检索结果-内蒙古大学图书馆

Data Assimilation Enhances WRF-Chem Performance in Modeling Volcanic Ash Clouds from Hunga Tonga–Hunga Ha’apai Eruption

引用

Journal of Meteorological Research 2024年第6期38卷 1122-1140页

作者： Hosni SNOUN Mohammad Mosaed ALAHMADI Amirhossein NIKFAL Abderrazak ARIF William HATHEWAY Meznah A.ALAMRO Alaeddine MIHOUB Moez KRICHEN Numthaja Co. Ltd.Jeddah23345Saudi Arabia Jülich Supercomputing Centre(JSC) Forschungszentrum JülichJülich52428Germany Institut National de la Météorologie Tunis Carthage2035Tunisia Free Researcher AustinTexas78666USA Department of Information Technology College of Computer&Information SciencePrincess Nourah Bint Abdul Rahman UniversityRiyadh11564Saudi Arabia Department of Management Information Systems and Production Management College of Business and EconomicsQassim UniversityBuraidah51452Saudi Arabia Faculty of Computer Science and Information Technology(FCSIT) Al-Baha UniversityAl-Baha65528Saudi Arabia ReDCAD Laboratory University of SfaxSfax3038Tunisia

Volcanic eruptions release large amounts of ash clouds and gas aerosols into the atmosphere,which can be simulated by air quality prediction ***,the performance of these models remains unsatisfactory,even though both relevant physics and chemistry are ***,exploring the approaches for improvement such as inclusion of data assimilation is *** this study,we depict the modeling of the volcanic ash dispersion from the Hunga Tonga–Hunga Ha’apai underwater volcano,which erupted in a series of large explosions in late December 2021 and early January *** 15 January 2022,a particularly significant explosion sent a massive ash cloud high into the *** used the inline Weather Research and Forecasting model coupled with chemistry(WRF-Chem)and incorporated meteorological data assimilation within the Flux Adjusting Surface Data Assimilation System(FASDAS).We compared three forecast scenarios:one with only meteorology and no chemistry(OMET),one with gas and aerosol chemistry and no assimilation(NODA),and one with both chemistry and assimilation(FASDAS).We found that FASDAS resulted in lower planetary boundary layer height(PBLH),downward surface shortwave flux,and 2-m temperature by up to 800 m,200 W m^(−2),and 6℃ on the land portion,respectively,while the opposite was observed near the eruption *** validated the model against the observations and the results showed that FASDAS significantly enhanced the model performance in retrieving meteorological ***,the simulations also revealed significant biases in the concentration of volcanic ash around the ash *** from the Copernicus TROPOspheric Monitoring Instrument Sentinel-5 Precursor(TROPOMI-S5P)showed a westward trend of the total SO2 *** work demonstrates the significant contribution of data assimilation to the results of operational air quality predictions during violent volcanic eruption events.

关键词： Hunga Tonga-Hunga Ha’apai volcano WRF-Chem Flux Adjusting Surface Data Assimilation System(FASDAS) data assimilation SO2 TROPOspheric Monitoring Instrument Sentinel-5 Precursor(TROPOMI-S5P)

来源：评论

学校读者我要写书评

暂无评论

Navigation Design to Improve Interaction Technique in Multi-Browser Virtual Environment 15

Navigation Design to Improve Interaction Technique in Multi-...

引用

15th IEEE International Conference on Cognitive Infocommunications, CogInfoCom 2024

作者： Ichsan, Mochammad Hannats Hanafi Sik-Lanyi, Cecilia Guzsvinecz, Tibor Department of Electrical Engineering and Information Systems Faculty of Information Technology University of Pannonia Egyetem u. 10 Veszprem8200 Hungary Department of Informatics Faculty of Computer Science Brawijaya University Malang Indonesia Hungarian Research Network Piarista u. 4 Budapest1052 Hungary Department of Information Technology and its Applications Faculty of Information Technology University of Pannonia Gasparich M. u. 18/A Zalaegerszeg8900 Hungary

ISBN: (纸本)9798350378245

Efficient, precise, and intuitive navigation in a Virtual Environment (VE) or in desktop Virtual Reality (VR) is critical to improving user experience. This research introduces three navigation designs for physical embodiment inside VE using a computer mouse for multi-browser VE in desktop VR based on navigation possibilities. Navigation is intended for the First-Person Shooter (FPS) perspective: Intuitive Navigation (IntuNav), Edge Shift Navigation (EdgeNav), and Twist Shift Navigation (TwistNav). IntuNav uses mouse x and y coordinate movements to move and rotate the camera. EdgeNav relies on the cursor positioning at the edge of the screen for camera rotation and movement. TwistNav uses a middle click and right mouse click for camera movement and rotation. The current navigation design has been implemented in Unity with C#. This research proposed three model designs based on feasible navigation possibilities, which shows that each navigation model has unique advantages that can be adapted to user needs and preferences. Based on the test results using the System Usability Scale, IntuNav and EdgeNav obtained good results and can be used for further development. © 2024 IEEE.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Help Wanted - Challenges in Data Collection, Analysis and Communication of Cyber Threats in Security Operation Centers 17

Help Wanted - Challenges in Data Collection, Analysis and Co...

引用

17th International Conference on Wirtschaftsinformatik, WI 2022

作者： Basyurt, Ali Sercan Fromm, Jennifer Kuehn, Philipp Kaufhold, Marc-André Mirbabaie, Milad University of Duisburg-Essen Department of Computer Science and Applied Cognitive Science Duisburg Germany Technical University of Darmstadt Department of Computer Science Darmstadt Germany Paderborn University Department of Information Systems Paderborn Germany

Security Operation Centers are tasked with collecting and analyzing cyber threat data from multiple sources to communicate warning messages and solutions. These tasks are extensive and resource consuming, which makes supporting approaches valuable to experts. However, to implement such approaches, information about the challenges these experts face while performing these tasks is necessary. We therefore conducted semi-structured expert interviews to identify these challenges. By doing so, valuable insights into these challenges based on expert knowledge is acquired, which in return could be leveraged to develop automated approaches to support experts and address these challenges. © 2022 17th International Conference on Wirtschaftsinformatik, WI 2022. All rights reserved.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Feature Selection Framework for Predicting Students Performance

引用

computers, Materials & Continua 2022年第1期70卷 1893-1920页

作者： Maryam Zaffar Manzoor Ahmed Hashmani Raja Habib KS Quraishi Muhammad Irfan Samar Alqhtani Mohammed Hamdi High Performance Cloud Computing(HPC3) Department of Computer and Information SciencesUniversiti Teknologi PETRONAS32610SeriIskandarMalaysia Department of Computer Science and Information Technology University of LahorePakistan Department of Process Engineering Pakistan Institute of Engineering&Applied SciencesNiloreIslamabadPakistan Electrical Engineering Department College of EngineeringNajran UniversityNajran61441Saudi Arabia College of Computer Science and Information Systems Najran University61441NajranSaudi Arabia

Student performance prediction helps the educational stakeholders to take proactive decisions and make interventions,for the improvement of quality of education and to meet the dynamic needs of *** selection of features for student’s performance prediction not only plays significant role in increasing prediction accuracy,but also helps in building the strategic plans for the improvement of students’academic *** are different feature selection algorithms for predicting the performance of students,however the studies reported in the literature claim that there are different pros and cons of existing feature selection algorithms in selection of optimal *** this paper,a hybrid feature selection framework(using feature-fusion)is designed to identify the significant features and associated features with target class,to predict the performance of *** main goal of the proposed hybrid feature selection is not only to improve the prediction accuracy,but also to identify optimal features for building productive strategies for the improvement in students’academic *** key difference between proposed hybrid feature selection framework and existing hybrid feature selection framework,is two level feature fusion technique,with the utilization of cosine-based ***,according to the results reported in existing literature,cosine similarity is considered as the best similarity measure among existing similarity *** proposed hybrid feature selection is validated on four benchmark datasets with variations in number of features and number of *** validated results confirm that the proposed hybrid feature selection framework performs better than the existing hybrid feature selection framework,existing feature selection algorithms in terms of accuracy,f-measure,recall,and *** reported in presented paper show that the proposed approach gives more than 90%accuracy on benchmark dataset that is better tha

关键词： Educational data mining feature selection hybrid feature selection

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Fake News Detection Model Using fakenewslingual dataset with Feature Selection 12

An Ensemble Fake News Detection Model Using fakenewslingual ...

引用

12th IEEE Conference on systems, Process and Control, ICSPC 2024

作者： Choong, Hoi Chun Chua, Hui Na Jasser, Muhammed Basheer Wong, Richard T.K. Aldharhani, Ghassan Saleh Sunway University No. 5 School of Engineering and Technology Department of Computing and Information Systems Jalan Universiti Selangor Darul Ehsan Bandar Sunway47500 Malaysia Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur Malaysia UKM University Faculty of Information Science and Technology Selangor Bangi Malaysia

ISBN: (纸本)9798350391398

The rapid dissemination of information on social media acts as a double-edged sword, promoting the spread of accurate information and fake news, which can disrupt social cohesion and undermine trust in media and institutions. Existing fake news detection methods often lack feature comprehensiveness and struggle to generalize across different fake news types and sources. This study aims to enhance feature comprehensiveness by incorporating headline features into existing models and improve model generalization through ensemble techniques and hyperparameter tuning. The study expanded an existing dataset with headline, sentiment, and readability features. We assessed the impact of these additional features on model performance and explored various ensemble learning techniques (Bagging, AdaBoost, Gradient Boost) with tailored hyperparameters. An optimal model was then used to build a prototype for real and fake news classification. Integrating headline features showed marginally improved accuracy from 98.63% to 98.66%. While using ensemble learning models and hyperparameter tuning, accuracy increased significantly to 99.34%. This research enriched the dataset with headline features, enhancing the detection model's accuracy and generalization. The enhanced dataset, which we named fakenewslingual, has been made publicly available for further research. The study underscores the effectiveness of headline features and ensemble models in fake news detection. © 2024 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Automated Detection of Alzheimer's Disease Using EfficientNet-B3 Architecture with Transfer Learning 25

Automated Detection of Alzheimer's Disease Using EfficientNe...

引用

25th International Arab Conference on information Technology, ACIT 2024

作者： Aburomman, Ahmad Abuowaida, Suhaila Al-Momani, Adai Al Henawi, Esraa Elsoud, Esraa Abu Salah, Zaher Alzoubi, Haneen Chan, Huah Yong Khouj, Mohammed Zarqa University Department of Data Science and Ai Zarqa Jordan Al-Bayt University Department of Computer Science Ai Mafraq Jordan Zarqa University Department of Computer Science Zarqa Jordan The Hashemite University Department of Information Technology Zarqa Jordan Applied Science Private University Faculty of Information Technology Amman Jordan Universiti Sains Malaysia School of Computer Sciences Pulau Pinang Gelugor11800 Malaysia University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia

ISBN: (纸本)9798331540012

In order to bring forward expansion in both the accuracy and the processing speed of the detection of Alzheimer's disease, an automated approach for Alzheimer's disease diagnosis with passable EfficientNet-B3 neural network and transfer learning techniques is provided in this work. After direct fitness on a large number of annotated brain images, the model of EfficientNet-B3 is further trained, in an effort to obtain worse depicted quality connected with Alzheimer's Disease. To hasten the process of training and to make the model fit for this specific task, transfer learning was employed. The results of these experiments prove the efficiency of our approach to the diagnostic Alzheimer's disease compared to the most advanced and regular deep learning methods. Thus, the model may also withstand the test amidst diverse clinical populations by performing well in dementia classification with precision and recall performance coupled with over 99% accuracy. These findings demonstrate how the EfficientNet-B3 architecture and transfer learning enhance generalization across. © 2024 IEEE.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Addressing Disruptions in Traffic Light Control

引用

computers, Materials & Continua 2022年第5期71卷 2225-2247页

作者： Faizan Rasheed Kok-Lim Alvin Yau Rafidah Md Noor Yung-Wey Chong School of Engineering and Computer Science University of HertfordshireHatfieldAL109ABUK Department of Computing and Information Systems Sunway UniversitySubang Jaya47500Malaysia Faculty of Computer Science and Information Technology University of MalayaKuala Lumpur50603Malaysia National Advanced IPv6 Centre Universiti Sains MalaysiaUSMPenang11800Malaysia

This paper investigates the use of multi-agent deep Q-network(MADQN)to address the curse of dimensionality issue occurred in the traditional multi-agent reinforcement learning(MARL)*** proposed MADQN is applied to traffic light controllers at multiple intersections with busy traffic and traffic disruptions,particularly *** is based on deep Q-network(DQN),which is an integration of the traditional reinforcement learning(RL)and the newly emerging deep learning(DL)*** enables traffic light controllers to learn,exchange knowledge with neighboring agents,and select optimal joint actions in a collaborative manner.A case study based on a real traffic network is conducted as part of a sustainable urban city project in the Sunway City of Kuala Lumpur in *** is also performed using a grid traffic network(GTN)to understand that the proposed scheme is effective in a traditional traffic *** proposed scheme is evaluated using two simulation tools,namely Matlab and Simulation of Urban Mobility(SUMO).Our proposed scheme has shown that the cumulative delay of vehicles can be reduced by up to 30%in the simulations.

关键词： Artificial intelligence traffic light control traffic disruptions multi-agent deep Q-network deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

ProMIL: Probabilistic Multiple Instance Learning for Medical Imaging 26

ProMIL: Probabilistic Multiple Instance Learning for Medical...

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Struski, Lukasz Rymarczyk, Dawid Lewicki, Arkadiusz Sabiniewicz, Robert Tabor, Jacek Zieliński, Bartosz Faculty of Mathematics and Computer Science Jagiellonian University Poland Faculty of Applied Computer Science University of Information Technology and Management Rzeszow Poland Department of Pediatric Cardiology and Congenital Heart Diseases Medical University of Gdansk Poland Ues Ltd. Doctoral School of Exact and Natural Sciences Jagiellonian University Poland

ISBN: (纸本)9781643684369

Multiple Instance Learning (MIL) is a weakly-supervised problem in which one label is assigned to the whole bag of instances. An important class of MIL models is instance-based, where we first classify instances and then aggregate those predictions to obtain a bag label. The most common MIL model is when we consider a bag as positive if at least one of its instances has a positive label. However, this reasoning does not hold in many real-life scenarios, where the positive bag label is often a consequence of a certain percentage of positive instances. To address this issue, we introduce a dedicated instance-based method called ProMIL, based on deep neural networks and Bernstein polynomial estimation. An important advantage of ProMIL is that it can automatically detect the optimal percentage level for decision-making. We show that ProMIL outperforms standard instance-based MIL in real-world medical applications. We make the code available. © 2023 The Authors.

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cardiovascular Disease Analytics with Demographic and Behavioral Risk Features through Unsupervised and Ensemble Learning Techniques 12

Enhancing Cardiovascular Disease Analytics with Demographic ...

引用

12th IEEE Conference on systems, Process and Control, ICSPC 2024

作者： Sem, Li Xiang Chua, Hui Na Jasser, Muhammed Basheer Wong, Richard T.K. Aldharhani, Ghassan Saleh Sunway University No. 5 Jalan Universiti School of Engineering and Technology Department of Computing and Information Systems Bandar Sunway Selangor Darul Ehsan47500 Malaysia Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur Malaysia UKM University Faculty of Information Science and Technology Selangor Bangi Malaysia

ISBN: (纸本)9798350391398

Cardiovascular diseases (CVD) are a leading health concern, projected to affect 23.6 million people by 2030. Despite extensive research, challenges remain in conventional diagnostic accuracy and limited healthcare access in low-income communities. Current computing methods for detecting CVD rely on costly medical tests. Subsequently, prior studies have documented many inconsistent insights on the development of CVD due to variations in study design and demographics. This research addresses these gaps by studying the potential of incorporating demographics and behavioral risk factors for CVD detection and experimenting with various modeling and sampling techniques to address imbalanced target distributions and improve detection accuracy. The resampled BRFSS dataset was subjected to regression analysis to capture demographic trends in CVD development, with two cross-referenced datasets for comparison. Association rule mining identified key risk factors linked to CVD. Classifiers, including XGBoost, Random Forest, SVM, Multilayer Perceptron, and Logistic Regression, were used to establish baseline performance, and these classifiers were integrated into CatBoost as a meta-classifier using a stacking ensemble approach. Our findings indicate that demographic factors significantly influence CVD development, but effects vary by region, culture, and lifestyle. Key risk factors such as diabetes, smoking, and stroke were identified as significant contributors to CVD. Our experiment results show that leveraging full features set with fine-tuned ensemble stacking techniques increases model performance and achieves an accuracy of 96%. Our research contributes valuable insights into the consistency of demographic effects and identifies key risk factors for CVD. The proposed ensemble model demonstrates exceptional performance, highlighting its potential as a cost-effective tool for early cardiac detection and improved healthcare accessibility. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Identifying Travel Modes Using GPS Trajectories: A Short Review

Identifying Travel Modes Using GPS Trajectories: A Short Rev...

引用

International Conference on Communications, Signal Processing, and their Applications (ICCSPA)

作者： Samer Murrar Mahmoud H. Qutqut Fatima Al-Haj Faculty of Information Technology Applied Science Private University Amman Jordan Faculty of Computer Science University of New Brunswick Fredericton NB Canada

ISBN: (数字)9798350384819

ISBN: (纸本)9798350384826

Intelligent Transportation systems (ITS) depend on precisely identifying travel modes from GPS data, which is crucial for optimizing traffic management, enhancing road safety, and making informed urban planning decisions. The ubiquity of mobile devices has led to a rapid increase in GPS data collection, which challenges practical data analysis. This paper evaluates the performance of three sophisticated deep learning frameworks for classifying travel modes from GPS trajectories: the Convolutional Encoder-Recurrent Conditional Random Field (ConvEncoder-CRFR), the Convolutional Neural Network (CNN) ensemble with Discrete Wavelet Transform (DWT), and the Long Short-Term Memory (LSTM)-based Deep Neural Network (DNN). This analysis delves into each method's capabilities to distinguish between various travel modes, such as walking, biking, bus, car, and train. Moreover, it emphasizes the broader implications of these techniques in advancing ITS functionality and contributing to developing more intelligent and sustainable urban environments.

关键词： Performance evaluation Reviews Urban planning Transportation Transforms Road safety Mobile handsets Discrete wavelet transforms Convolutional neural networks Global Positioning System

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：