检索结果-内蒙古大学图书馆

A Neural Network-Based Approach to Normality Testing for Dependent Data

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kim, Minwoo Genton, Marc G. Huser, Raphaël Castruccio, Stefano Department of Statistics Pusan National University Korea Republic of Statistics program King Abdullah University of Science and Technology Saudi Arabia Department of Applied and Computational Mathematics and Statistics University of Notre Dame United States

There is a wide availability of methods for testing normality under the assumption of independent and identically distributed data. When data are dependent in space and/or time, however, assessing and testing the marginal behavior is considerably more challenging, as the marginal behavior is impacted by the degree of dependence. We propose a new approach to assess normality for dependent data by non-linearly incorporating existing statistics from normality tests as well as sample moments such as skewness and kurtosis through a neural network. We calibrate (deep) neural networks by simulated normal and non-normal data with a wide range of dependence structures and we determine the probability of rejecting the null hypothesis. We compare several approaches for normality tests and demonstrate the superiority of our method in terms of statistical power through an extensive simulation study. A real world application to global temperature data further demonstrates how the degree of spatio-temporal aggregation affects the marginal normality in the data. © 2023, CC BY.

关键词： Higher order statistics

Modeling of Measurement Error in Financial Returns Data

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jasra, Ajay Maama, Mohamed Mijatović, Aleksandar School of Data Science The Chinese University of Hong Kong Shenzhen China Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Department of Statistics University of Warwick United Kingdom

In this paper we consider the modeling of measurement error for fund returns data. In particular, given access to a time-series of discretely observed log-returns and the associated maximum over the observation period, we develop a stochastic model which models the true log-returns and maximum via a Lévy process and the data as a measurement error there-of. The main technical difficulty of trying to infer this model, for instance Bayesian parameter estimation, is that the joint transition density of the return and maximum is seldom known, nor can it be simulated exactly. Based upon the novel stick breaking representation of [12] we provide an approximation of the model. We develop a Markov chain Monte Carlo (MCMC) algorithm to sample from the Bayesian posterior of the approximated posterior and then extend this to a multilevel MCMC method which can reduce the computational cost to approximate posterior expectations, relative to ordinary MCMC. We implement our methodology on several applications including for real data. Copyright © 2024, The Authors. All rights reserved.

关键词： Markov chains

Advancing electrochemical impedance analysis through innovations in the distribution of relaxation times method

学校读者我要写书评

暂无评论

Joule 2024年第7期8卷 1958-1981页

作者： Maradesa, Adeleke Py, Baptiste Huang, Jake Lu, Yang Iurilli, Pietro Mrozinski, Aleksander Law, Ho Mei Wang, Yuhao Wang, Zilong Li, Jingwei Xu, Shengjun Meyer, Quentin Liu, Jiapeng Brivio, Claudio Gavrilyuk, Alexander Kobayashi, Kiyoshi Bertei, Antonio Williams, Nicholas J. Zhao, Chuan Danzer, Michael Zic, Mark Wu, Phillip Yrjänä, Ville Pereverzyev, Sergei Chen, Yuhui Weber, André Kalinin, Sergei V. Schmidt, Jan Philipp Tsur, Yoed Boukamp, Bernard A. Zhang, Qiang Gaberšček, Miran O'Hayre, Ryan Ciucci, Francesco Department of Mechanical and Aerospace Engineering The Hong Kong University of Science and Technology Hong Kong Metallurgical and Materials Engineering Colorado School of Mines Golden80401 United States Beijing Key Laboratory of Green Chemical Reaction Engineering and Technology Department of Chemical Engineering Tsinghua University Beijing China Green Energy Storage Trento38123 Italy Department of Manufacturing and Production Engineering Faculty of Mechanical Engineering and Ship Technology Institute of Machine and Materials Technology Gdańsk University of Technology Gdańsk Poland Electrode Design for Electrochemical Energy Systems University of Bayreuth Bayreuth Germany School of Chemistry University of New South Wales Sydney Australia School of Advanced Energy Sun Yat-Sen University Shenzhen China Sustainable Energy Center CSEM Neuchâtel2002 Switzerland Interdisciplinary Faculty of Science and Engineering Shimane University Matsue Japan Centre for Electronic and Optical Materials National Institute for Materials Science Tsukuba Japan Department of Civil and Industrial Engineering University of Pisa Pisa Italy Department of Materials Imperial College London Exhibition Road LondonSW7 2AZ United Kingdom Department of Chemical Engineering Massachusetts Institute of Technology Cambridge02139 United States Electrical Energy Systems University of Bayreuth Bayreuth Germany Ruder Boskovic Institute Zagreb Croatia Department of Materials and Minerals Resources Engineering National Taipei University Taipei Taiwan Finland Johann Radon Institute for Computational and Applied Mathematics Linz Austria School of Science and Engineering Nanjing Tech. University Nanjing China Karlsruhe Germany Department of Materials Science and Engineering University of Tennessee KnoxvilleTN37996 United States Physical Science Division Pacific Northwest National Laboratory RichlandWA99354 United States Systems Engineering for Electrical Energy Storage University of B

Electrochemical impedance spectroscopy (EIS) is widely used in electrochemistry, energy sciences, biology, and beyond. Analyzing EIS data is crucial, but it often poses challenges because of the numerous possible equivalent circuit models, the need for accurate analytical models, the difficulties of nonlinear regression, and the necessity of managing large datasets within a unified framework. To overcome these challenges, non-parametric models, such as the distribution of relaxation times (DRT, also known as the distribution function of relaxation times, DFRT), have emerged as promising tools for EIS analysis. For example, the DRT can be used to generate equivalent circuit models, initialize regression parameters, provide a time-domain representation of EIS spectra, and identify electrochemical processes. However, mastering the DRT method poses challenges as it requires mathematical and programming proficiency, which may extend beyond experimentalists’ usual expertise. Post-inversion analysis of DRT data can be difficult, especially in accurately identifying electrochemical processes, leading to results that may not always meet expectations. This article examines non-parametric EIS analysis methods, outlining their strengths and limitations from theoretical, computational, and end-user perspectives, and provides guidelines for their future development. Moreover, insights from survey data emphasize the need to develop a large impedance database, akin to an impedance genome. In turn, software development should target one-click, fully automated DRT analysis for multidimensional EIS spectra interpretation, software validation, and reliability. Particularly, creating a collaborative ecosystem hinged on free software could promote innovation and catalyze the adoption of the DRT method throughout all fields that use impedance data. © 2024 Elsevier Inc.

关键词： Electrochemical impedance spectroscopy

Diagnosis of Leukemia Disease Based on Enhanced Virtual Neural Network

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第11期69卷 2031-2044页

作者： K.Muthumayil S.Manikandan S.Srinivasan JoséEscorcia-Gutierrez Margarita Gamarra Romany F.Mansour Department of Information Technology PSNA College of Engineering and TechnologyDindigul624622India Department of Information Technology K.Ramakrishnan College of EngineeringTiruchirappalli621112India Department of Biomedical Engineering Saveetha School of EngineeringSIMATSChennai602105India Electronic and Telecommunicacions Program Universidad Autónoma del CaribeBarranquilla08001Colombia Department of Computational Science and Electronic Universidad de la CostaCUCBarranquilla08001Colombia Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharga72511Egypt

White Blood Cell(WBC)cancer or leukemia is one of the serious cancers that threaten the existence of human *** spite of its prevalence and serious consequences,it is mostly diagnosed through manual *** risks of inappropriate,sub-standard and wrong or biased diagnosis are high in manual ***,there is a need exists for automatic diagnosis and classification method that can replace the manual *** is mainly classified into acute and chronic *** current research work proposed a computer-based application to classify the *** the feature extraction stage,we use excellent physical properties to improve the diagnostic system’s accuracy,based on Enhanced Color Co-Occurrence *** study is aimed at identification and classification of chronic lymphocytic leukemia using microscopic images of WBCs based on Enhanced Virtual Neural Network(EVNN)*** proposed method achieved optimum accuracy in detection and classification of leukemia from WBC ***,the study results establish the superiority of the proposed method in automated diagnosis of *** values achieved by the proposed method in terms of sensitivity,specificity,accuracy,and error rate were 97.8%,89.9%,76.6%,and 2.2%,***,the system could predict the disease in prior through images,and the probabilities of disease detection are also highly optimistic.

关键词： White blood cells enhanced virtual neural networking segmentation feature extraction chronic lymphocytic leukemia

Dynamic Measure of Hyperuniformity and Nonhyperuniformity in Heterogeneous Media via the Diffusion Spreadability

学校读者我要写书评

暂无评论

Physical Review Applied 2022年第3期17卷 034022-034022页

作者： Haina Wang Salvatore Torquato Department of Chemistry Princeton University Princeton New Jersey 08544 USA Department of Chemistry Department of Physics Princeton Center for Theoretical Science Princeton Institute for the Science and Technology of Materials and Program in Applied and Computational Mathematics Princeton University Princeton New Jersey 08544 USA

Time-dependent interphase diffusion processes in multiphase heterogeneous media are ubiquitous phenomena in physics, chemistry and biology. Examples of heterogeneous media include composites, geological media, gels, foams, and cell aggregates. The recently developed concept of spreadability, S(t), provides a direct link between time-dependent diffusive transport and the microstructure of two-phase media across length scales [Torquato, S., Phys. Rev. E., 104 054102 (2021)]. To investigate the capacity of S(t) to probe microstructures of real heterogeneous media, we explicitly compute S(t) for well-known two-dimensional and three-dimensional idealized model structures that span across nonhyperuniform and hyperuniform classes. Among the former class, we study fully penetrable spheres and equilibrium hard spheres, and in the latter class, we examine sphere packings derived from “perfect glasses,” uniformly randomized lattices (URLs), disordered stealthy hyperuniform point processes, and Bravais lattices. Hyperuniform media are characterized by an anomalous suppression of volume fraction fluctuations at large length scales compared to that of any nonhyperuniform medium. We further confirm that the small-, intermediate-, and long-time behaviors of S(t) sensitively capture the small-, intermediate-, and large-scale characteristics of the models. In instances in which the spectral density χ~V(k) has a power-law form B|k|α in the limit |k|→0, the long-time spreadability provides a simple means to extract the value of the coefficients α and B that is robust against noise in χ~V(k) at small wave numbers. For typical nonhyperuniform media, the intermediate-time spreadability is slower for models with larger values of the coefficient B=χ~V(0). Interestingly, the excess spreadability S(∞)−S(t) for URL packings has nearly exponential decay at small to intermediate t, but transforms to a power-law decay at large t, and the time for this transition has a logarithmic divergence in th

关键词： Complex systems Diffusion Flows in porous media Rocks Composite materials Glassy systems Porous materials Random & disordered media

Modeling High-Resolution Spatio-Temporal Wind with Deep Echo State Networks and Stochastic Partial Differential Equations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Kesen Kim, Minwoo Castruccio, Stefano Genton, Marc G. Statistics Program King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Department of Statistics Pusan National University Busan46241 Korea Republic of Department of Applied and Computational Mathematics and Statistics University of Notre Dame Notre DameIN46556 United States

In the past decades, clean and renewable energy has gained increasing attention due to a global effort on carbon footprint reduction. In particular, Saudi Arabia is gradually shifting its energy portfolio from an exclusive use of oil to a reliance on renewable energy, and, in particular, wind. Modeling wind for assessing potential energy output in a country as large, geographically diverse and understudied as Saudi Arabia is a challenge which implies highly non-linear dynamic structures in both space and time. To address this, we propose a spatio-temporal model whose spatial information is first reduced via an energy distance-based approach and then its dynamical behavior is informed by a sparse and stochastic recurrent neural network (Echo State Network). Finally, the full spatial data is reconstructed by means of a non-stationary stochastic partial differential equation-based approach. Our model can capture the fine scale wind structure and produce more accurate forecasts of both wind speed and energy in lead times of interest for energy grid management and save annually as much as one million dollar against the closest competitive model. © 2024, CC BY.

关键词： Clean energy

COVID-19 Infected Lung Computed Tomography Segmentation and Supervised Classification Approach

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第7期68卷 391-407页

作者： Aqib Ali Wali Khan Mashwani Samreen Naeem Muhammad Irfan Uddin Wiyada Kumam Poom Kumam Hussam Alrabaiah Farrukh Jamal Christophe Chesneau Department of Computer Science Concordia College BahawalpurBahawalpur63100Pakistan Department of Computer Science&IT Glim Institute of Modern StudiesBahawalpur63100Pakistan Institute of Numerical Sciences Kohat University of Science&TechnologyKohat26000Pakistan Institute of Computing Kohat University of Science and TechnologyKohat26000Pakistan Program in Applied Statistics Department of Mathematics and Computer ScienceFaculty of Science and TechnologyRajamangala University of Technology ThanyaburiThanyaburi12110Thailand Departments of Mathematics Faculty of ScienceCenter of Excellence in Theoretical and Computational Science(TaCS-CoE)&KMUTT Fixed Point Research LaboratoryRoom SCL 802 Fixed Point LaboratoryScience Laboratory BuildingKing Mongkut’s University of Technology Thonburi(KMUTT)Bangkok10140Thailand Department of Medical Research China Medical University HospitalTaichung40402Taiwan College of Engineering Al Ain UniversityAl Ain64141United Arab Emirates Department of Mathematics Tafila Technical UniversityTafila66110Jordan Department of Statistics The Islamia University of BahawalpurBahawalpur63100Pakistan 11Department of MathematicsUniversitéde CaenLMNOCaen14032France

The purpose of this research is the segmentation of lungs computed tomography(CT)scan for the diagnosis of COVID-19 by using machine learning *** dataset contains data from patients who are prone to the *** contains three types of lungs CT images(Normal,Pneumonia,and COVID-19)collected from two different sources;the first one is the Radiology department of Nishtar Hospital Multan and Civil Hospital Bahawalpur,Pakistan,and the second one is a publicly free available medical imaging database known as *** the preprocessing,a novel fuzzy c-mean automated region-growing segmentation approach is deployed to take an automated region of interest(ROIs)and acquire 52 hybrid statistical features for each ***,12 optimized statistical features are selected via the chi-square feature reduction *** the classification,five machine learning classifiers named as deep learning J4,multilayer perceptron,support vector machine,random forest,and naive Bayes are deployed to optimize the hybrid statistical features *** is observed that the deep learning J4 has promising results(sensitivity and specificity:0.987;accuracy:98.67%)among all the deployed *** a complementary study,a statistical work is devoted to the use of a new statistical model to fit the main datasets of COVID-19 collected in Pakistan.

关键词： COVID-19 machine learning fuzzy c-mean deep learning J4

Riccati sub-equation method for solving fractional flood wave equation and fractional plasma physics equation

学校读者我要写书评

暂无评论

Partial Differential Equations in Applied mathematics 2024年 10卷

作者： Phoosree, Sirasrete Khongnual, Nattinee Sanjun, Jiraporn Kammanee, Athassawat Thadee, Weerachai Education Program in Mathematics Faculty of Education Suratthani Rajabhat University Suratthani 84100 Thailand Department of Mathematics Faculty of Science and Technology Nakhon Si Thammarat Rajabhat University Nakhon Si Thammarat 80280 Thailand Department of Mathematics Faculty of Science and Technology Suratthani Rajabhat University Suratthani 84100 Thailand Division of Computational Science (Mathematics) Faculty of Science Prince of Songkla University Songkhla Hat Yai 90110 Thailand Department of General Education Faculty of Liberal Arts Rajamangala University of Technology Srivijaya Songkhla 90000 Thailand

In the field of mathematical physics, the Riccati sub-equation method is an important tool for locating the analytical solutions of nonlinear space–time fractional equations. In this study, we provide the Riccati sub-equation method for solving the space–time fractional equation by means of the Ablowitz–Kaup–Newell–Segur (AKNS) equation and the generalized Zakharov–Kuznetsov–Benjamin–Bona–Mahony (GZK-BBM) equation, which explain the effect of flood waves and plasma physics, respectively, and reach new analytical solutions, including parameters. Each equation yields fifteen different solutions, which are in the form of generalized hyperbolic functions, generalized triangular functions, and rational functions. The effect of the arising graphs of both equations is in the form of kink waves and periodic waves, which are presented in 2D and 3D graphs. © 2024 The Author(s)

关键词： Ablowitz–Kaup–Newell–Segur equation Analytical solutions Fractional partial differential equations Generalized Zakharov–Kuznetsov–Benjamin–Bona–Mahony equation Riccati sub-equation method

High-frequency aware perceptual image enhancement

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Roh, Hyungmin Kang, Myungjoo The Interdisciplinary Program of Computational Science and Technology Seoul National University Seoul Korea Republic of Department of Mathematics Seoul National University Seoul Korea Republic of

In this paper, we introduce a novel deep neural network suitable for multi-scale analysis and propose efficient model-agnostic methods that help the network extract information from high-frequency domains to reconstruct clearer images. Our model can be applied to multi-scale image enhancement problems including denoising, deblurring and single image super-resolution. Experiments on SIDD, Flickr2K, DIV2K, and REDS datasets show that our method achieves state-of-the-art performance on each task. Furthermore, we show that our model can overcome the over-smoothing problem commonly observed in existing PSNR-oriented methods and generate more natural high-resolution images by applying adversarial training. © 2021, CC BY.

关键词： Image enhancement