检索结果-内蒙古大学图书馆

Science, engineering and Business for Sustainable Development Goals (SEB-SDG), International conference on

作者： Oladapo Muyiwa Oladoja Adesola Grace Folorunso Taiwo Mobolaji Adegoke Sule Omeiza Bashiru Kingley Chinedu Arum Aliyu Abba Mustapha Department of Mathematics and Statistics First Technical University Ibadan Nigeria Department of Statistics FCAHPT Moor Plantation Ibadan Nigeria Department of Mathematical Sciences Prince Abubarkar Audu University Anyigba Nigeria Deparmtment of Statistics University of Nigeria Nsukka Nigeria Department of Mathematical Sciences University of Maiduguri Maiduguri Nigeria

One important environmental concern that has the potential to inflict serious ecological harm and also affect human life is a forest fire. Several factors can lead to forest fires, but uncertainties on the correct model specification can be a serious issue in the model selection processes. The variable selection approach Bayesian Model Averaging (BMA) accommodates for variability in model by aggregating the quantities by their Posterior Model Probabilities (PMP). This study used a model averaging strategy to model the major factors contributing to forest fires using a model prior that is uniform in choice as recommended by most in literature and uniform information parameter prior. The covariates Duff Moisture Code (DMC), and temperature with a Posterior Inclusion Probability (PIP) of 100% and a fairly large coefficient band appear to be the most relevant of the ten predictors investigated. Other relevant covariates in modeling burned area in the forest are y axis geographical coordinate with PIP of 91.8% and wind with PIP of 84.5%. With a Posterior Model Probability, the best model, 53.4%, found involves the y axis spatial coordinate, DMC, temperature and wind. Having a PIP of more than 50%, the four variables are important in modeling forest fires.

关键词： Temperature distribution Monte Carlo methods Uncertainty Codes Biological system modeling Input variables Moisture

来源：评论

学校读者我要写书评

暂无评论

Simulation of precision feeding systems for swine 13

Simulation of precision feeding systems for swine

引用

13th International conference Knowledge and Systems engineering, KSE 2021

作者： Pham, Linh Manh Nguyen-Ba, Hieu Nguyen, Hoai Son Le, Huy-Ham Vnu University of Engineering and Technology 144 Xuan Thuy Cau Giay Hanoi Viet Nam Vietnam National University of Agriculture Faculty of Animal Science Trau Quy Gia Lam Hanoi Viet Nam

ISBN: (纸本)9781665499750

Precision livestock farming has become an inevitable trend for agricultural industry in the world. In that field, precision feeding is widely acknowledged because of its potential to reduce feed costs, environmental footprint and to improve animal health and welfare. Precision feeding involves modern multidisciplinary technologies such as information technology, mechanics, electronics, automation, etc. Such a system consists of automatic troughs linked to a computer system to exploit data collected from the individual animals (e.g. body weight, feed intake and feeding behaviour), and/or from ambient sensors. Data is processed and analysed based on mathematical models to make predictions, warnings for farmers or to formulate diets that fit requirements of each individual animal at each production period. However, implementing such a system often requires high investment, which may go beyond the capabilities of smallholders and small/medium laboratories. Furthermore, the risk of implementing by design but not conforming to reality is very high. To avoid this problem, we introduce an agent-based modelling approach to simulate precision feeding systems for swine. Two simulation experiments were conducted to provide predictions about the growth of individual pigs and the usefulness of precision feeding systems over classic feeding models. © 2021 IEEE.

关键词： Computational methods

来源：评论

学校读者我要写书评

暂无评论

Modern extreme value statistics for Utopian extremes

arXiv

引用

arXiv 2023年

作者： Richards, Jordan Alotaibi, Noura Cisneros, Daniela Gong, Yan Guerrero, Matheus B. Redondo, Paolo Shao, Xuanjie School of Mathematics University of Edinburgh United Kingdom Statistics Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Harvard School of Public Health BostonMA United States Department of Mathematics California State University FullertonCA United States

Capturing the extremal behaviour of data often requires bespoke marginal and dependence models which are grounded in rigorous asymptotic theory, and hence provide reliable extrapolation into the upper tails of the data-generating distribution. We present a toolbox of four methodological frameworks, motivated by modern extreme value theory, that can be used to accurately estimate extreme exceedance probabilities or the corresponding level in either a univariate or multivariate setting. Our frameworks were used to facilitate the winning contribution of Team Yalla to the EVA (2023) conference Data Challenge, which was organised for the 13th International conference on Extreme Value Analysis. This competition comprised seven teams competing across four separate sub-challenges, with each requiring the modelling of data simulated from known, yet highly complex, statistical distributions, and extrapolation far beyond the range of the available samples in order to predict probabilities of extreme events. Data were constructed to be representative of real environmental data, sampled from the fantasy country of "Utopia". © 2023, CC BY.

关键词： Extrapolation

来源：评论

学校读者我要写书评

暂无评论

Estimated Posture for human Elbow Flexion in Acoustic Environments

Estimated Posture for Human Elbow Flexion in Acoustic Enviro...

引用

Smart Electronics and Communication (ICOSEC), International conference on

作者： P. Pandi Selvi V. Sangeetha Sathish Kumar L. D. Saravanan Manikandan J Department of Computer Science Mangayarkarasi of organization Paravai Tamil Nadu India Karpagam Academy of Higher Education Coimbatore TamilNadu India School of Computing Science and Engineering VIT Bhopal University Kotrikalan MP India

The present study proposes a novel approach to address the challenge of identifying smoking and phone usage behaviours among individuals amidst the intricate surroundings of construction sites. Specifically, the method involves the recognition of elbow flexor behaviours through posture estimation. The localization and detection of key points pertaining to the human upper body have been achieved through the application of AlphaPose. Subsequently, the present study introduces the HEFBD model, which is a mathematical framework that discriminates human elbow flexion behaviour. The model is constructed using human key points and is designed to identify the area that is relevant for recognising tiny objects while mitigating the impact on the complicated background. A method for image reconstruction with super-resolution is employed as a pre-processing technique for images that exhibit blurring. Furthermore, the performance of You Only Look Once (YOLO) has been enhanced through the incorporation of a tiny object identification layer and the integration of a convolutional inhibitory attention model, thereby improving its detection capabilities. The method has demonstrated an improvement in detection precision of 6.7 % and a reduction in false identification rates due to complex backgrounds of 12%. These outcomes outperform existing detect approaches and meet the requirements for immediate results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Monitoring the neural network modelling of wear behaviour of Ti-6Al-4 V reinforced with nano B₄C particle

Monitoring the neural network modelling of wear behaviour of...

引用

International conference on Advancements and Futuristic Trends in Mechanical and Materials engineering (AFTMME)

作者： Ramkumar, T. Selvakumar, M. Chandrasekar, P. Mohanraj, M. Krishnasharma, R. Dr Mahalingam Coll Engn & Technol Dept Mech Engn Pollachi 642003 India Dr Mahalingam Coll Engn & Technol Dept Automobile Engn Pollachi 642003 India Ambal Profess Grp Inst Dept Mech Engn Palladam 641662 India Hindusthan Coll Engn & Technol Dept Mech Engn Coimbatore 641032 Tamil Nadu India ST Hindu Coll Dept Phys Nagercoil 629002 India

The main objective of the study is to fabricate nano boron carbide (B4C) reinforced with titanium metal matrix composite (Ti-6Al-4 V) through powder metallurgy route. Composites preforms of Ti-6Al-4 V- (2-10) wt. % of nano boron carbide were fabricated. The characterization of the fabricated samples was preformed through Scanning electron microscope and X-Ray diffraction. Pin-on-disk wear testing machine was used to describe the lubricating wear behavior of the composites by varying loads and sliding distances. The surface morphology of worn out surfaces was also examined. Investigations over basic and functional properties of developed MMC revealed that the addition of nano B4C decrease the specific wear rate (SWR) and coefficient of friction (CoF). To predict the tribological properties of titanium matrix composites, Artificial Neural Network (ANN) technique was adopted to arrive at optimal values of the input parameters based on the experimental data. The results illustrated that the mathematical models of tribological properties of Ti-6Al-4 V-B4C are reliable with a less error and high level of accuracy. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Ti-6Al-4V Boron carbide SEM morphology Tribology ANN SWR

来源：评论

学校读者我要写书评

暂无评论

Meta-Analysis of Spread of Disease: COVID-19*

Meta-Analysis of Spread of Disease: COVID-19*

引用

International conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： Pranshul Agarwal Gurjot Kamal Kant Sharma Jasminder Kaur Sandhu Rakesh Sahu Computer Science Engineering Chandigarh Univeristy Electrical Engineering Chandigarh Univeristy Chandigarh Univeristy

It has become clear that statistical analysis of COVID-19 is an essential strategy for comprehending and containing the ongoing global pandemic. The purpose of this study is to examine the value of static analysis methods in examining the spread of the COVID-19 virus, its effects on human health, and the efficacy of containment measures. Static analytic approaches provide a thorough and quantitative evaluation of the COVID-19 pandemic by utilising data from numerous sources, including epidemiological reports, medical records, and social media platforms. With the help of this method, scientists and decision-makers can better understand the behaviour of the virus, locate possible hotspots, and create evidence-based mitigation strategies. In the context of COVID-19, static analysis is applied across a wide range of fields, including but not limited to data mining, machine learning, and statistical modelling. These methods make it possible to find hidden trends, forecast illness progression, and assess the success of public health initiatives. Furthermore, the efficiency and precision of decision-making processes are improved by the incorporation of static analysis with real-time data streams. Stakeholders can quickly adapt to new difficulties by keeping an eye on crucial indicators like infection rates, hospitalisations, and vaccine coverage. They can then tailor their activities to address these challenges.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Problems of Digitalization in the Protection of Works of Intellectual Property

Problems of Digitalization in the Protection of Works of Int...

引用

International conference on Control Systems, mathematical modelling, Automation and Energy Efficiency (SUMMA)

作者： Arushan A. Vartumyan Valeria N. Orobinskaya German G. Mikhailov Mikhail E. Levchenko Aleksandr Pachin Natalia N. Pachina Deputy Director for Research and Innovation Pyatigorsk Institute (branch) North Caucasus Federal University Pyatigorsk Russian Federation Department of Planning and Organization of Research Work Pyatigorsk Institute (branch) North Caucasus Federal University University Pyatigorsk Institute (branch) North Caucasus Federal University Pyatigorsk Russian Federation Department of Sociology Lipetsk State Technical University Lipetsk Russian Federation Faculty of Civil Engineering Lipetsk State Technical University Lipetsk Russian Federation

The article analyzes the actual problems and risks of digitalization of works of intellectual property in various types of civil law relations. The rapid pace of digitalization development introduces new products and solutions aimed at simplifying human life and increasing profits, but in turn, directly proportionally affect the decrease in confidentiality and security of intellectual work objects. Modern technologies provide new opportunities and at the same time cause new problems in their protection. Every year, cases of piracy and illegal distribution of intellectual property are rapidly increasing. In light of the geopolitical situation in the world and the increasing frequency of cyber-attacks, the security and preservation of the key rights and freedoms of the author and his works is a particularly important factor. This problem fundamentally affects the interests of the state in matters of sovereignty and the development of scientific, cultural, economic and other areas affecting the field of intellectual property. In this regard, the article discusses current methods of intellectual property protection. In this regard, the article discusses current methods of intellectual property protection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Deep Learning for Predictive modelling in Fluid Dynamics

Using Deep Learning for Predictive Modelling in Fluid Dynami...

引用

Artificial Intelligence, human-Computer Interaction and Robotics (AIHCIR), International conference on

作者： Saadaldeen Rashid Ahmed Ari Taha Guron Duaa A. Majeed Mohammed Abdul Malek Al Saadi Wameedh Abduladheem Zainab T. Al-Sharify Al-Lbraheemi Fuqdan Taj-Aldeen Naser Abdali Rafad Imad Kadhim Computer Science Department Bayan University Kurdistan Iraq Artificial Intelligence Engineering Department College of Engineering AI-Ayen University Thi-Qar Iraq Aeronautical Engineering Department Baghdad University Baghdad Iraq Department of Medical Instrumentation Techniques Engineering Al-Ma'moon University College Baghdad Iraq Pharmacy department Al Hikma University College Baghdad Iraq Chemical Engineering Birmingham University UK College of Dentistry University of Al-Ameed Karbala Iraq Mathematics Department College of Basic Education Misan University Misan Iraq Medical Devices Technology Engineering University of hilla Babylon Iraq

ISBN: (数字)9798331534035

ISBN: (纸本)9798331534042

Predictive modeling of fluid dynamics is vital for many engineering applications, but classical computational fluid dynamics (CFD) methods tend to suffer with high computing costs and low scalability, notably in the complicated turbulent flow regimes. In this work we investigate the use of deep learning models-specifically Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), and Physics-Informed Neural Networks (PINN s)-to develop predictive models that may supplement fluid dynamics simulations with potentially im-proved accuracy and efficiency. Perform an evaluation and comparison of the forecasting ability for the velocity fields of these models with an emphasis on turbulent flow regimes. The authors apply each model to a real-world fluid dynamics dataset, assessing their success across multiple axes: large-scale feature capture, localized interactions, and physical law adherence. However, the maj or findings demonstrate that PINN s had the best performance with a coefficient of determination (R2) of 0.97 and mean absolute error (MAE) of 0.015 across turbulent regions but relatively weaker CNNs and GNNs with an accuracy figure of 95%. Although CNNs were successful in modeling the large-scale flow features and GNN s were easy to extract localized interactions, PINN s delivered the most accurate results by adding the N avier-Stokes equations into the loss functions [11]. Abstract Smooth and accurate solutions are vital in fluid dynamics, especial-Iy for achieving physical consistency. This work highlights the potential of PINNs for obtaining such predictions, giving a pathway towards efficient simulations in practical applications.

关键词： Deep learning Training Accuracy Fluid dynamics Computational modeling Computational fluid dynamics Predictive models Feature extraction mathematical models Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Spintronic Device Potential in Neuromorphic Computing from a Device-Circuit Modeling Perspective

Spintronic Device Potential in Neuromorphic Computing from a...

引用

International conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Bashetty Suman N M Deepika B Rajalakshm Jay Singh Ginni Nijhawan Mazin Riyadh Department of Computer Science and Engineering MLR Institute of Technology Hyderabad Telangana India Institute of Aeronautical Engineering Dundigal Hyderabad Department of Computer Science New Horizon College of Engineering Bangalore Dept. of EEE GL Bajaj Institute of Technology & Management Greater Noida U.P. India Lovely Professional University Phagwara AL-Hameed College of Engineering Technology National University of Science and Technology Dhi Qar Iraq

Recent years have seen tremendous progress in the area of neuromorphic computing, which seeks to mimic the parallel processing power and energy efficiency of the human brain. From the standpoint of device-circuit modelling, this work explores how spintronic devices might improve the scalability and performance of neuromorphic systems. Utilizing the inherent spin of the electron and the magnetic moment that goes along with it, spintronics has special benefits in terms of non-volatility, low power consumption, and high integration density. We provide a thorough model that accurately depicts the complex behaviour of spintronic components and how they are incorporated into neuromorphic circuits. Our results suggest that spintronic devices may improve the overall efficiency of neuromorphic systems by reducing the power-delay product substantially. Furthermore, it is possible to realize synaptic capabilities and plasticity processes with better accuracy by using the intrinsic features of spintronic devices, such as magnetoresistance and spin-transfer torque. Additionally, the research identifies problems with device variability and suggests possible fixes. In summary, spintronic devices have great potential to transform the field of neuromorphic computing if they are properly modelled and integrated.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum Imprecise Bayesian Networks (QIBN) for modelling Socio-Ecological-Technical Systems under Uncertainty

Quantum Imprecise Bayesian Networks (QIBN) for Modelling Soc...

引用

International conference on System Reliability and Science (ICSRS)

作者： Umberto Alibrandi Enrico Zio Khalid M. Mosalam Department of Civil and Architectural Engineering Aarhus University Aarhus Denmark Centre de Recherche sur les Risques et les Crises (CRC) MINES Paris-PSL Sophia Antipolis France Energy Department Politecnico Milano Milano Italy Department of Civil and Environmental Engineering University of California Berkeley Berkeley CA USA

Socio-ecological-technical systems are dynamic ecosystems composed of natural and man-made elements, whose interactions are affected not only by the natural environment, but also culture, personal behaviour, politics, economics and social organisation. These systems must be resilient to respond systemically to shocks and stresses. To cope with the inherent uncertainty of load effects and resistances, safety analyses are often performed through risk-based methods. An interesting tool is represented from Bayesian Network (BN), a probabilistic graphical model useful for risk-informed decision making. A notable example of socio-ecological-technical systems is represented by urban ecosystems. They rely on infrastructures that are not stand-alone and are dependent on other systems (environmental, cyber, physical, and human) to which they are interconnected, i.e., forming a system of systems. Moreover, empirical findings show that humans tend to violate the expected utility metric and consequently violate the laws of Classical Probability (CP). Thus, novel methodologies are necessary to model, understand, and predict their dynamic responses. (ii) hidden interdependencies, where the variables of the BN can be dependent even if they are not linked nor sharing a common parent node, and (iii) human decision making under uncertainty. The promising features of QIBN are demonstrated through three benchmark examples of different nature: (a) two-stage gambling as an example of human decision making showing violation of the total probability theorem, (b) Structural Health Monitoring (SHM), and (c) damage monitoring through risk-informed digital twin technologies.

关键词：

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：