检索结果-内蒙古大学图书馆

Forecasting stock market returns using deep learning and time series techniques: a comparative and empirical study using technical indicators

引用

Multimedia Tools and Applications 2024年 1-21页

作者： Fahd, Kalloubi Badr, Hirchoua Eddine, Labiad Salah Mouad, Aterhi LTI Laboratory National School of Applied Sciences El Jadida Morocco Casablanca Morocco Modeling Simulation and Data Analysis Mohammed VI Polytechnic University Ben Guerir Morocco

Deep learning models enable learning strategic and accurate behaviors. Nevertheless, training accurate models in dynamic environments, such as stock markets, has been a long-standing challenge. They suffer from partial observability, long-term dependencies, and require merging different handcrafted features. Moreover, selecting the model architecture and fine-tuning different parameters is very challenging. In this paper, we conduct a comparative and empirical study of different possible scenarios. We demonstrate and provide a solid recommendation for possible network architectures. Precisely, we compare different recurrent neural network models alongside time series techniques and report their influence on out-of-sample stock returns. Furthermore, we run an empirical study to determine the best features and hyperparameters using several feature importance techniques. Strong technical indicators have fueled the input prices to push the input representation forward. Extensive experiments have been presented to evaluate the performance of different models, and the results are critically analyzed and empirically verified. The results demonstrate that bidirectional recurrent neural networks and the autoregressive integrated moving average with explanatory variable model provide better performances in predicting the following day’s closing price and provide better references and insights for future investments. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Numerical simulation of process analysis and sensitivity analysis of factors influencing liquid hydrogen release in open spaces

引用

Renewable Energy 2025年 252卷

作者： Liang, Yanwei Qu, Yongfeng Peng, Nan Ghidaglia, Jean-Michel Liu, Liqiang Zuo, Jiansheng Liu, Hongmin Ke, Changlei Li, Kongrong State Key Laboratory of Cryogenic Science and Technology Technical Institute of Physics and Chemistry Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing China Centre Borelli University of Paris-Saclay Gif-sur-Yvette 91190 France Modeling Simulation & Data Analysis UM6P Benguerir Morocco

Hydrogen is considered an ideal clean energy and is expected to gradually replace fossil fuels. Among the methods of hydrogen storage and transportation, liquid hydrogen storage offers the advantages of high energy density, safety at low temperatures, and the absence of high-pressure equipment, making it the most suitable method in many scenarios. However, in the event of an accidental liquid hydrogen leak, it will rapidly evaporate in large quantities, potentially causing significant hazards. A research project based on the open-source computational fluid dynamics (CFD) code, OpenFOAM, has been initiated for this purpose. The validity of the numerical model was confirmed by comparing it with NASA's large-scale liquid hydrogen release experiments conducted in open spaces, specifically through comparisons of hydrogen concentration contours and data collected by sensors. The deviations between the simulation results and the experimental data were within an acceptable range. The effects of atmospheric wind speed, ground type, atmospheric pressure, temperature, and release duration on the liquid hydrogen release process were analyzed. The changes in hydrogen concentration, the maximum movement distance of the hydrogen cloud, and the volume of the hydrogen cloud over time were analyzed and compared under different conditions. Finally, the impact of these factors on liquid hydrogen release within their possible natural ranges was compared. It was found that under natural conditions, atmospheric wind speed and release duration significantly affect liquid hydrogen release more than other factors. When atmospheric wind speed is high, more attention should be paid to preventing leaks, as the potential hazard downwind is enormous. In the event of a leak, it should be stopped as soon as possible to minimize the release duration. © 2025 Elsevier Ltd

关键词： Wind effects

来源：评论

学校读者我要写书评

暂无评论

Progress and trends in liquid hydrogen release

引用

International Journal of Hydrogen Energy 2025年

作者： Liang, Yanwei He, Ming Qu, Yongfeng Peng, Nan Ghidaglia, Jean-Michel Liu, Liqiang State Key Laboratory of Cryogenic Science and Technology Technical Institute of Physics and Chemistry Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing China Centre Borelli University of Paris-Saclay Gif-sur-Yvette91190 France Modeling Simulation & Data Analysis UM6P Benguerir Morocco

Liquid hydrogen (LH2) is a promising method for large-scale, long-distance storage and transportation of green energy. However, LH2 leaks pose significant safety risks, such as fire and explosion, due to the rapid formation of gaseous hydrogen. Therefore, understanding the release behavior of LH2 is crucial for ensuring energy security and advancing hydrogen energy applications. This paper reviews the evolution of research on LH2 release behavior, highlighting key experimental and modeling studies. By combining bibliometric methods, the paper presents progress and trends from the micro level (specific research activities) to the macro level (statistical literature information). The Web of Science Core Collection was searched using keywords such as "liquid hydrogen" + "leakage," resulting in 571 relevant articles. After the manual screening, 349 valid articles were retained. The paper identifies a surge in research activity in recent years, particularly in countries such as China, the United States, and Japan. Despite this progress, there remains a lack of systematic studies and open-access data in certain areas. The paper also outlines advancements and trends in experimentation and modeling, which are crucial for the safe and effective use of LH2 in energy systems. © 2025 Hydrogen Energy Publications LLC

关键词： Hydrogen storage

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Finite Element Algorithm for Thermal Darcy Flows with Variable Viscosity 1

引用

21st International Conference on Computational Science, ICCS 2021

作者： Salhi, Loubna El-Amrani, Mofdi Seaid, Mohammed Laboratory Modeling Simulation and Data Analysis University Mohammed VI Polytechnic Benguerir Morocco Mathematics and Applications Laboratory FST Abdelmalek Essaadi University Tangier Morocco Department of Engineering University of Durham South Road DurhamDH1 3LE United Kingdom International Water Research Institute University Mohammed VI Polytechnic Benguerir Morocco

ISBN: (数字)9783030779801

ISBN: (纸本)9783030779795

This paper deals with the development of a stable and efficient unified finite element method for the numerical solution of thermal Darcy flows with variable viscosity. The governing equations consist of coupling the Darcy equations for the pressure and velocity fields to a convection-diffusion equation for the heat transfer. The viscosity in the Darcy flows is assumed to be nonlinear depending on the temperature of the medium. The proposed method is based on combining a semi-Lagrangian scheme with a Galerkin finite element discretization of the governing equations along with an robust iterative solver for the associate linear systems. The main features of the enhanced finite element algorithm are that the same finite element space is used for all solutions to the problem including the pressure, velocity and temperature. In addition, the convection terms are accurately dealt with using the semi-Lagrangian scheme and the standard Courant-Friedrichs-Lewy condition is relaxed and the time truncation errors are reduced in the diffusion terms. Numerical results are presented for two examples to demonstrate the performance of the proposed finite element algorithm. © 2021, Springer Nature Switzerland AG.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

First principles investigations of the electronic and magnetic properties of RVO3 (R = Er, Ho, Y, Lu) vanadates

arXiv

引用

arXiv 2022年

作者： Jmal, Sohail Ait Balli, Sohail Ait Bouhani, Hamza Mounkachi, Omar AMEEC Team LERMA International University of Rabat Parc Technopolis Rocade de Rabat- Salé 11100 Morocco Complex Systems and Interactions Ecole Centrale Casablanca Morocco Laboratory of Condensed Matter and Interdisciplinary Sciences Department of Physics Faculty of Sciences Mohammed V University in Rabat PO Box 1014 Rabat Morocco Modeling Simulation & Data Analysis Program Mohammed VI Polytechnic University Ben Guerir43150 Morocco

In this paper, we investigate the influence of the rare earth element (R) on the physical properties of RVO3 (R = Er, Ho, Y, Lu). For this purpose, a theoretical work is reported in this study using ab initio method with the intent of enhancing our knowledge of the electronic, and magnetic properties of RVO3 (R = Er, Ho, Y, Lu) compounds. The electronic properties of these materials show the presence of Jahn-Teller effect, with a band gap of approximately 0.58eV, 1.57eV, 1.12eV, 1.28eV, for ErVO3, HoVO3, YVO3, LuVO3, respectively. The magnetic contribution of Ho, Er, and V atoms in HoVO3, and ErVO3 compounds was disentangled using X-ray magnetic circular dichroism (XMCD). The magnetic anisotropies of RVO3 with (R = Er, Ho, Y, Lu) are studied and analyzed using spin orbit coupling. We noticed an easy axis of magnetization along the c-direction with strong magneto-crystalline anisotropy energies for the non-magnetic rare earth elements (R = Lu, Y)VO3. For the magnetic rare earth elements, the easy and hard magnetization direction were found to be along b-axis and c-axis, and a- axis and c-axis for HoVO3, and ErVO3, respectively. This means that instead of the standard magnetization demagnetization process, large thermal effects can be obtained by spinning their single crystals in constant magnetic fields. The exchange coupling between (Ho-V) is also found to be greater than the other exchange interactions in HoVO3. Accordingly, a large conventional magnetocaloric effect could be created in HoVO3, since the Ho Ising moments experience a metamagnetic transition. However, the magnetocaloric effect (MCE) is expected to be lower in ErVO3 due to the weak (Er-V) exchange coupling. © 2022, CC BY.

关键词： Holmium compounds

来源：评论

学校读者我要写书评

暂无评论

Investigation of the Electronic, Magnetic, Exchange Interactions, and Magnetocaloric Properties in Orthotitanate Oxides Rtio3 (R = Er, Ho)

SSRN

引用

SSRN 2023年

作者： Jmal, Sohail Ait Tamerd, Mohamed Ait Mounkachi, Omar Salvestrini, Jean Paul Balli, Mohamed AMEEC Team LERMA International University of Rabat Parc Technopolis Rocade de Rabat- Salé 11100 Morocco Laboratory of Condensed Matter and Interdisciplinary Sciences Department of Physics Faculty of Sciences Mohammed V University in Rabat PO Box 1014 Rabat Morocco Modeling Simulation & Data Analysis Program Mohammed VI Polytechnic University Ben Guerir43150 Morocco Institute of Applied Physics Mohammed VI Polytechnic University Lot 660 Hay Moulay Rachid BP 43150 Ben Guerir Morocco CNRS IRL 2958 Georgia Tech CNRS 2 rue Marconi Metz57070 France Georgia Institute of Technology School of Electrical and Computer Engineering AtlantaGA30332-0250 United States

Strong correlated materials are emerging materials in low magnetocaloric cooling applications. The development of these fields necessitates materials with appealing magnetic, and magnetocaloric features. In this context, Density Functional Theory (DFT) combined with Monte Carlo simulations (MCs) are performed to comprehensively examine various physical, and magnetic features of the orthorhombic perovskite-type RTiO3. A metallic behavior of (Ho, Er)TiO3 has been found via the density of state using GGA+U approach. X-ray magnetic circular dichroism (XMCD) was carried out to identify the magnetic contributions of Ho, Er, and Ti atoms in HoTiO3, and ErTiO3 compounds. The spin-orbit coupling was added in our calculations to study and evaluate the magnetocrystalline anisotropies of RTiO3 with (R= Ho, Er). We noticed an easy magnetization axis along the b-direction for HoTiO3, and along the c-direction for ErTiO3. Low magnetocrystalline anisotropy energies were found compared to other perovskite oxides such as RVO3, and RMnO3indicating that a weak rotating magnetocaloric effect (RMCE) is expected in (Ho, Er)TiO3. Moreover, the exchange coupling interactions were calculated using Ising model, the (Ti-Ti) interaction coupling is ferromagnetic, and larger than the other exchange interactions in (Ho, Er)TiO3. Furthermore, these exchange coupling interactions were utilized within the Heisenberg model for MCs, allowing us to understand the driving mechanisms underlying magnetocaloric and magnetic behaviors in (Ho, Er)TiO3. © 2023, The Authors. All rights reserved.

关键词： Perovskite

来源：评论

学校读者我要写书评

暂无评论

BCI System using a Novel Processing Technique Based on Electrodes Selection for Hand Prosthesis Control ⁎

引用

IFAC-PapersOnLine 2021年第15期54卷 364-369页

作者： Alisson Constantine Víctor Asanza Francis R. Loayza Enrique Peláez Diego Peluffo-Ordóñez Facultad de Ingeniería en Electricidad y Computación Escuela Superior Politécnica del Litoral ESPOL Campus Gustavo Galindo km 30.5 Vía Perimetral P.O. Box 09-01-5863 Guayaquil Ecuador Facultad de Ingeniería en Mecánica y Ciencias de la Producción Escuela Superior Politécnica del Litoral ESPOL Neuroimaging and Bioengineering Laboratory LNB Campus Gustavo Galindo km 30.5 Vía Perimetral P.O. Box 09-01-5863 Guayaquil Ecuador Smart Data Analysis Systems Group (SDAS Research Group - ***) Ben Guerir 47963 Morocco Modeling Simulation and Data Analysis (MSDA) Research Program Mohammed VI Polytechnic University Ben Guerir 47963 Morocco Faculty of Engineering Corporacion Universitaria Autónoma de Nariño Carrera 28 No. 19-24 Pasto Colombia 520001

This work proposes an end-to-end model architecture, from feature extraction to classification using an Artificial Neural Network. The feature extraction process starts from an initial set of signals acquired by electrodes of a Brain-Computer Interface (BCI). The proposed architecture includes the design and implementation of a functional six Degree-of-Freedom (DOF) prosthetic hand. A Field Programmable Gate Array (FPGA) translates electroencephalography (EEG) signals into movements in the prosthesis. We also propose a new technique for selecting and grouping electrodes, which is related to the motor intentions of the subject. We analyzed and predicted two imaginary motor-intention tasks: opening and closing both fists and flexing and extending both feet. The model implemented with the proposed architecture showed an accuracy of 93.7% and a classification time of 8.8y«s for the FPGA. These results present the feasibility to carry out BCI using machine learning techniques implemented in a FPGA card.

关键词： Bio-signals analysis Neural Networks Brain Computer Interface Embedded Systems FPGA

来源：评论

学校读者我要写书评

暂无评论

Classification of Subjects with Parkinson’s Disease using Finger Tapping dataset ⁎

引用

IFAC-PapersOnLine 2021年第15期54卷 376-381页

作者： Víctor Asanza Nadia N. Sánchez-Pozo Leandro L. Lorente-Leyva Diego Hernan Peluffo-Ordóñez Fancis R. Loayza Enrique Peláez Facultad de Ingeniería en Electricidad y Computación Escuela Superior Politécnica del Litoral ESPOL Campus Gustavo Galindo km 30.5 Vía Perimetral P.O. Box 09-01-5863 Guayaquil Ecuador Facultad de Ingeniería en Mecánica y Ciencias de la Producción Escuela Superior Politécnica del Litoral ESPOL Neuroimaging and Bioengineering Laboratory LNB Campus Gustavo Galindo km 30.5Vía Perimetral P.O. Box 09-01-5863 Guayaquil Ecuador Smart Data Analysis Systems Group (SDAS Research Group -***) Ben Guerir 47963 Morocco Modeling Simulation and Data Analysis (MSDA) Research Program Mohammed VI Polytechnic University Ben Guerir 47963 Morocco Faculty of Engineering Corporación Universitaria Autónoma de Nariño Carrera 28 No. 19-24 Pasto Colombia 520001

Parkinson’s disease is the second most common neurodegenerative disorder and affects more than 7 million people globally. In this work, we classify subjects with Parkinson’s disease using data from finger-tapping on a keyboard. We use a free database by Physionet with more than 9 million records, preprocessed to delete atypical data. In the feature extraction stage, we obtained 48 features. We use Google Colaboratory to train, validate, and test nine supervised learning algorithms that detect the disease. As a result, we achieve a degree of accuracy higher than 98%.

关键词： Parkinson’s disease Classification Machine Learning Finger Tapping

来源：评论

学校读者我要写书评

暂无评论

Health co-benefits of post-COVID-19 low-carbon recovery in Chinese cities

Nature Cities

引用

Nature Cities 2024年 695-705页

作者： Chenxi Lu Felix Creutzig Jiawei Hu Yingjian Huang Huibin Mo Ying Yu Yun Li Da Huo Xuanren Song Xiaoting Huang Zhu Liu Yun Sun Kai Liu Shaohui Zhang Karyn Morrissey Jinpyo Hong Zhu Deng Zhuanjia Du Mercator Research Institute on Global Commons and Climate Change Berlin Germany Sustainability Economics of Human Settlements Technical University Berlin Berlin Germany Belfer Center for Science and International Affairs Harvard Kennedy School Harvard University Cambridge MA USA Alibaba Cloud Hangzhou China Guangdong Key Laboratory for Urbanization and Geo-simulation School of Geography and Planning Sun Yat-sen University Guangzhou China Shenzhen Key Laboratory of Ecological Remediation and Carbon Sequestration Institute of Environment and Ecology Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Data-Driven EnviroLab Department of Public Policy University of North Carolina at Chapel Hill Chapel Hill NC USA Department of Environmental Sciences and Engineering Gillings School of Global Public Health University of North Carolina at Chapel Hill Chapel Hill NC USA Faculty of Engineering Science Department of Architecture KU Leuven Leuven Belgium Department of Earth System Science Ministry of Education Key Laboratory for Earth System Modeling Institute for Global Change Studies Tsinghua University Beijing China Department of Civil & Mineral Engineering University of Toronto Toronto Ontario Canada School of Environmental Science and Engineering Tianjin University Tianjin China Department of Geography King’s College London London UK Guangdong Holdings Limited Guangzhou China International Institute for Applied Systems Analysis (IIASA) Laxenburg Austria Division for Climate and Energy Policy Department of Technology Management and Economics Technical University of Denmark Lyngby Denmark School of Engineering Brown University Providence RI USA Department of Geography University of Hong Kong Hong Kong SAR China Department of Political Science Columbia University New York NY USA

Post-pandemic green recovery is pivotal in achieving global sustainable development goals by simultaneously revitalizing economies and reducing greenhouse gas emissions, air pollution and improving public welfare. However, subnational and city-level understanding of green recovery, its efficacy and its alignment with public health is poorly understood. Here we focus on post-COVID-19 low-carbon recovery—economic growth combined with reduced carbon emissions—and explore health co-benefits in Chinese cities. A novel near-real-time daily carbon emission dataset of 48 cities in China is developed, coupled with detailed health and economic municipal statistics and models. We find that, on average, six low-carbon-recovery cities, mainly megacities, saved 1.2 times as many lives per 100,000 population compared with the 42 other cities, and their annual monetary avoided premature deaths per 100,000 population was 1.5 times more than the 42 other cities. The accumulated monetary health co-benefits for low-carbon-recovery cities were US$ 4.2 billion (95% confidence interval, 2.1–6.3) during the post-COVID-19 period. We show that government spending on electric vehicles increases the likelihood of achieving low-carbon recovery in Chinese cities. Our results underscore the significant health co-benefits of low-carbon recovery, pointing to synergies between advancing local welfare and global environmental objectives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Autonomous migration of virtual machine based on OpenStack

引用

International Journal of Hybrid Information Technology 2016年第8期9卷 65-84页

作者： Zhou, Li Yu, Zhuoer Zhang, Jilin Wan, Jian Wu, Yusen School of Computer and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou China College of Electrical Engineering Zhejiang University Hangzhou310058 China School of Information and Electronic engineering Zhejiang University of Science & Technology Hangzhou310023 China Zhejiang Provincial Engineering Center on Media Data Cloud Processing and Analysis HangzhouZhejiang China

For the problem of compute nodes load unbalance leads to the overload node impact VM performance and the underload node waste electrical energy. Dynamic VM consolidation is an efficient approach for improving the utilization of servers and reducing energy costs. In this paper, we introduce dynamic consolidation into OpenStack and implement AMVM based on OpenStack. AMVM collect and analyze all performance data of VM and compute node in OpenStack. Then AMVM automatically schedules VM live migrate to the most appropriate node according to the real-time load of all compute nodes. Then we use hybrid-copy instead of pre-copy in AMVM to improve the efficiency of VM live migration. Finally, we analyze the performance of hybrid-copy, hybrid-copy can reduce page faults compared with post-copy and reduce total data transferred compared with pre-copy. © 2016 SERSC.

关键词： Virtual machine

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：