检索结果-内蒙古大学图书馆

Assessing the Impact of Physical Configuration and Lead Time on WRF Forecasting of an Extreme Wind Event

Journal of Meteorological Research 2025年第1期39卷 154-171页

作者： Rocío OTERO Matías SUAREZ Edgardo PIEROBON Leandro MATURANO Ignacio MONTAMAT Juan Ezequiel SANCHEZ Lucia SANDALIO Andrés RODRIGUEZ Denis POFFO Hydrometeorology Laboratory Department of ExactPhysical and Natural SciencesNational University of CordobaCórdobaX5016GCAArgentina Institute for Advanced Studies in Engineering and Technology National Scientific and Technical Research CouncilCordobaX5016GCAArgentina Radar and Remote Sensing Laboratory Department of MathematicsAstronomyPhysics and Computer ScienceNational University of CordobaCordobaX5016HUAArgentina

The central region of Argentina is known to be a source of some most extreme weather events in the world,which are partially associated with the passage of cold fronts accompanied often by extreme wind *** may cause severe property damage and even loss of human ***,there is a lack of studies that evaluate the performance of the numerical weather prediction(NWP)models such as weather research and forecasting(WRF)model in anticipating this type of weather in the *** study compares the performance of the operational WRF in Argentina using four combinations of various planetary boundary layer(PBL)and microphysics parameterization schemes under varied lead times in predicting an extreme wind event(gusts>30 m s^(-1))in Central *** results demonstrate that the WRF model is capable of providing an acceptable prediction of wind speed during an extreme *** is found that no single combination outperforms the others,although there is a slight tendency for Combination A,which utilizes the Mellor-Yamada-Janjic(MYJ)parameterization for the PBL and the Eta similarity parameterization for the surface layer,to more accurately capture the extreme wind *** with wind gust observations at five weather stations,the wind gust parameterization predicted the intensity and occurrence time of the peak wind,with an acceptable bias(time of peak<±1 h).Analysis of grid configurations(resolutions of 4 vs 9/3/1 km)revealed that higher resolution does not imply an improvement in the wind gust forecast for this particular *** regard to lead time,a shorter lead time does not necessarily result in more accurate ***,it is beneficial to conduct multiple sensitivity runs in order to obtain and understand the dispersion of forecasted wind speeds.

关键词： extreme wind wind event weather research and forecasting(WRF)model wind gust forecast cold front lead time

来源：评论

学校读者我要写书评

暂无评论

Real-Time Implementation of Quadrotor UAV Control System Based on a Deep Reinforcement Learning Approach

引用

computers, Materials & Continua 2024年第12期81卷 4757-4786页

作者： Taha Yacine Trad Kheireddine Choutri Mohand Lagha Souham Meshoul Fouad Khenfri Raouf Fareh Hadil Shaiba Aeronautical Sciences Laboratory Aeronautical and Spatial Studies InstituteBlida 1 UniversityBlida0900Algeria Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia Energy and Embedded Systems for Transportation Research Department ESTACA-LABMontigny-Le-Bretonneux78066France Department of Electrical Engineering University of SharjahSharjah27272United Arab Emirates Department of Computer Science College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia

The popularity of quadrotor Unmanned Aerial Vehicles(UAVs)stems from their simple propulsion systems and structural ***,their complex and nonlinear dynamic behavior presents a significant challenge for control,necessitating sophisticated algorithms to ensure stability and accuracy in *** strategies have been explored by researchers and control engineers,with learning-based methods like reinforcement learning,deep learning,and neural networks showing promise in enhancing the robustness and adaptability of quadrotor control *** paper investigates a Reinforcement Learning(RL)approach for both high and low-level quadrotor control systems,focusing on attitude stabilization and position tracking tasks.A novel reward function and actor-critic network structures are designed to stimulate high-order observable states,improving the agent’s understanding of the quadrotor’s dynamics and environmental *** address the challenge of RL hyper-parameter tuning,a new framework is introduced that combines Simulated Annealing(SA)with a reinforcement learning algorithm,specifically Simulated Annealing-Twin Delayed Deep Deterministic Policy Gradient(SA-TD3).This approach is evaluated for path-following and stabilization tasks through comparative assessments with two commonly used control methods:Backstepping and Sliding Mode Control(SMC).While the implementation of the well-trained agents exhibited unexpected behavior during real-world testing,a reduced neural network used for altitude control was successfully implemented on a Parrot Mambo mini *** results showcase the potential of the proposed SA-TD3 framework for real-world applications,demonstrating improved stability and precision across various test scenarios and highlighting its feasibility for practical deployment.

关键词： Deep reinforcement learning hyper-parameters optimization path following quadrotor twin delayed deep deterministic policy gradient and simulated annealing

来源：评论

学校读者我要写书评

暂无评论

A Novel Preprocessing Technique to Aid the Detection of Infected Areas of CT Images in COVID-19 Patients Artificial Intelligence (AI) for Communication Systems

A Novel Preprocessing Technique to Aid the Detection of Infe...

引用

Trends in Quantum Computing and Emerging Business Technologies (TQCEBT), International Conference on

作者： J. Kalaivani A. S. Arunachalam R. Gobinath Department of Computer Science School of Computing Sciences Vels Institute of Science Technology and Advanced Studies (VISTAS) Chennai India Department of Computer Science Christ University Bengaluru India

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

An innovative preprocessing method for discerning infected areas in CT images of COVID-19 is described in this abstract. The methodology being suggested exploits the capabilities of artificial intelligence (AI) to improve disease detection communication systems. By employing sophisticated AI algorithms to preprocess CT images, the method seeks to increase the precision and effectiveness of COVID-19-associated area detection. The incorporation of artificial intelligence (AI) into communication systems facilitates enhanced image analysis, resulting in improved diagnostic capabilities and treatment strategizing. The study's findings demonstrate the potential of preprocessing techniques powered by artificial intelligence in augmenting communication systems with the aim of enhancing healthcare outcomes.

关键词： COVID-19 Quantum computing Communication systems Computed tomography Perturbation methods Noise Refining

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Telegram App Reviews Using Text Classification Models 4

Sentiment Analysis of Telegram App Reviews Using Text Classi...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Thomas, Lijo P Thomas, Juby Menon, Vishnu Achutha Sateesh Kumar, T.K. Kristu Jayanti College Department of Computer Science Bengaluru India Kristu Jayanti College Department of Media Studies Bengaluru India Institute for Educational and Developmantal Studies Deparment of Communication and International Studies Noida India Kristu Jayanti College Department of Commerce Bengaluru India

ISBN: (纸本)9798331523923

This study explores sentiment analysis of Telegram app reviews using four machine learning-models: Naive Bayes, Random Forest, Logistic-Regression and Neural Networks. A dataset of 76,500 reviews was analyzed, and the models were evaluated based on precision, recall, F1-score, and accuracy across three sentiment categories: Negative, Neutral, and Positive. Among the models, random -forest achieved the highest accuracy of 75% but struggled with Neutral sentiment classification, a challenge shared by the other models. Logistic Regression and Naive Bayes both delivered 74% accuracy, with slightly better precision and recall for Negative and Positive sentiments. Neural Networks achieved 72% accuracy but faced difficulties in identifying Neutral sentiments. The use of 'Natural Language Processing' (NLP) techniques, such as text preprocessing and feature extraction, proved crucial for improving performance. © 2025 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Collision-aware interactive simulation using graph neural networks

引用

Visual Computing for Industry,Biomedicine,and Art 2022年第1期5卷 174-186页

作者： Xin Zhu Yinling Qian Qiong Wang Ziliang Feng Pheng‑Ann Heng College of Computer Science Sichuan UniversityChengdu 610065China Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518055China Department of Computer Science and Engineering The Chinese University of Hong KongHong KongChina

Deep simulations have gained widespread attention owing to their excellent acceleration ***,these methods cannot provide effective collision detection and response *** propose a deep interac-tive physical simulation framework that can effectively address tool-object *** framework can predict the dynamic information by considering the collision *** particular,the graph neural network is chosen as the base model,and a collision-aware recursive regression module is introduced to update the network parameters recursively using interpenetration distances calculated from the vertex-face and edge-edge ***,a novel self-supervised collision term is introduced to provide a more compact collision *** study extensively evaluates the proposed method and shows that it effectively reduces interpenetration artifacts while ensuring high simulation efficiency.

关键词： Deep physical simulation Collision-aware Continuous collision detection Graph neural network

来源：评论

学校读者我要写书评

暂无评论

MLRegTest: a benchmark for the machine learning of regular languages

引用

The Journal of Machine Learning Research 2024年第1期25卷 13641-13685页

作者： Sam Van der Poel Dakotah Lambert Kalina Kostyszyn Tiantian Gao Rahul Verma Derek Andersen Joanne Chau Emily Peterson Cody St. Clair Paul Fodor Chihiro Shibata Jeffrey Heinz School of Mathematics Georgia Institute of Technology Department of Computer Science Haverford College Department of Linguistics & Institute of Advanced Computational Science Stony Brook University Department of Computer Science Stony Brook University Department of Computer Science Stony Brook University Department of Linguistics Stony Brook University Department of Advanced Sciences Graduate School of Science and Engineering Hosei University

Synthetic datasets constructed from formal languages allow fine-grained examination of the learning and generalization capabilities of machine learning systems for sequence classification. This article presents a new benchmark for machine learning systems on sequence classification called MLRegTest, which contains training, development, and test sets from 1,800 regular *** kinds of formal languages represent different kinds of long-distance dependencies, and correctly identifying long-distance dependencies in sequences is a known challenge for ML systems to generalize successfully. MLRegTest organizes its languages according to their logical complexity (monadic second order, first order, propositional, or restricted propositional) and the kind of logical literals (string, tier-string, subsequence, or combinations thereof). The logical complexity and choice of literal provides a systematic way to understand different kinds of long-distance dependencies in regular languages, and therefore to understand the capacities of different ML systems to learn such long-distance ***, the performance of different neural networks (simple RNN, LSTM, GRU, transformer) on MLRegTest is examined. The main conclusion is that performance depends significantly on the kind of test set, the class of language, and the neural network architecture.

关键词： formal languages regular languages subregular languages sequence classification neural networks long-distance dependencies

来源：评论

学校读者我要写书评

暂无评论

Lung Disease Classification Utilizing Convolutional Neural Network with CXR Imaging 3

Lung Disease Classification Utilizing Convolutional Neural N...

引用

3rd IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2023

作者： Orano, Jannie Fleur V. Maravillas, Elmer A. Orano, Jonah Flor V. College of Computer Studies and Information Technology Southern Leyte State University Southern Leyte Philippines College of Computer Studies Cebu Institute of Technology-University Cebu City Philippines Visayas State University Department of Computer Science and Technology Baybay City Philippines

ISBN: (纸本)9798350317022

Lung diseases present significant and widespread health challenges globally. Each year, a considerable portion of the world's population receives diagnoses for various lung conditions, affecting individuals of all ages, including adults, teenagers, children, smokers, and non-smokers alike. This classification underscores the status of lung diseases as a prominent cause of death and disability on a global scale. To enhance survival rates and prevent complications in the successful treatment of chest diseases, a Convolutional Neural Network (CNN) classification system was developed. This system focuses on the diagnosis of six distinct types of lung diseases-effusion, atelectasis, infiltration, nodule, mass and pneumothorax-through the analysis of chest X-rays. The dataset used for training the neural network model consisted of 8,125 sample images. The developed model demonstrated an impressive accuracy of 82.53% with a Cohen's kappa value of 0.788. This CNN classification model has practical utility and can be implemented on computer-based, mobile-based platforms, serving as supplementary tools for radiologists and doctors in the decision-making process during diagnostic evaluations of lung diseases. © 2023 IEEE.

关键词： Chest diseases Chest X-ray Convolution Neural Network Deep Learning Lung Disease Pneumothorax

来源：评论

学校读者我要写书评

暂无评论

Heterogeneity-Aware Federated Learning with Adaptive Client Selection and Gradient Compression 42

Heterogeneity-Aware Federated Learning with Adaptive Client ...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Jiang, Zhida Xu, Yang Xu, Hongli Wang, Zhiyuan Qian, Chen University of Science and Technology of China School of Computer Science and Technology China University of Science and Technology of China Suzhou Institute for Advanced Research China University of California Jack Baskin School of Engineering Department of Computer Science and Engineering United States

ISBN: (纸本)9798350334142

Federated learning (FL) allows multiple clients cooperatively train models without disclosing local data. However, the existing works fail to address all these practical concerns in FL: limited communication resources, dynamic network conditions and heterogeneous client properties, which slow down the convergence of FL. To tackle the above challenges, we propose a heterogeneity-aware FL framework, called FedCG, with adaptive client selection and gradient compression. Specifically, the parameter server (PS) selects a representative client subset considering statistical heterogeneity and sends the global model to them. After local training, these selected clients upload compressed model updates matching their capabilities to the PS for aggregation, which significantly alleviates the communication load and mitigates the straggler effect. We theoretically analyze the impact of both client selection and gradient compression on convergence performance. Guided by the derived convergence rate, we develop an iteration-based algorithm to jointly optimize client selection and compression ratio decision using submodular maximization and linear programming. Extensive experiments on both real-world prototypes and simulations show that FedCG can provide up to 5.3× speedup compared to other methods. © 2023 IEEE.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

ALL-MorphNet: A Novel Hybrid Deep Learning Architecture for Automated Acute Lymphoblastic Leukemia Diagnosis in Microscopic Images

ALL-MorphNet: A Novel Hybrid Deep Learning Architecture for ...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Lourdu Rayappan R. Parameswari Department of Computer Science and Information Technology School of Computing Sciences Vels Institute of Science Technology & Advanced Studies Chennai India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Acute lymphoblastic leukaemia (ALL) is the most common cancer in children, but early detection is difficult because its symptoms are often subtle and easy to miss. While automated diagnostic tools hold significant promise, they face numerous challenges. These include a lack of diverse data, unbalanced datasets, and the requirement for high-performance computing. To address these challenges, we developed ALL-MorphNet, a novel deep learning model designed to classify ALL cells from microscopic images. The model starts by using a convolutional stem block to capture small local details from the images. Next, a dynamic morphological block analyzes the images at multiple scales to capture both fine- and coarse-grained patterns. This step uses an attention mechanism to focus on the most important features. Subsequently, a fusion module concatenates these features without information loss. Finally, a hybrid transformer block incorporates long-range relationships into a comprehensive understanding of the image. We evaluated the model on the ALL-IDB2 dataset, achieving an accuracy of 94%, outperforming traditional CNNs, such as ResNet, VGG, and transformer-based models, which achieved 85-90% accuracy on the same dataset. Future studies will aim to improve the model practicality to a variety of datasets, multimodal inputs, and enhanced morphological processing. Additionally, we focused on optimising the framework for deployment in resource-constrained environments to ensure its applicability to real-world clinical workflows. This advancement contributes to enhancing early and precise ALL diagnostics and reducing healthcare disparities in both high-income and low-and-middle-income countries.

关键词： Deep learning Accuracy Attention mechanisms Microscopy Computational modeling Leukemia Medical services computer architecture Transformers Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Key-dependent cube attack on reduced Frit permutation in Duplex-AE modes

引用

science China(Information sciences) 2021年第3期64卷 226-228页

作者： Lingyue QIN Xiaoyang DONG Keting JIA Rui ZONG Institute for Advanced Study Tsinghua University Department of Computer Science and Technology Tsinghua University

Dear editor,Recently, the permutation-based cryptology becomes a good topic in symmetric-key research groups. Many dedicated ciphers are permutation-based, and researchers introduced lots of cryptographic permutations which were suitable for different applications(collision-resistant hashing, preimageresistant hashing, message authentication, message encryption, etc.). Frit(fault-resistant iterative transformation) is a new lightweight 384-bit cryptographic permutation proposed by Simon et al.

关键词： Information Systems and Communication Service

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：