检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Fischer-Abaigar, Unai Kern, Christoph Barda, Noam Kreuter, Frauke Dept. of Statistics LMU Munich Germany Munich Center for Machine Learning Germany Joint Program in Survey Methodology University of Maryland United States Dept. of Software and Information Systems Engineering Dept. of Epidemiology Biostatistics and Community Health Sciences Ben-Gurion University of the Negev Israel

AI-driven decision-making systems are becoming instrumental in the public sector, with applications spanning areas like criminal justice, social welfare, financial fraud detection, and public health. While these systems offer great potential benefits to institutional decision-making processes, such as improved efficiency and reliability, these systems face the challenge of aligning machine learning (ML) models with the complex realities of public sector decision-making. In this paper, we examine five key challenges where misalignment can occur, including distribution shifts, label bias, the influence of past decision-making on the data side, as well as competing objectives and human-in-the-loop on the model output side. Our findings suggest that standard ML methods often rely on assumptions that do not fully account for these complexities, potentially leading to unreliable and harmful predictions. To address this, we propose a shift in modeling efforts from focusing solely on predictive accuracy to improving decision-making outcomes. We offer guidance for selecting appropriate modeling frameworks, including counterfactual prediction and policy learning, by considering how the model estimand connects to the decision-maker’s utility. Additionally, we outline technical methods that address specific challenges within each modeling approach. Finally, we argue for the importance of external input from domain experts and stakeholders to ensure that model assumptions and design choices align with real-world policy objectives, taking a step towards harmonizing AI and public sector objectives. © 2023, CC BY-NC-ND.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Parallel Approximations for High-Dimensional Multivariate Normal Probability Computation in Confidence Region Detection Applications

Parallel Approximations for High-Dimensional Multivariate No...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Xiran Zhang Sameh Abdulah Jian Cao Hatem Ltaief Ying Sun Marc G. Genton David E. Keyes Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Statistics Program King Abdullah University of Science and Technology Extreme Computing Research Center King Abdullah University of Science and Technology Thuwal Saudi Arabia Department of Mathematics The University of Houston Houston Texas USA

ISBN: (数字)9798350387117

ISBN: (纸本)9798350387124

Addressing the statistical challenge of computing the multivariate normal (MVN) probability in high dimensions holds significant potential for enhancing various applications. For example, the critical task of detecting confidence regions where a process probability surpasses a specific threshold is essential in diverse applications, such as pinpointing tumor locations in magnetic resonance imaging (MRI) scan images, determining hydraulic parameters in groundwater flow issues, and forecasting regional wind power to optimize wind turbine placement, among numerous others. One common way to compute high-dimensional MVN probabilities is the Separation-of-Variables (SOV) algorithm. This algorithm is known for its high computational complexity of O(n 3 ) and space complexity of O(n 2 ), mainly due to a Cholesky factorization operation for an n×n covariance matrix, where n represents the dimensionality of the MVN problem. This work proposes a high-performance computing framework that allows scaling the SOV algorithm and, subsequently, the confidence region detection algorithm. The framework leverages parallel linear algebra algorithms with a task-based programming model to achieve performance scalability in computing process probabilities, especially on large-scale systems. In addition, we enhance our implementation by incorporating Tile Low-Rank (TLR) approximation techniques to reduce algorithmic complexity without compromising the necessary accuracy. To evaluate the performance and accuracy of our framework, we conduct assessments using simulated data and a wind speed dataset. Our proposed implementation effectively handles high-dimensional multivariate normal (MVN) probability computations on shared and distributed-memory systems using finite precision arithmetics and TLR approximation computation. Performance results show a significant speedup of up to 20X in solving the MVN problem using TLR approximation compared to the reference dense solution without sacrificin

关键词： Accuracy Tensors Wind speed Magnetic resonance imaging Linear algebra Wind power generation Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

An Analytical Air Pollution Model with Time Dependent Eddy Diffusivity

引用

Journal of Environmental Protection 2013年第8期4卷 16-23页

作者： Tiziano Tirabassi Marco Túllio Vilhena Daniela Buske Gervásio Annes Degrazia Department of Mathematics and Statistics (IFM/DME) Federal University of Pelotas (UFPel) Pelotas Brazil epartment of Physics Federal University of Santa Maria (UFSM) Santa Maria Brazil Graduate Program in Mechanical Engineering Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil Institute of Atmospheric Sciences and Climate (ISAC) National Research Council (CNR) Bologna Italy

Air pollution transport and dispersion in the atmospheric boundary layer are modeled by the advection-diffusion equation, that is, essentially, a statement of conservation of the suspended material in an incompressible flow. Many models simulating air pollution dispersion are based upon the solution (numerical or analytical) of the advection-diffusion equation assuming turbulence parameterization for realistic physical scenarios. We present the general time dependent three-dimensional solution of the advection-diffusion equation considering a vertically inhomogeneous atmospheric boundary layer for arbitrary vertical profiles of wind and eddy-diffusion coefficients. Numerical results and comparison with experimental data are shown.

关键词： Analytical Solution Advection-Diffusion Equation Air Pollution Modeling Integral Transform Decomposition Method

来源：评论

学校读者我要写书评

暂无评论

A hybrid spherical fuzzy logarithmic decomposition of criteria importance and alternative ranking technique based on Adaptive Standardized Intervals model with application

引用

Decision Analytics Journal 2024年 11卷

作者： Yalçın, Galip Cihan Kara, Karahan Senapati, Tapan Mathematics Program Kırıkkale University Yahşihan/Kırıkkale 71450 Turkey Logistics Program Artvin Çoruh University Artvin 08300 Turkey School of Mathematics and Statistics Southwest University Beibei Chongqing 400715 China Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Thandalam Tamilnadu Chennai 602105 India

This study presents a hybrid fuzzy Multi-Attribute Group Decision Making (MAGDM) model with application to commercial insurance selection. The proposed hybrid model uses Spherical Fuzzy (SF) sets using Yager t-norm and t-conorm operations. The Logarithmic Decomposition of Criteria Importance (LODECI) method is used for criterion weighting due to its efficacy in stabilizing scenarios that may challenge other weighting techniques. For alternative ranking, the study employs the Alternative Ranking Technique based on Adaptive Standardized Intervals (ARTASI), offering enhanced flexibility in handling uncertainties inherent in expert evaluations. The combination of these methods and the utilization of SF sets gives rise to the proposed SF-LODECI-ARTASI hybrid model. The paper systematically delineates the procedural steps involving SF sets, Yager t-norm and t-conorm operations, SF-LODECI, and SF-ARTASI methods. Subsequently, the developed hybrid model is applied to a case study of commercial insurance selection, supported by a numerical example. The research application results emphasize the consistency of these findings with other alternative methods. Additionally, sensitivity scenarios are constructed to scrutinize the robustness of the proposed hybrid model. The study concludes by elucidating implications and contributions to the existing literature. © 2024 The Author(s)

关键词： Alternative ranking technique based on adaptive standardized intervals Insurance selection Logarithmic decomposition of criteria importance Multi-attribute group decision making Spherical fuzzy sets Yager t-norm and t-conorm

来源：评论

学校读者我要写书评

暂无评论

Coarse-Grid Selection Using Simulated Annealing

arXiv

引用

arXiv 2021年

作者： Zaman, Tareq U. MacLachlan, Scott P. Olson, Luke N. West, Matt Scientific Computing Program Memorial University of Newfoundland NL Canada Department of Mathematics and Statistics Memorial University of Newfoundland NL Canada Department of Computer Science University of Illinois at Urbana-Champaign IL United States Department of Mechanical Science and Engineering University of Illinois at Urbana-Champaign IL United States

Multilevel techniques are efficient approaches for solving the large linear systems that arise from discretized partial differential equations and other problems. While geometric multigrid requires detailed knowledge about the underlying problem and its discretization, algebraic multigrid aims to be less intrusive, requiring less knowledge about the origin of the linear system. A key step in algebraic multigrid is the choice of the coarse/fine partitioning, aiming to balance the convergence of the iteration with its cost. In work by MacLachlan and Saad [1], a constrained combinatorial optimization problem is used to define the "best" coarse grid within the setting of a two-level reduction-based algebraic multigrid method and is shown to be NP-complete. Here, we develop a new coarsening algorithm based on simulated annealing to approximate solutions to this problem, which yields improved results over the greedy algorithm developed previously. We present numerical results for test problems on both structured and unstructured meshes, demonstrating the ability to exploit knowledge about the underlying grid structure if it is available. © 2021, CC BY.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

Combining Experimental and Observational Data for Identification and Estimation of Long-Term Causal Effects

arXiv

引用

arXiv 2022年

作者： Ghassami, AmirEmad Yang, Alan Richardson, David Shpitser, Ilya Tchetgen, Eric Tchetgen Department of Computer Science Johns Hopkins University United States Department of Electrical Engineering Stanford University United States Department of Environmental and Occupational Health Program in Public Health University of California Irvine United States Department of Statistics and Data Science The Wharton School University of Pennsylvania United States

We consider the task of identifying and estimating the causal effect of a treatment variable on a long-term outcome variable using data from an observational domain and an experimental domain. The observational domain is subject to unobserved confounding. Furthermore, subjects in the experiment are only followed for a short period of time;hence, long-term effects of treatment are unobserved but short-term effects will be observed. Therefore, data from neither domain alone suffices for causal inference about the effect of the treatment on the long-term outcome, and must be pooled in a principled way, instead. Athey et al. (2020) proposed a method for systematically combining such data for identifying the downstream causal effect in view. Their approach is based on the assumptions of internal and external validity of the experimental data, and an extra novel assumption called latent unconfoundedness. In this paper, we first review their proposed approach, and then we propose three alternative approaches for data fusion for the purpose of identifying and estimating average treatment effect as well as the effect of treatment on the treated. Our first approach is based on assuming equi-confounding bias for the short-term and long-term outcomes. Our second approach is based on a relaxed version of the equi-confounding bias assumption, where we assume the existence of an observed confounder such that the short-term and long-term potential outcome variables have the same partial additive association with that confounder. Our third approach is based on the proximal causal inference framework, in which we assume the existence of an extra variable in the system which is a proxy of the latent confounder of the treatment-outcome relation. We propose influence function-based estimation strategies for each of our data fusion frameworks and study the robustness properties of the proposed estimators. © 2022, CC BY.

关键词： Data fusion

来源：评论

学校读者我要写书评

暂无评论

No-boundary thinking: a viable solution to ethical data-driven AI in precision medicine

引用

AI and ethics 2022年第4期2卷 635-643页

作者： Tayo Obafemi-Ajayi Andy Perkins Bindu Nanduri Donald C Wunsch Ii James A Foster Joan Peckham Engineering Program Missouri State University Springfield MO USA. Department of Computer Science and Engineering Mississippi State University Starkville MS USA. Department of Comparative Biomedical Sciences College of Veterinary Medicine Mississippi State University Starkville MS USA. Electrical & Computer Engineering Department Missouri University of Science and Technology Rolla MO USA. Biological Sciences Department University of Idaho Moscow ID USA. Computer Science & Statistics Department University of Rhode Island Kingston RI USA.

Today Artificial Intelligence (AI) supports difficult decisions about policy, health, and our personal lives. The AI algorithms we develop and deploy to make sense of information, are informed by data, and based on models that capture and use pertinent details of the population or phenomenon being analyzed. For any application area, more importantly in precision medicine which directly impacts human lives, the data upon which algorithms are run must be procured, cleaned, and organized well to assure reliable and interpretable results, and to assure that they do not perpetrate or amplify human prejudices. This must be done without violating basic assumptions of the algorithms in use. Algorithmic results need to be clearly communicated to stakeholders and domain experts to enable sound conclusions. Our position is that AI holds great promise for supporting precision medicine, but we need to move forward with great care, with consideration for possible ethical implications. We make the case that a no-boundary or convergent approach is essential to support sound and ethical decisions. No-boundary thinking supports problem definition and solving with teams of experts possessing diverse perspectives. When dealing with AI and the data needed to use AI, there is a spectrum of activities that needs the attention of a no-boundary team. This is necessary if we are to draw viable conclusions and develop actions and policies based on the AI, the data, and the scientific foundations of the domain in question.

关键词： Artificial intelligence Data science Ethics Precision medicine

来源：评论

学校读者我要写书评

暂无评论

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

引用

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

来源：评论

学校读者我要写书评

暂无评论

Retracted: The Effect of Mixed Pertamax with Tuak Nias (Tuonifaro) on Fuel Consumption at 125CC Machine and Its Dissemination Using Website

Retracted: The Effect of Mixed Pertamax with Tuak Nias (Tuon...

引用

2018 Workshop on Multidisciplinary and Its Applications: Applied Mathematics, Computer Science, Information Systems, and Information Technology, WMA-Mathcomtech 2018

作者： Achmad Daengs, G.S. Tarigan, Kristian Ongko, Erianto Hartono, H. Abdullah, Dahlan Erliana, Cut Ita Nurmawati, N. Sallu, Sulfikar Sriadhi, S. Iskandar, Akbar Kurniasih, Nuning Daengs, Achmad Nanuru, Ricardo Freedom Saleh, A.A. Setiawan, Muhammad Ikhsan Hadikurniawati, Wiwien Winarno, Edy Department of Mechanical Engineering Universitas Darma Agung Medan Indonesia Department of Informatics Akademi Teknologi Industri Immanuel Indonesia Department of Computer Science STMIK IBBI Medan Indonesia Department of Informatics Universitas Malikussaleh Aceh Indonesia Department of Industrial Engineering Universitas Malikussaleh Aceh Indonesia Faculty of Industry Technique University of 45 Surabaya Indonesia Faculty of Information Technology Universitas Sembilan Belas November Kolaka Sulawesi Tenggara Indonesia Department of Electrical Engineering Universitas Negeri Medan Indonesia Department of Informatics STMIK AKBA Makassar Indonesia Faculty of Communication Sciences Library and Information Science Program Universitas Padjadjaran Bandung Indonesia Department of Management Universitas 45 Surabaya Indonesia Universitas Kristen Indonesia Maluku. Ambon Indonesia Statistics Financial and Social Sciences Research Group Indonesia Department of Civil Engineering Narotama University Surabaya Indonesia Faculty of Information Technology Universitas Stikubank Semarang Indonesia

The purpose of this research is to know how influence of mixture of pertamax with Tuak Nias (Tuonifaro) to fuel consumption at 125 cc engine To prove that Tuak Nias or Tuonifaro can be used as fuel mixture on motorcycle and examine how big influence of mix between Tuak Nias or Tuonifaro with Pertamax, conducting research by literature study method or literature study. Many authors use various supporting / input factors and supporting books related to the titles discussed. because Tuak Nias or tuonifaro contain low 4-5% ethanonic elements and contain 90% alcoholic elements so that the fuel easily burns easily in the combustion chamber and produces great power. The results of this research will be disseminated using the website. © Published under licence by IOP Publishing Ltd.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

A Simulation-Based Model for Optimal Demand Response Load Shifting: A Case Study for the Texas Power Market

SSRN

引用

SSRN 2019年

作者： Schaperow, Jacob R. Gabriel, Steven A. Siemann, Michael Crawford, Jaden Civil and Environmental Engineering University of California Los Angeles 420 Westwood Plaza 6722 Boelter Hall Los AngelesCA90095 United States Mechanical Engineering/Applied Mathematics Statistics & Scientific Computing Program University of Maryland College ParkMD20742 United States Whisker Labs 12410 Milestone Center Drive GermantownMD20876 United States

This paper describes a prototype Monte Carlo simulation tool that we use to evaluate retail demand response (DR) programs for the Texas power market (the Electric Reliability Council of Texas/ERCOT), but which could also be applied to other regions. The model simulates a direct load control technique in which customers’ power consumption is adjusted during certain time periods called DR events. During a DR event, smart thermostats automatically increase participating customers’ temperature setpoints, reducing air-conditioning loads and thus potentially shielding retail electric providers (REPs) from financial losses during times of peak load. This study identified a Pareto optimal load control schedule based on forecasted load, settlement point prices and weather variables, taking into account stochastic load and prices as well as gray-box thermodynamic modeling. A Pareto optimal schedule is defined as the schedule that maximizes profit to the REP and minimizes its risk of low profits. We show how much benefit REPs stand to gain by following an optimal load schedule and how much they stand to lose by enacting DR events at the wrong times. © 2019, The Authors. All rights reserved.

关键词： Sales

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：