检索结果-内蒙古大学图书馆

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： Vikram Puri Aman Kataria Sita Rani Piyush Kumar Pareek Center of Visualization and Simulation Duy Tan University Da Nang Vietnam Amity Institute of Defence Technology Amity University Noida Uttar Pradesh India Department of Computer Science and Engineering Guru Nanak Dev Engineering College Ludhiana India Dept. of Artificial Intelligence and Machine Learning Nitte Meenakshi Institute of Technology Bengaluru India

The healthcare system has become more reliant on the data collection capabilities of fast evolving IoT devices. Patient healthcare records (PHR) now contain additional information as a result. However, securing identities and guaranteeing data security have emerged as critical challenges in the healthcare system. When it comes to regulating PHR, many of the centralized and decentralized methods now in use struggle difficulties such as single point of failure, high transaction fees, slow throughput, and excessive latency. To address these concerns, a distributed ledger technology (DLT)-based framework named IOTA rather than a blockchain-based platform such as Ethereum or Polygon is proposed. The proposed framework considered the example of a hospital with several patients on the same and various floors. Furthermore, the suggested approach employs a real-time experimental setup for calculating the time and power consumption of the devices.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human Activity Classification using G-XGB

Human Activity Classification using G-XGB

引用

Data Science and Network Security (ICDSNS), International Conference on

作者： Aman Kataria Vikram Puri Piyush Kumar Pareek Sita Rani Amity Institute of Defence Technology Amity University Noida India Center of Visualization and Simulation Duy Tan University Da Nang Vietnam Dept. of Artificial Intelligence and Machine Learning and IPR Cell Nitte Meenakshi Institute of Technology Bengaluru India Department of Computer Science and Engineering Guru Nanak Dev Engineering College Ludhiana India

Wearable body sensors have recently gained popularity because they monitor user behaviors and vital indicators. These sensors are designed to monitor various physiological factors, such as motion, temperature, and heart rate, among others. Making sense of the data gathered by these sensors requires separating the dependent and independent features. The dependent parameters are those that body-worn sensors can read in this scenario. Examples of such elements include blood oxygen levels, heart rate, temperature, mobility, and airflow. These sensors capture data about a person's activity and health. The independent parameters in wearable body sensors are related to the dependent parameters, whereas the dependent parameters are those that the sensors can measure directly. Such characteristics include age, sex, weight, and environmental influences. For example, humidity and airflow might impair a temperature sensor's accuracy. The user's age or level of physical fitness may also influence the accuracy of a heart rate monitor. Activity monitors are used in this study to capture the actions of various people. Static and dynamic properties are derived from the activity monitor recording. The performance evaluations of the eight distinct machine-learning models that were created using the retrieved features are discussed in this paper. The Grid Search method is used to enhance the performance of the XGB model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast monte carlo simulation of dynamic power systems under continuous random disturbances

Fast monte carlo simulation of dynamic power systems under c...

引用

2020 IEEE Power and Energy Society General Meeting, PESGM 2020

作者： Qiu, Yiwei Lin, Jin Chen, Xiaoshuang Liu, Feng Songy, Yonghua Tsinghua University State Key Laboratory of Control and Simulation of Power Systems and Generation Equipment Department of Electrical Engineering Beijing100084 China The University of Macau Department of Electrical and Computer Engineering 999078 China

ISBN: (纸本)9781728155081

Continuous-time random disturbances from the renewable generation pose a significant impact on power system dynamic behavior. In evaluating this impact, the disturbances must be considered as continuous-time random processes instead of random variables that do not vary with time to ensure accuracy. Monte Carlo simulation (MCs) is a nonintrusive method to evaluate such impact that can be performed on commercial power system simulation software and is easy for power utilities to use, but is computationally cumbersome. Fast samplings methods such as Latin hypercube sampling (LHS) have been introduced to speed up sampling random variables, but yet cannot be applied to sample continuous disturbances. To overcome this limitation, this paper proposes a fast MCs method that enables the LHS to speed up sampling continuous disturbances, which is based on the Itô process model of the disturbances and the approximation of the Itô process by functions of independent normal random variables. A case study of the IEEE 39-Bus System shows that the proposed method is 47.6 and 6.7 times faster to converge compared to the traditional MCs in evaluating the expectation and variance of the system dynamic response. © 2020 IEEE.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Chances and Challenges of ChatGPT and Similar Models for Education in M&S

Chances and Challenges of ChatGPT and Similar Models for Edu...

引用

2023 Winter simulation Conference, WSC 2023

作者： Tolk, Andreas Barry, Philip Loper, Margaret L. Rabadi, Ghaith Scherer, William T. Yilmaz, Levent The Mitre Corporation Modeling and Analysis Innovation Center 1001 Research Park Blvd #200 CharlottesvilleVA22911 United States L3Harris Corporation Mission Analysis Group 2235 Monroe Street HerndonVA20171 United States Georgia Tech Research Institute Georgia Institute of Technology AtlantaGA30308 United States University of Central Florida School of Modeling Simulation and Training 3100 Technology Pkwy OrlandoFL32826 United States University of Virgina Department of Systems and Information Engineering CharlottesvilleVA22904 United States Auburn University Samuel Ginn College of Engineering Computer Science and Software Engineering AuburnAL36849 United States

ISBN: (纸本)9798350369663

This position paper summarizes the inputs of a group of experts from academia and industry presenting their view on chances and challenges of using ChatGPT within Modeling and simulation education. The experts also address the need to evaluate continuous education as well as education of faculty members to address scholastic challenges and opportunities while meeting the expectation of industry. Generally, the use of ChatGPT is encouraged, but it needs to be embedded into an updated curriculum with more emphasis on validity constraints, systems thinking, and ethics. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Digital Twins with Advances in simulation and Artificial Intelligence: Opportunities and Challenges

Enhancing Digital Twins with Advances in Simulation and Arti...

引用

simulation Winter Conference

作者： Simon J. E. Taylor Charles M. Macal Andrea Matta Markus Rabe Susan M. Sanchez Guodong Shao Department of Computer Science Modelling & Simulation Group Brunel University London Uxbridge UK Decision & Infrastructure Sciences Division Argonne National Laboratory Lemont IL USA Department of Mechanical Engineering Politecnico di Milano Milano Italy Department IT in Production and Logistics TU Dortmund University Dortmund Germany Operations Research Department Naval Postgraduate School Monterey CA USA Engineering Laboratory National Institute of Standards and Technology Gaithersburg MD USA

simulations are used to investigate physical systems. A digital twin goes beyond this by connecting a simulation with the physical system with the purpose of analyzing and controlling that system in real-time. In the past 5 years there has been a substantial increase in research into simulation and Artificial Intelligence (AI). The combination of simulation with AI presents many possible innovations. Similarly, combining AI with simulation presents further possibilities including approaches to developing trustworthy and explainable AI methods, solutions to problems arising from sparce or no data and better methods for time series analysis. Given the progress that has been made in Digital Twins and simulation and AI, what opportunities are there from combining these two exciting research areas? What challenges need to be overcome to achieve these? This article discusses these from the perspectives of six leading members of the Modeling & simulation community.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chances and Challenges of Chatgpt and Similar Models for Education in M&S 23

Chances and Challenges of Chatgpt and Similar Models for Edu...

引用

Proceedings of the Winter simulation Conference

作者： Andreas Tolk Philip Barry Margaret L. Loper Ghaith Rabadi William T. Scherer Levent Yilmaz The MITRE Corporation Modeling and Analysis Innovation Center Charlottesville USA L3Harris Corporation Mission Analysis Group Herndon USA Georgia Tech Research Institute Georgia Institute of Technology Atlanta USA University of Central Florida School of Modeling Simulation and Training Orlando USA University of Virgina Department of Systems and Information Engineering Charlottesville USA Auburn University Samuel Ginn College of Engineering Computer Science and Software Engineering Auburn USA

ISBN: (纸本)9798350369663

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assessing mechanisms for microbial taxa and community dynamics using process models

引用

mLife 2023年第3期2卷 239-252页

作者： Linwei Wu Yunfeng Yang Daliang Ning Qun Gao Huaqun Yin Naija Xiao Benjamin YZhou Si Chen Qiang He Jizhong Zhou Institute of Ecology Key Laboratory for Earth Surface Processes of the Ministry of EducationCollege of Urban and Environmental SciencesPeking UniversityBeijingChina Institute for Environmental Genomics University of OklahomaNormanOKUSA Department of Microbiology and Plant Biology University of OklahomaNormanOKUSA State Key Joint Laboratory of Environment Simulation and Pollution Control School of EnvironmentTsinghua UniversityBeijingChina School of Minerals Processing and Bioengineering Central South UniversityChangshaChina Department of Mathematics Lunt HallNorthwestern UniversityEvanstonIllinoisUSA Department of Civil and Environmental Engineering The University of TennesseeKnoxvilleTennesseeUSA Institute for a Secure and Sustainable Environment The University of TennesseeKnoxvilleTennesseeUSA School of Civil Engineering and Environmental Sciences University of OklahomaNormanOklahomaUSA Earth and Environmental Sciences Lawrence Berkeley National LaboratoryBerkeleyCaliforniaUSA School of Computer Science University of OklahomaNormanOKUSA

Disentangling the assembly mechanisms controlling community composition,structure,distribution,functions,and dynamics is a central issue in *** various approaches have been proposed to examine community assembly mechanisms,quanti-tative characterization is challenging,particularly in microbial ***,we present a novel approach for quantitatively delineating community assembly mechanisms by combining the consumer–resource model with a neutral model in stochastic differential *** time-series data from anaerobic bioreactors that target microbial 16S rRNA genes,we tested the applicability of three ecological models:the consumer–resource model,the neutral model,and the combined *** results revealed that model performances varied substantially as a function of population abundance and/or process *** combined model performed best for abundant taxa in the treatment bioreactors where process conditions were *** contrast,the neutral model showed the best performance for rare *** analysis further indicated that immigration rates decreased with taxa abundance and com-petitions between taxa were strongly correlated with phylogeny,but within a certain phylogenetic distance *** determinism underlying taxa and community dynamics were quantitatively assessed,showing greater determinism in the treatment bioreactors that aligned with the subsequent abnormal system *** its mechanistic basis,the framework developed here is expected to be potentially applicable beyond microbial ecology.

关键词： community assembly mechanisms consumer-resource model neutral model species dynamics

来源：评论

学校读者我要写书评

暂无评论

Towards responsible AI for education: Hybrid human-AI to confront the Elephant in the room

arXiv

引用

arXiv 2025年

作者： Hooshyar, Danial Šír, Gustav Yang, Yeongwook Kikas, Eve Hämäläinen, Raija Kärkkäinen, Tommi Gašević, Dragan Azevedo, Roger School of digital Technologies Tallinn University Tallinn Estonia Department of Education University of Jyväskylä Jyväskylä Finland Department of Computer Science Czech Technical University Prague Czech Republic Department of Computer Science and Engineering Gangneung-Wonju National University Wonju Korea Republic of School of Natural Sciences and Health Tallinn University Tallinn Estonia Faculty of Information Technology University of Jyväskylä Jyväskylä Finland Faculty of Information Technology Monash University ClaytonVIC Australia School of Modeling Simulation and Training University of Central Florida Orlando United States

Despite significant advancements in AI-driven educational systems and ongoing calls for responsible AI for education, multiple critical issues remain unresolved—acting as the elephant in the room within the AI in education, learning analytics, educational data mining, learning sciences, and educational psychology communities. This critical analysis paper identifies and examines nine persistent challenges that continue to undermine the fairness, transparency, and effectiveness of current AI methods and applications in education. These include: 1) the lack of clarity around what AI for education truly means—often ignoring the distinct purposes, strengths, and limitations of different AI families—and the growing trend of equating it with domain-agnostic, company-driven large language models;2) the widespread neglect of essential learning processes such as motivation, emotion, and (meta)cognition in AI-driven learner modelling and their contextual nature;3) the limited integration of domain knowledge and lack of stakeholder involvement in AI design and development;4) the continued use of non-sequential machine learning models on temporal educational data, which fails to capture the dynamics and dependencies critical to understanding real learning progressions;5) the misuse of non-sequential metrics to evaluate sequential or temporal models;6) using unreliable explainable AI methods to provide explanations for black-box models;7) ignoring ethical guidelines in addressing data inconsistencies during model training;8) use of mainstream AI methods for pattern discovery and learning analytics without systematic benchmarking, which risks leading to unreliable conclusions;and 9) focusing on global prescriptions while overlooking localized, student-specific recommendations. Supported by both theoretical and empirical research, we demonstrate how hybrid AI methods—specifically neural-symbolic AI—address the elephant in the room and serve as the foundation for building responsibl

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Exploring Machine Learning Techniques to Identify Important Factors Leading to Injury in Curve Related Crashes

arXiv

引用

arXiv 2023年

作者： Moeinaddini, Mehdi Pourmoradnasseri, Mozhgan Hadachi, Amnir Cools, Mario ITS Lab Institute of Computer Science University of Tartu Narva mnt 18 Tartu51009 Estonia LEMA Research Group Urban & Environmental Engineering Department University of Liège Liège Belgium Department of Informatics Simulation and Modelling KULeuven Campus Brussels Brussels Belgium Faculty of Business Economics Hasselt University Diepenbeek Belgium

Different factors have effects on traffic crashes and crash-related injuries. These factors include segment characteristics, crash-level characteristics, occupant level characteristics, environment characteristics, and vehicle level characteristics. There are several studies regarding these factors’ effects on crash injuries. However, limited studies have examined the effects of pre-crash events on injuries, especially for curve-related crashes. The majority of previous studies for curve-related crashes focused on the impact of geometric features or street design factors. The current study tries to eliminate the aforementioned shortcomings by considering important pre-crash events related factors as selected variables and the number of vehicles with or without injury as the predicted variable. This research used CRSS data from the National Highway Traffic Safety Administration (NHTSA), which includes traffic crash-related data for different states in the USA. The relationships are explored using different machine learning algorithms like the random forest, C5.0, CHAID, Bayesian Network, Neural Network, C&R Tree, Quest, etc. The random forest and SHAP values are used to identify the most effective variables. The C5.0 algorithm, which has the highest accuracy rate among the other algorithms, is used to develop the final model. Analysis results revealed that the extent of the damage, critical pre-crash event, pre-impact location, the trafficway description, roadway surface condition, the month of the crash, the first harmful event, number of motor vehicles, attempted avoidance maneuver, and roadway grade affect the number of vehicles with or without injury in curve-related crashes. © 2023, CC BY.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimal vaccination and treatment policies with constrained inequalities to study limited vaccination resources for a multistrain reaction–diffusion SEIR model of COVID-19

引用

Partial Differential Equations in Applied Mathematics 2024年 10卷

作者： El Alami Laaroussi, Adil El Bhih, Amine Rachik, Mostafa Applied Mathematics and Computer Science Team Higher Normal School Tetuan Abdelmalek Essaadi University Tétouan Morocco Laboratory of Analysis Modeling and Simulation Department of Mathematics and Computer Science Faculty of Sciences Ben M'Sik Hassan II University Casablanca BP 7955 Morocco Multidisciplinary Research and Innovation Laboratory (LPRI) Moroccan School of Engineering Sciences (EMSI) Casablanca Morocco

The availability of an effective vaccine is a major challenge in COVID-19 vaccination campaigns. In this article, we propose a comprehensive strategy incorporating distributed controls via vaccination and treatment while considering the limitations of available resources expressed as inequalities constrained. Our approach utilizes a spatiotemporal model that includes multiple strains of the virus and considers spatial heterogeneity, providing a more accurate representation of disease transmission. By using a generalized two-strain ODE model, we effectively capture the evolution of COVID-19, including various strains and variants. To validate our model, we establish the positivity and boundedness of the system's solution. Through the exploration of vaccination and treatment controls. Our study aims to reduce the spread of the disease between strains and identify optimal values that minimize the number of infected individuals and associated costs. This work provides useful insights into effective strategies for controlling the COVID-19 epidemic, even with limited vaccination resources. Furthermore, we demonstrate the existence of controls and describe their characterizations in terms of state and adjoint functions. The penalty method is used to treat the inequalities constrained. More importantly, our numerical simulation shows that adequate vaccination resources and simultaneous treatment can effectively reduce and even eliminate the spread of COVID-19. © 2024 The Author(s)

关键词： Forward-Backward Sweep numerical method Limited vaccine supply Optimal control with inequalities constraints SEIR spatiotemporal and multi-strain model

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：