检索结果-内蒙古大学图书馆

Autism Spectrum Disorder Prediction by an Explainable Deep Learning Approach

Computers, Materials & Continua 2022年第4期71卷 1459-1471页

作者： Anupam Garg Anshu Parashar Dipto Barman Sahil Jain Divya Singhal Mehedi Masud Mohamed Abouhawwash Computer Science and Engineering Department Thapar Institute of Engineering and TechnologyPatialaIndia School of Computer Science and Statistics Trinity College DublinDublinIreland University Institute of Biotechnology Chandigarh UniversityMohaliIndia Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA

Autism Spectrum Disorder (ASD) is a developmental disorderwhose symptoms become noticeable in early years of the age though it canbe present in any age group. ASD is a mental disorder which affects the communicational, social and non-verbal behaviors. It cannot be cured completelybut can be reduced if detected early. An early diagnosis is hampered by thevariation and severity of ASD symptoms as well as having symptoms commonly seen in other mental disorders as well. Nowadays, with the emergenceof deep learning approaches in various fields, medical experts can be assistedin early diagnosis of ASD. It is very difficult for a practitioner to identifyand concentrate on the major feature’s leading to the accurate prediction ofthe ASD and this arises the need for having an automated approach. Also,presence of different symptoms of ASD traits amongst toddlers directs tothe creation of a large feature dataset. In this study, we propose a hybridapproach comprising of both, deep learning and Explainable Artificial Intelligence (XAI) to find the most contributing features for the early and preciseprediction of ASD. The proposed framework gives more accurate predictionalong with the recommendations of predicted results which will be a vital aidclinically for better and early prediction of ASD traits amongst toddlers.

关键词： Deep learning explainable artificial intelligence autism spectrum disorder machine learning

来源：评论

学校读者我要写书评

暂无评论

A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts 41

A General Theory for Softmax Gating Multinomial Logistic Mix...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Nguyen, Huy Akbarian, Pedram Nguyen, TrungTin Ho, Nhat Department of Statistics and Data Sciences United States Department of Electrical and Computer Engineering The University of Texas Austin United States School of Mathematics and Physics The University of Queensland Australia Univ. Grenoble Alpes Inria CNRS Grenoble INP LJK France

Mixture-of-experts (MoE) model incorporates the power of multiple submodels via gating functions to achieve greater performance in numerous regression and classification applications. From a theoretical perspective, while there have been previous attempts to comprehend the behavior of that model under the regression settings through the convergence analysis of maximum likelihood estimation in the Gaussian MoE model, such analysis under the setting of a classification problem has remained missing in the literature. We close this gap by establishing the convergence rates of density estimation and parameter estimation in the softmax gating multinomial logistic MoE model. Notably, when part of the expert parameters vanish, these rates are shown to be slower than polynomial rates owing to an inherent interaction between the softmax gating and expert functions via partial differential equations. To address this issue, we propose using a novel class of modified softmax gating functions which transform the input before delivering them to the gating functions. As a result, the previous interaction disappears and the parameter estimation rates are significantly improved. Copyright 2024 by the author(s)

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Stochastic modeling and performance optimization of sludge digestion processing system using genetic algorithm

引用

International Journal of Information Technology (Singapore) 2022年第7期14卷 3391-3400页

作者： Kumar, Ashish Goyal, Drishty Sinwar, Deepak Saini, Monika Department of Mathematics & Statistics Manipal University Jaipur Rajasthan Jaipur 303007 India Department of Computer and Communication Engineering Manipal University Jaipur Jaipur-303007 Rajasthan India

The main objective of present study is to propose a novel stochastic model for performance optimization of sludge digestion processing system (SDPS). A SDPS is critical subsystem of sewage treatment plant configured using six subsystems. All the six subsystems are configured in series. The concept of parallel redundancy, cold standby redundancy, perfect repairs, and sufficient repair facilities used in the development of the model. Markov modeling is employed to develop the mathematical model of SDPS and set of Chapman–Kolmogorov is derived. The failure and repair rates followed the exponential distribution. To optimize the performance of the SDPS, population based heuristic approach genetic algorithm (GA) is adopted with uniform genetic operators. The experimental data is collected with the help of plant personals. The numerical and graphical results for various reliability measures of SDPS also derived to highlight the importance of the study. © 2022, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management.

关键词： Availability Genetic algorithm Markov modeling Mutation Population

来源：评论

学校读者我要写书评

暂无评论

Dynamic Spatial Durbin Modeling (Case: Percentage of Poor Population in Indonesia 2010-2019)

Dynamic Spatial Durbin Modeling (Case: Percentage of Poor Po...

引用

International Conference on mathematics, statistics and Data Science 2020, ICMSDS 2020

作者： Sunandi, E. Sumertajaya, I.M. Djuraidah, A. Wigena, A.H. Fitrianto, A. Statistics Program Department of Mathematics Bengkulu University Bengkulu Indonesia Department of Statistics IPB University Bogor Indonesia

The dynamic panel model assumes that each observation unit is independent of each other. But sometimes this assumption is violated, so there are spatial effects in the model. This study aimed to make percentage modeling of poverty in Indonesia using the Dynamic Spatial Durbin Model (DSDM). The data used in this study were secondary data obtained from the statistics Indonesia in the period 2010-2019. The parameter estimation method used in this model was the Maximum Likelihood (ML). According to Moral-Benito, Allison and Williams the ML method has the best performance when used on panel data that has small cross-section data dimensions. The results of this study indicated that spatial dependence, time lag, variables of Poverty Gap Index, Poverty Severity Index and Logarithm of Expenditures per Capita affect poverty in Indonesia significantly. Other results showed that DSDM was able to explain the diversity in models at 95.6 %. This seemed higher when it's compared to the Spatial Durbin Model (SDM). Thus, the result of the study proved that DSDM is the best model for modelling dynamic poverty data panel in Indonesia during 2010-2019. © Published under licence by IOP Publishing Ltd.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

A Bayesian Logit-Normal Model in Small Area Estimation

A Bayesian Logit-Normal Model in Small Area Estimation

引用

International Conference on mathematics, statistics and Data Science 2020, ICMSDS 2020

作者： Sunandi, E. Kurnia, A. Sadik, K. Notodiputro, K.A. Statistics Program Department of Mathematics Bengkulu University Bengkulu Indonesia Department of Statistics IPB University Bogor Indonesia

The Logit-Normal model is one of the GLM Bayes models with random covariates used in binary data. This study aimed to examine and evaluate the characteristics of the Logit-Normal model. The second objective was to apply the Logit-Normal model to estimate the proportion of poverty in the small area of Mukomuko District in Bengkulu Province. We used the Hierarchical Bayes (HB) method to estimate parameters model. The simulation results obtained from the optimum number of iterations and gibbs samples, namely 500 iterations and 100 gibbs samples, respectively. In addition, when seen the value of piHB has the same tendency with the parameter pi and piDE. The value of piHBH tends to overestimate at piHB 60%. Conversely, piHB tends to underestimate piHB > 60%. Furthermore, in the simulation results the estimated value of variance and MSE piHB tends to be smaller than the variance of proportion. The application of the HB method for Logit-Normal model in the Mukomuko District poverty data produces piHB which has the same tendency as the result of direct estimator (piDE). The majority (21 villages) value of var(piHB) are smaller or equal to the var(piDE). This indicates that the estimation using the HB method can improve the estimation of the proportion parameters obtained by using the direct estimation method on poverty data. © Published under licence by IOP Publishing Ltd.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

A Universal Transfer Theorem for Convex Optimization Algorithms Using Inexact First-order Oracles 41

A Universal Transfer Theorem for Convex Optimization Algorit...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Kerger, Phillip Molinaro, Marco Jiang, Hongyi Basu, Amitabh Department of Applied Mathematics and Statistics Johns Hopkins University Baltimore United States Microsoft Research Redmond United States Department of Computer Science PUC-Rio Rio de Janeiro Brazil Department of Civil and Environmental Engineering Cornell University Ithaca United States

Given any algorithm for convex optimization that uses exact first-order information (i.e., function values and subgradients), we show how to use such an algorithm to solve the problem with access to inexact first-order information. This is done in a "black-box" manner without knowledge of the internal workings of the algorithm. This complements previous work that consider the performance of specific algorithms like (accelerated) gradient descent with inexact information. In particular, our results apply to a wider range of algorithms beyond variants of gradient descent, e.g., projection-free methods, cutting-plane methods, or any other first-order methods formulated in the future. Further, they also apply to algorithms that handle structured nonconvexities like mixed-integer decision variables. Copyright 2024 by the author(s)

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Pseudopotential Lattice Boltzmann Analysis for Multicomponent Flow

引用

Communications in Computational Physics 2022年第9期32卷 1156-1178页

作者： Yong Zhao Gerald G.Pereira Shibo Kuang Zhenhua Chai Baochang Shi School of Mathematics and Statistics Changsha University of Science and TechnologyChangsha 410114HunanChina CSIRO Data61 Private Bag 10Clayton South 3168Australia ARC Research Hub for Computational Particle Technology Department of Chemical EngineeringMonash UniversityVictoria 3800Australia School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China

This paper presents a pseudopotential lattice Boltzmann analysis to show the deficiency of previous pseudopotential models,i.e.,inconsistency between equilibrium velocity and mixture *** rectify this problem,there are two strategies:decoupling relaxation time and kinematic viscosity or introducing a system mixture relaxation ***,we constructed two modified models:a two-relaxationtime(TRT)scheme and a triple-relaxation-time(TriRT)scheme to decouple the relaxation time and kinematic ***,inspired by the idea of a system mixture relaxation time,we developed three mixture models under different collision schemes,***-SRT,mix-TRT,and mix-TriRT ***,we derived the advection-diffusion equation for the multicomponent system and derived the mutual diffusivity in a ***,we conducted several numerical simulations to validate the analysis on these *** numerical results show that these models can obtain smaller spurious currents than previous models and have a wider range for the accessible viscosity ratio with fourth-order *** to previous models,presentmodels avoid complex matrix operations and only fourth-order isotropy is *** increased simplicity and higher computational efficiency of these models make them easy to apply to engineering and industrial applications.

关键词： Lattice Boltzmann method multicomponent flows Chapman-Enskog analysis

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Building Integrated Photovoltaic (BIPV): MANOVA Analysis 1

Performance Analysis of Building Integrated Photovoltaic (BI...

引用

1st Middle East and North Africa Solar Conference, MENA-SC 2023

作者： Alzahmi, Wadhah Alyaarbi, Alyaa Alnaqbi, Tahani Alzaatreh, Ayman Dubai Electricity and Water Authority Dubai United Arab Emirates American University of Sharjah Sharjah Department of Industrial Engineering Engineering Systems Management Program Sharjah26666 United Arab Emirates College of Arts and Sciences American University of Sharjah Sharjah Department of Mathematics and Statistics Sharjah26666 United Arab Emirates

ISBN: (纸本)9781665491464

Global energy consumption has increased over the years due to population growth, economic expansion, and the pursuit of a higher quality of life. The building sector is a critical sector for high consumption, contributing to about 36% of the total global energy consumption in 2020. The global interest in reducing energy consumption allows different sectors to adopt renewable resources such as solar photovoltaics (PV). However, utilizing solar PV in buildings has limitations due to rooftop space constraints in newly designed buildings. Due to this limitation and continuous innovation in solar PV technologies, Building Integrated Photovoltaics (BIPV) have been introduced as a potential alternative for solar PV in buildings. As such, BIPV energy performance and panel temperatures are affected by many factors such as orientation setup and technology type. Therefore, this research aims to analyze the impact of technology type (indium gallium selenide (CIGS) and monocrystalline (MONO) & orientation on BIPV energy production & module temperature. The data used for this study is based on a project completed in Dubai for BIPV in building applications. The results indicate that BIPV type and system orientation during each session significantly affect BIPV energy production and BIPV module temperature. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Intelligent Deep Learning Based Disease Diagnosis Using Biomedical Tongue Images

引用

Computers, Materials & Continua 2022年第3期70卷 5667-5681页

作者： V.Thanikachalam S.Shanthi K.Kalirajan Sayed Abdel-Khalek Mohamed Omri Lotfi M.Ladhar Sri Sivasubramaniya Nadar College of Engineering Chennai603110India Department of Information Technology Department of Electronics and Communication EngineeringCARE College of EngineeringTiruchirappalli620009India Department of Electronics and Communication Engineering KPR Institute of Engineering and TechnologyCoimbatore641407India Department of Mathematics and Statistics College of ScienceTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia Mathematics Department Faculty of ScienceSohag UniversitySohagEgypt Deanship of Scientific Research King Abdulaziz UniversityJeddahSaudi Arabia Department of Electrical and Computer Engineering Faculty of EngineeringKing Abdulaziz UniversityJeddahSaudi Arabia

The rapid development of biomedical imaging modalities led to its wide application in disease ***-based diagnostic procedures are proficient and non-invasive in nature to carry out secondary diagnostic processes ***,physicians examine the characteristics of tongue prior to *** this scenario,to get rid of qualitative aspects,tongue images can be quantitatively inspected for which a new disease diagnosis model is *** model can reduce the physical harm made to the *** tongue image analytical methodologies have been proposed ***,there is a need exists to design an intelligent Deep Learning(DL)based disease diagnosis *** this motivation,the current research article designs an Intelligent DL-basedDisease Diagnosis method using Biomedical Tongue Images called IDLDD-BTI *** proposed IDLDD-BTI model incorporates Fuzzy-based Adaptive Median Filtering(FADM)technique for noise removal ***,SqueezeNet model is employed as a feature extractor in which the hyperparameters of SqueezeNet are tuned using Oppositional Glowworm Swarm Optimization(OGSO)*** last,Weighted Extreme Learning Machine(WELM)classifier is applied to allocate proper class labels for input tongue color *** design of OGSO algorithm for SqueezeNet model shows the novelty of the *** assess the enhanced diagnostic performance of the presented IDLDD-BTI technique,a series of simulations was conducted on benchmark dataset and the results were examined in terms of several *** resultant experimental values highlighted the supremacy of IDLDD-BTI model over other state-of-the-art methods.

关键词： Biomedical images image processing tongue color image deep learning squeezenet disease diagnosis

来源：评论

学校读者我要写书评

暂无评论

Wavelet Decomposition Impacts on Traditional Forecasting Time Series Models

引用

Computer Modeling in engineering & Sciences 2022年第3期130卷 1517-1532页

作者： W.A.Shaikh S.F.Shah S.M.Pandhiani M.A.Solangi Department of Mathematics and Statistics Quaid-e-Awam University of EngineeringScience&TechnologyNawabshahSindhPakistan Department of Basic Sciences&Related Studies Mehran University of Engineering&TechnologyJamshoroSindhPakistan Department of General Studies Jubail University CollegeAl JubailSaudi Arabia

This investigative study is focused on the impact of wavelet on traditional forecasting time-series models,which significantly shows the usage of wavelet *** Decomposition(WD)algorithm has been combined with various traditional forecasting time-series models,such as Least Square Support Vector Machine(LSSVM),Artificial Neural Network(ANN)and Multivariate Adaptive Regression Splines(MARS)and their effects are examined in terms of the statistical *** WD has been used as a mathematical application in traditional forecast modelling to collect periodically measured parameters,which has yielded tremendous constructive ***,it is observed that the wavelet combined models are classy compared to the various time series models in terms of performance ***,combining wavelet forecasting models has yielded much better results.

关键词： Impact wavelet decomposition combined traditional forecasting models statistical analysis

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：