping

引用

Physical Review E 2025年第2期111卷 025401-025401页

作者： Wout Laeremans Anne Floor den Ouden Jef Hooyberghs Wouter G. Ellenbroek Soft Matter and Biological Physics Department of Applied Physics and Science Education and Institute for Complex Molecular Systems Eindhoven University of Technology P.O. Box 513 5600 MB Eindhoven Netherlands Laboratory of Physical Chemistry Department of Chemical Engineering and Chemistry Eindhoven University of Technology P.O. Box 513 5600 MB Eindhoven Netherlands UHasselt Faculty of Sciences Data Science Institute Theory Lab Agoralaan 3590 Diepenbeek Belgium

This study deals with polymer looping, an important process in many chemical and biological systems. We investigate basic questions on the looping dynamics of a polymer under tension using the freely jointed chain (FJC) model. Previous theoretical approaches to polymer looping under tension have relied on barrier escape methods, which assume local equilibrium, an assumption that may not always hold. As a starting point, we use an analytical expression for the equilibrium looping probability as a function of the number of monomers and applied force, predicting an inverse relationship between looping time and looping probability. Using molecular dynamics simulations, the predictions of this theoretical approach are validated within the numerical precision achieved. We compare our predictions to those of the barrier escape approach by way of a calculation of the mean first passage time (MFPT) for the ends of a polymer to cross. For this purpose, we derive the exact free energy landscape, but the resulting temporal predictions do not agree with the observed inverse scaling. We conclude that the traditional barrier escape approach does not provide satisfactory predictions for polymer looping dynamics and that the inverse scaling with looping probability offers a more reliable alternative.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Investigation of Automatic Part-of-Speech Tagging using CRF, HMM and LSTM on Misspelled and Edited Texts 5

Investigation of Automatic Part-of-Speech Tagging using CRF,...

引用

5th Artificial Intelligence and Cloud Computing Conference, AICCC 2022

作者： Aydinov, Farhad Huseynov, Igbal Sayadzada, Sofiya Rustamov, Samir Data Science University of Glasgow United Kingdom Computational Linguistics and Language Technologies Charles University Prague Czech Republic Department of Applied Mathematics and Computer Science Technical University of Denmark Copenhagen Denmark School of Information Technology and Engineering ADA University Baku Azerbaijan Institute of Control Systems BakuVarna Bulgaria Azerbaijan

ISBN: (纸本)9781450398749

Part-of-speech tagging is the process of assigning words in a given text to appropriate parts-of speech in order to reduce the disambiguation which may arise depending on the contextual usage of the words. In this paper, the problem of word sense disambiguation in Azerbaijani language is addressed by applying part of speech tagging on two varying data corpora, misspelled, and edited (clean) text using 3 different machine learning algorithms: Hidden Markov Model, Long Short-Term Memory, and Conditional Random Fields. The comparative analysis on the outcomes of the mentioned algorithms and their accuracy scores were analysed in the paper. The misspelled dataset for the experiments is provided by Unibank from their chatbot dialogues while the clean textual data was retrieved from the books and newspapers in Azerbaijani. The experiments showed that the Bidirectional LSTM has the highest accuracy scores for both edited (98.2%) and noisy (96.2%) data corpora. Suggested models can be used in the application of algorithms focuses on part of speech tags and syntactic structure of Azerbaijani language which is an agglutinative language belonging to Turkic languages family, thus enabling the research to be further investigated in other agglutinative languages with similar grammatical structure. © 2022 ACM.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Universal subgradient and proximal bundle methods for convex and strongly convex hybrid composite optimization

arXiv

引用

arXiv 2024年

作者： Guigues, Vincent Liang, Jiaming Monteiro, Renato D.C. School of Applied Mathematics FGV/EMAp Rio de Janeiro22250-900 Brazil Goergen Institute for Data Science Department of Computer Science University of Rochester RochesterNY14620 United States School of Industrial and Systems Engineering Georgia Institute of Technology AtlantaGA30332 United States

This paper develops two parameter-free methods for solving convex and strongly convex hybrid composite optimization problems, namely, a composite subgradient type method and a proximal bundle type method. Both functional and stationary complexity bounds for the two methods are established in terms of the unknown strong convexity parameter. To the best of our knowledge, the two proposed methods are the first universal methods for solving hybrid strongly convex composite optimization problems that do not rely on any restart scheme nor require the knowledge of the optimal value. © 2024, CC BY.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Classifying and Detecting Kidney Stone using MRI based on CNN and Attention Model

A Novel Method for Classifying and Detecting Kidney Stone us...

引用

Integration of Emerging Technologies for the Digital World (ICIETDW), International Conference on

作者： Gnanapoo Denosha T P Lalitha Mohammad Shahnawaz Nasir Mohammad Shabbir Alam N Aparna Rajasree Rajamohanan Department of Mathematics Vignan's Foundation for Science Technology and Research Guntur Andhra Pradesh India Geetanjali College of Engineering and Technology Hyderabad Telangana India Department of Computer Science College of Engineering and Computer Science Jazan University Jizan Riyadh Kingdom of Saudi Arabia Department of Biomedical Engineering Dhaanish Ahmed Institute of Technology Coimbatore Tamilnadu India Department of Computer Science (Artificial Intelligence & Data Science) Karpagam Academy of Higher Education Coimbatore India

ISBN: (数字)9798331541170

ISBN: (纸本)9798331541187

When training neural networks, the Back Propagation Network approach is frequently employed. It uses data and images to construct an automated kidney stone classification system. Classification of medical MRI kidney imaging and identification of stones typically involves human assessment. Due of the impracticality of dealing with massive data volumes, this technique is incorrect. Operator error is a potential source of noise contamination in Magnetic Resonance (MR) images. This leads to serious problems with image processing and inaccurate classification characteristics. On the other hand, the use AI, NN, and feature extraction to isolate the target area using back propagation network analysis has yielded impressive results. The objective of this endeavor was to detect kidney stones by use of the Back Propagation Network. In order to accomplish this, data image preprocessing acquires a framework, reduces noise, and removes bed-mats. area, volume of area, and stone's surface area are utilized for feature extraction after the momentum phrase and R proper term are employed for picture segmentation. All three of these models—CNN, LSTM, and AGCNN-LSTM were utilized to train the projected model. With a 96% accuracy rate, the suggested model surpassed its predecessor.

关键词： Backpropagation Training Accuracy Magnetic resonance imaging Noise Predictive models Feature extraction Convolutional neural networks Artificial intelligence Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Development of Advanced Noise Filtering Techniques for Medical Image Enhancement

Development of Advanced Noise Filtering Techniques for Medic...

引用

Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), International Conference on

作者： Sumit Kushwaha K. Amuthachenthiru Geetha. K Jonnadula Narasimharao Dileep Kumar M Sai Sudha Gadde Department of Computer Applications University Institute of Computing Chandigarh University Punjab India Department of Artificial Intelligence and Data Science Ramco Institute of Technology Rajapalayam Tamil Nadu India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of Computer Science and Engineering CMR Technical Campus Hyderabad Telangana India Faculty of Management Sciences Hensard University Bayelsa Nigeria Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Telangana India

Medical imaging modalities, including computed tomography (CT), magnetic resonance imaging (MRI), X-rays, and ultrasound, are extensively employed in the healthcare industry for diagnostic purposes. Noise, on the other hand, can disturb these approaches and lead to inaccurate diagnosis. Due to this problem, the significance of noise removal technologies has grown in the field of medical imaging, specifically for the examination and understanding of medical images and anatomical structures. To tackle these challenges, a variety of denoising techniques have been developed, such as the Weiner filter (WF), Gaussian filter, and median filter. This work employs a Deep Learning (DL) method known as Convolutional Autoencoder (CAE) to remove noise from medical images. We gather chest X-ray images for analysis and focus on common noise types that affect medical images, such as Poisson and Gaussian noise. We evaluate the effectiveness of the suggested denoising method CAE by comparing it to the commonly employed WF methodology. The Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR) are employed to assess and compare the performance of the WF and CAE in reducing Poisson and Gaussian noise. The study's findings indicate that the suggested denoising method based on CAE shows promising results in terms of improving quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging SDN: Empirical Evaluation of Privacy Enriched data Communication over VANET Using Software Defined Network Assistance

Leveraging SDN: Empirical Evaluation of Privacy Enriched Dat...

引用

International Conference on science Technology engineering and Management (ICONSTEM)

作者： R. Ratheesh S. Vijayalakshmi B. Arunsundar M. Swarna G. Saranya Department of ECE Agni College of Technology Chennai Department of ECE R.M.K. Engineering College Chennai Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Department of ECE Dr. M.G.R. Educational and Research Institute University Chennai Department of Electronics and Communication Engineering Sri Krishna College of Engineering and Technology Kuniyamuthur Coimbatore

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

In the realm of modern transportation systems, Vehicular Ad Hoc Networks (VANETs) play a pivotal role in enabling efficient communication among vehicles and infrastructure elements for enhanced road safety and traffic management. However, the inherent vulnerabilities in VANETs, such as privacy breaches and security threats, necessitate robust frameworks to mitigate risks and ensure secure data transmission. This paper presents a comprehensive architecture for Privacy-Enriched data Communication over VANETs using Software-Defined Network (SDN) assistance. The proposed framework integrates key components including vehicles, Roadside Units (RSUs), and SDN controllers to facilitate secure and privacy-aware communication. Vehicles act as data sources, employing pseudonyms and encryption mechanisms to protect user privacy. RSUs serve as access points, collecting and relaying data while enforcing access control policies. SDN controllers provide centralized management, dynamically allocating resources and enforcing privacy policies through encryption, pseudonymization, and access control mechanisms. Communication protocols such as IEEE 802.11p and LTE enable vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communication, while the OpenFlow protocol facilitates communication between SDN controllers and network devices. Additionally, trust management mechanisms evaluate the trustworthiness of network entities based on behavioral analysis, reliability metrics, and security considerations, ensuring the integrity and resilience of the network. By amalgamating SDN-based management with privacy enhancement mechanisms and trust management protocols, the proposed framework offers a robust solution for addressing privacy and security challenges in VANETs, thereby fostering safer and more secure transportation ecosystems.

关键词： Access control data privacy Protocols Vehicle-to-infrastructure Vehicular ad hoc networks Transportation Encryption

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：