检索结果-内蒙古大学图书馆

Xgboost Machine Learning Algorithm Utilised for Predictive Modelling of Bearing Capacity of Soils Stabilised by Cementitious Additives’-Enriched Eco-Friendly Pozzolans

SSRN

引用

SSRN 2022年

作者： Eyo, Eyo U. Abbey, Samuel J. Onyekpe, Uche Faculty of Environment and Technology Department of Engineering Design and Mathematics Civil Engineering Cluster University of the West of England Bristol United Kingdom Department of Data Science School of Science Technology and Health York St. John University United Kingdom

An estimation of the California Bearing Ratio (CBR) of a soil stabilised by an environmentally-friendly binder composite is one of the most important steps in the development of a correct mix design for subsequent application in the field. In this study, the Extreme Gradient Boosting (XGBoost) machine learning (ML) algorithm is applied to intelligently model the soaked CBR of potential soil subgrade materials stabilised by cementitious additives’-enriched agro-based pozzolanic materials. ML prediction suggests the range of proportion of the binder composite that could be adopted to stabilise a soil subgrade to achieve an optimum CBR value is between 10 – 15% by dry weight of the natural soil but with the quantity of agro-based pozzolans being 4 times more in the mix. Satisfactory performance of the XGBoost algorithm used is confirmed by the high coefficient of determination (R2) of 0.924 and mean absolute percentage error (MAPE) of 2.032 achieved from ML regression. For ML multiclass classification of the stabilised subgrade quality, very high performance (an average AUC of 0.910) indicated the model’s capacity to distinguish between class labels. ML diagnostic training and testing suggested a very strong dependence of CBR on the binders, compaction parameters at optimum conditions and the soils’ specific gravity. © 2022, The Authors. All rights reserved.

关键词： Soils

来源：评论

学校读者我要写书评

暂无评论

Software package for regression algorithms based on Gaussian Conditional Random Fields

Software package for regression algorithms based on Gaussian...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Tijana Markovic Vladan Devedzic Fang Zhou Zoran Obradovic School of Innovation Design and Engineering Malardalen University Vasteras Sweden Faculty of Organizational Sciences University of Belgrade Belgrade Serbia School of Data Science and Engineering East China Normal University Shanghai China Center for Data Analytics and Biomedical Informatics Temple University Philadelphia USA

The Gaussian Conditional Random Fields (GCRF) algorithm and its extensions are used for machine learning regression problems in which the attributes of objects and the correlation between objects should be considered when making predictions. These algorithms can be applied in different domains where problems can be seen as graphs, but their implementation requires complex calculations and good programming skills. This paper presents an open source software package that includes a tool with graphical user interface (GCRFs tool) and Java library (GCRFs library). GCRFs tool is software that integrates various GCRF-based algorithms and supports training and testing of those algorithms on real-world datasets. The main goal of GCRFs tool is to provide a straightforward and user-friendly graphical user interface that will simplify the use of GCRF-based algorithms. GCRFs Java library contains basic classes for GCRF concepts and can be used by researchers who have experience in Java programming. Also, this paper presents the results of a pilot usability evaluation of the GCRFs tool, where the software was evaluated with expert and non-expert users. This evaluation gave us detailed insight into the experiences and opinions of the users and helped us outline priorities for future development.

关键词： Training Java Machine learning algorithms Software packages Software algorithms Programming Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Long-term prediction of El Niño-Southern Oscillation using reservoir computing with data-driven realtime filter

arXiv

引用

arXiv 2025年

作者： Jinno, Takuya Mitsui, Takahito Nakai, Kengo Saiki, Yoshitaka Yoneda, Tsuyoshi School of Sustainable Design University of Toyama Toyama930-8555 Japan Faculty of Health Data Science Juntendo Univerity Chiba Urayasu279-0013 Japan The Graduate School of Environment Life Natural Science and Technology Okayama University Okayama700-8530 Japan Graduate School of Business Administration Hitotsubashi University Tokyo186-8601 Japan Graduate School of Economics Hitotsubashi University Tokyo186-8601 Japan

In recent years, the application of machine learning approaches to time-series forecasting of climate dynamical phenomena has become increasingly active. It is known that applying a band-pass filter to a time-series data is a key to obtaining a high-quality data-driven model. Here, to obtain longer-term predictability of machine learning models, we introduce a new type of band-pass filter. It can be applied to realtime operational prediction workflows since it relies solely on past time series. We combine the filter with reservoir computing, which is a machine-learning technique that employs a data-driven dynamical system. As an application, we predict the multi-year dynamics of the El Niño-Southern Oscillation with the prediction horizon of 24 months using only past time series. © 2025, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Emergent competition shapes the ecological properties of multi-trophic ecosystems

arXiv

引用

arXiv 2023年

作者： Feng, Zhijie Marsland, Robert Rocks, Jason W. Mehta, Pankaj Department of Physics Boston University BostonMA02215 United States Pontifical University of the Holy Cross Rome Italy Biological Design Center Boston University BostonMA02215 United States Faculty of Computing and Data Science Boston University BostonMA02215 United States

Ecosystems are commonly organized into trophic levels – organisms that occupy the same level in a food chain (e.g., plants, herbivores, carnivores). A fundamental question in theoretical ecology is how the interplay between trophic structure, diversity, and competition shapes the properties of ecosystems. To address this problem, we analyze a generalized Consumer Resource Model with three trophic levels using the zero-temperature cavity method and numerical simulations. We find that intra-trophic diversity gives rise to "emergent competition" between species within a trophic level due to feedbacks mediated by other trophic levels. This emergent competition gives rise to a crossover from a regime of top-down control (populations are limited by predators) to a regime of bottom-up control (populations are limited by primary producers) and is captured by a simple order parameter related to the ratio of surviving species in different trophic levels. We show that our theoretical results agree with empirical observations, suggesting that the theoretical approach outlined here can be used to understand complex ecosystems with multiple trophic levels. © 2023, CC BY.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Gamefication of Youth's Career Guidance Self-Identification

Gamefication of Youth's Career Guidance Self-Identification

引用

2022 International Conference on Smart Information Systems and Technologies, SIST 2022

作者： Poliakov, Mykyta Mezzane, Daoud Terenchuk, Svitlana Riabchun, Yuliia Rusnak, Patrik Biloshchytska, Svitlana Kyiv National University Of Construction And Architecture Department Of Information Technology Design And Applied Mathematics Kyiv Ukraine Inovative Materials Energy And Sustainable Devellopment Laboratpry Cadi Ayyad University Marrakech Morocco Kyiv National University Of Construction And Architecture Department Of Information Technology Kyiv Ukraine University Of Zilina Faculty Of Management Science And Informatics Zilina Slovakia Astana It University Department Of Computer Technology And Data Nur-Sultan Kazakhstan

ISBN: (数字)9781665467902

ISBN: (纸本)9781665467902

The work is devoted to solving the youth's professional orientation problem in modern conditions of limited offline communication. The urgency of development of new methods and tools of adolescents' professional orientation, which are based on modern information technologies, is shown. The research's focus is aimed at the introduction of computer game technologies in the work of career guidance centers, pre-university departments of colleges and higher education institutions. The expediency and effectiveness of the existing professional orientation computer game tasks usage in career guidance work with youth who need decision support at the stage of choosing a future profession are substantiated. It is shown that in the conditions of virtual reality the estimate reliability of personal qualities for compliance with a certain professional activity depends on the selection of game tasks. A clear criterion for automatic measurement of activity interest in professional activity, which depends on the task selection time, is proposed. There are fragments of computer game tasks that allow a person to self-estimate their ability to perform activities in different situations and professional relationships without communicating with career counselors and psychologists. © 2022 IEEE.

关键词： Computer games

来源：评论

学校读者我要写书评

暂无评论

Novel Analysis of Two Kinds Hybrid Models in Ferro Martial Inserting Variable Lorentz Force Past a Heated Disk:An Implementation of Finite Element Method

引用

Computer Modeling in Engineering & sciences 2023年第5期135卷 1393-1411页

作者： Enran Hou Umar Nazir Samaira Naz Muhammad Sohail Muhammad Nadeem Jung Rye Lee Choonkil Park Ahmed MGalal College of Mathematics Huaibei Normal UniversityHuaibei235000China Department of Applied Mathematics and Statistics Institute of Space TechnologyP.O.Box 2750Islamabad44000Pakistan Department of Mathematics Government College University FaisalabadFaisalabad38000Pakistan Department of Mathematics Khwaja Fareed University of Engineering&Information TechnologyRahim Yar Khan64200Pakistan School of Mathematics and Statistics Qujing Normal UniersityQujing655011China Department of Data Science Daejin UniversityKyunggi11159Korea Research Institute for Natural Sciences Hanyang UniversitySeoul04763Korea Mechanical Engineering Department College of EngineeringPrince Sattam Bin Abdulaziz UniversityWadi Addawaser11991Saudi Arabia Production Engineering and Mechanical Design Department Faculty of EngineeringMansoura UniversityMansouraP.O 35516Egypt

In this article,the rheology of Ferro-fluid over an axisymmetric heated disc with a variable magnetic field by considering the dispersion of hybrid nanoparticles is *** flow is assumed to be produced by the stretching of a rotating heated *** contribution of variable thermophysical properties is taken to explore themomentum,mass and thermal *** concept of boundary layermechanismis engaged to reduce the complex problem into a simpler one in the form of coupled partial differential equations *** complex coupled PDEs are converted into highly nonlinear coupled ordinary differential equations system(ODEs)and the resulting nonlinear flow problem is handled *** solution is obtained via finite element procedure(FEP)and convergence is established by conducting the grid-independent *** solution of converted dimensionless problem containing fluid velocity,temperature and concentration field is plotted against numerous involved emerging parameters and their impact is *** the obtained solution,it is monitored that higher values of magnetic parameter retard the fluid flow and escalating values of Eckert number results in to enhance temperature ***-fluid flow and heat energy for the case of the Yamada Ota hybrid model are higher than for the case of the Hamilton Crosser hybrid *** a model is applicable to the printing process,electronic devices,temperature measurements,engineering process and food-making *** amount of mass species is reduced *** impacts of chemical reaction and Schmidt parameter.

关键词： Ferro-fluid non-constant magnetic field heated disc thermal properties of nanoparticles hybrid correlations among nanoparticles

来源：评论

学校读者我要写书评

暂无评论

Vacancy-Type Defects in HfO2 Layers and Their Role in Amorphous-to-Crystalline Transition Studied by Monoenergetic Positron Beams

引用

IEEE Transactions on Semiconductor Manufacturing 2025年

作者： Uedono, Akira Kawakami, Kazuya Kuribara, Tatsunori Hasunuma, Ryu Harashima, Yosuke Shigeta, Yasuteru Ni, Zeyuan Yan, Ruolin Nakamura, Hideo Notake, Akira Moriya, Tsuyoshi Michishio, Koji Ishibashi, Shoji University of Tsukuba Faculty of Pure and Applied Science Tsukuba Ibaraki305-8573 Japan Nara Institute of Science and Technology Graduate School of Science and Technology Ikoma Nara630-0192 Japan Tokyo Electron Technology Solutions Ltd S-Technology Development Center Nirasaki Yamanashi650 Japan Tokyo Electron Technology Solutions Ltd Development Department1 Nirasaki Yamanashi407-0192 Japan Tokyo Electron Ltd Digital Design Center Sapporo Hokkaido060-0003 Japan Tokyo Electron Technology Solutions Ltd Software and Data Engineering Division Nirasaki Yamanashi407-0192 Japan National Institute of Advanced Industrial Science and Technology Research Institute for Measurement and Analytical Instrumentation Tsukuba Ibaraki305-8568 Japan National Institute of Advanced Industrial Science and Technology Research Center for Computational Design of Advanced Functional Materials Tsukuba Ibaraki305-8568 Japan

The annealing properties of vacancies in HfO2 layers deposited on Si substrates and their role in amorphous-to-crystalline transition were studied with monoenergetic positron beams. HfO2 layers with a thickness of 4.30 nm were fabricated by the atomic layer deposition technique. The major vacancytype defects in these layers were identified as a Hf vacancy (VHf) coupled with multiple oxygen vacancies (VOs) and larger vacancy clusters. After annealing at 500°C, the concentration of vacancy clusters started to increase, which was attributed to the agglomeration of intrinsic open spaces in the amorphous phase upon the phase transition from amorphous to monoclinic crystalline phases. The amorphous-crystalline transition started near the interface between the HfO2 layer and bottom electrodes (TiN). After the crystallization, the concentration of vacancy clusters decreased as the annealing temperature increased. © 2025 IEEE.

关键词： Hafnium oxides

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Medical Diagnostics with Transparent AI-Driven Decision Support Systems

Revolutionizing Medical Diagnostics with Transparent AI-Driv...

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： Annamalai M Tanusha Mittal Krishna Chaitanya Sunkara Himani Pandey Girish Jadhav Vivek Nemane Business Solution and Services Vinsys IT Services India Limited Pune India Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Oracle Cloud Engineering Data Center Design & Modeling AL/ML Expert North Carolina USA Department of Environmental Science ITM (SLS) Baroda University Vadodara India Department of Electrical Engineering Faculty of Engineering and Technology Parul institute of Engineering and Technology Parul University Post Limda India Faculty of Law Symbiosis Law School Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331528348

ISBN: (纸本)9798331528355

This study introduces an innovative AI-Driven Decision Support System (DSS) for revolutionizing healthcare diagnostics, emphasizing the use of Explainable AI (XAI) to enhance transparency and trust in medical decision-making. The proposed system integrates machine learning and deep learning algorithms to analyze and interpret complex medical data, providing clinicians with clear, understandable insights that support diagnostic accuracy and patient outcomes. The system was evaluated on a dataset of 25,000 patient records across multiple diagnostic domains, including cardiology, oncology, and radiology. Key performance metrics showed a significant improvement in diagnostic precision and explain ability. The model achieved an accuracy of 94.8% in diagnosing cardiac conditions, with an explanation accuracy of 92.1%, measured by how well the XAI techniques correlated with expert evaluations. For oncology cases, the system demonstrated an 87.5 % reduction in false positives, while maintaining an overall accuracy of 93.2%. In terms of clinician trust, surveys indicated a 35% increase in confidence when using the XAI-based system compared to traditional black-box models. Additionally, the time to generate diagnostic explanations was reduced by 40%, improving clinical workflow and decision-making efficiency. These results underscore the transformative potential of integrating XAI into healthcare decision support systems, providing not only accurate predictions but also interpretable insights that enhance trust and usability in medical diagnostics.

关键词： Decision support systems Deep learning Wireless communication Surveys Visualization Accuracy Oncology Medical diagnosis Usability Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Cyber Twin Technology for AI-Driven Real-Time Software Security in IoT Ecosystems

Cyber Twin Technology for AI-Driven Real-Time Software Secur...

引用

Mobile Networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： Krishna Chaitanya Sunkara Gulshan Dhasmana Ravi K S Nayana Yadav M Ishan Desai Rajmani Shankar Oracle Cloud Engineering Data Center Design & Modeling AL/ML Expert North Carolina USA Department of Computer Science & Engineering Graphic Era Deemed to be University Dehradun India Department of Mechanical Engineering Vidyavardhaka College of Engineering Mysuru India Department of Computer Science and Engineering AJ Institute of Engineering and Technology Mangalore India Department of Electrical Engineering Faculty of Engineering and Technology Parul institute of Engineering and Technology Parul University Gujarat India Faculty of Law Symbiosis Law School Symbiosis International (Deemed University) Pune India

ISBN: (数字)9798331528348

ISBN: (纸本)9798331528355

As Internet of Things (IoT) ecosystems grow more complex, ensuring real-time security has become a major challenge. Traditional security approaches are insufficient for handling dynamic and interconnected IoT networks, which are increasingly targeted by sophisticated cyber-attacks. To address these issues, new methodologies that combine real-time monitoring and adaptive security mechanisms are needed. Cyber Twin technology, an innovative extension of digital twin technology, presents a promising solution by creating AI-driven digital replicas of IoT devices and software systems for continuous security monitoring and management. This paper introduces a Cyber Twin Technology Framework for AI-driven real-time software security in IoT ecosystems. The framework employs advanced AI models, including Convolutional Neural Networks (CNNs) for anomaly detection and Generative Adversarial Networks (GANs) for synthetic data generation to simulate potential attack scenarios. A dynamic reinforcement learning module is integrated to optimize threat response strategies based on evolving threat patterns. By creating real-time digital replicas of IoT components, the Cyber Twin framework continuously monitors device behaviors, identifies anomalies, and autonomously initiates mitigation actions. The system is evaluated in a simulated IoT environment with over 500 interconnected devices. Experimental results demonstrate that the Cyber Twin framework achieved a 99.2% detection accuracy in identifying cyber threats, with a false positive rate of 1.3%. The dynamic response module reduced incident response time by 35% compared to traditional methods, enhancing the system's ability to neutralize potential threats in real-time. The use of GAN-based synthetic data also enabled proactive defense strategies, reducing attack success rates by 40% during testing. The Cyber Twin Technology Framework provides a robust solution for real-time software security in complex IoT ecosystems. By leveraging A

关键词： Accuracy Ecosystems Software systems Real-time systems Threat assessment Internet of Things Security Time factors Monitoring Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Covariance Linkage Assimilation method for Unobserved data Exploration

arXiv

引用

arXiv 2024年

作者： Harashima, Yosuke Miyake, Takashi Baba, Ryuto Takayama, Tomoaki Takasuka, Shogo Shigeta, Yasuteru Yamaguchi, Yuichi Kudo, Akihiko Fujii, Mikiya Graduate School of Science and Technology Nara Institute of Science and Technology Ikoma Nara630-0192 Japan Data Science Center Nara Institute of Science and Technology Ikoma Nara630-0192 Japan Research Center for Computational Design of Advanced Functional Materials National Institute of Advanced Industrial Science and Technology Ibaraki Tsukuba305-8568 Japan Center for Computational Sciences University of Tsukuba Ibaraki305-8577 Japan Faculty of Science Tokyo University of Science Shinjuku Tokyo162-8601 Japan Carbon Value Research Center Research Institute for Science & Technology Tokyo University of Science Noda Chiba278-8510 Japan Center for Material Research Platform Nara Institute of Science and Technology Ikoma Nara630-0192 Japan

This study proposes a materials search method combining a data assimilation technique based on a multivariate Gaussian distribution with Bayesian optimization. The efficiency of the search using this method was demonstrated using a pair of example functions. By combining Bayesian optimization with the data assimilation technique, the maximum value of the example function was found more efficiently compared to ordinary Bayesian optimization without the data assimilation. A practical demonstration was also conducted by constructing a data assimilation model for the bandgap of (Sr1−x1−x2Lax1Nax2)(Ti1−x1−x2Gax1Tax2)O3. The concentration dependence of the bandgap was analyzed, and synthesis was performed with chemical compositions in the sparse region of the training data points to validate the predictions. © 2024, CC BY.

关键词： data assimilation

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：