检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Óskarsdóttir, María Ahmed, Waqas Antonio, Katrien Baesens, Bart Dendievel, Rémi Donas, Tom Reynkens, Tom Department of Computer Science Reykjavik University Iceland AG Insurance Belgium Faculty of Economics and Business KU Leuven Belgium Faculty of Economics and Business University of Amsterdam Netherlands LRisk Leuven Research Center on Insurance and Financial Risk Analysis KU Leuven Belgium LStat Leuven Statistics Research Center KU Leuven Belgium Dept. of Decision Analytics and Risk University of Southampton United Kingdom

Insurance fraud occurs when policyholders file claims that are exaggerated or based on intentional damages. This contribution develops a fraud detection strategy by extracting insightful information from the social network of a claim. First, we construct a network by linking claims with all their involved parties, including the policyholders, brokers, experts, and garages. Next, we establish fraud as a social phenomenon in the network and use the BiRank algorithm with a fraud specific query vector to compute a fraud score for each claim. From the network, we extract features related to the fraud scores as well as the claims’ neighborhood structure. Finally, we combine these network features with the claim-specific features and build a supervised model with fraud in motor insurance as the target variable. Although we build a model for only motor insurance, the network includes claims from all available lines of business. Our results show that models with features derived from the network perform well when detecting fraud and even outperform the models using only the classical claim-specific features. Combining network and claim-specific features further improves the performance of supervised learning models to detect fraud. The resulting model flags highly suspicions claims that need to be further investigated. Our approach provides a guided and intelligent selection of claims and contributes to a more effective fraud investigation process. Copyright © 2020, The Authors. All rights reserved.

关键词： Insurance

来源：评论

学校读者我要写书评

暂无评论

Explainable Machine Learning for Scientific Insights and Discoveries

arXiv

引用

arXiv 2019年

作者： Roscher, Ribana Bohn, Bastian Duarte, Marco F. Garcke, Jochen Institute of Geodesy and Geoinformation University of Bonn Germany Institute of Computer Science University of Osnabrueck Germany Institute for Numerical Simulation University of Bonn Germany Dept. of Electrical and Computer Engineering University of Massachusetts Amherst United States Fraunhofer Center for Machine Learning and Fraunhofer SCAI Sankt Augustin Germany

Machine learning methods have been remarkably successful for a wide range of application areas in the extraction of essential information from data. An exciting and relatively recent development is the uptake of machine learning in the natural sciences, where the major goal is to obtain novel scientific insights and discoveries from observational or simulated data. A prerequisite for obtaining a scientific outcome is domain knowledge, which is needed to gain explainability, but also to enhance scientific consistency. In this article we review explainable machine learning in view of applications in the natural sciences and discuss three core elements which we identified as relevant in this context: transparency, interpretability, and explainability. With respect to these core elements, we provide a survey of recent scientific works incorporating machine learning, and in particular to the way that explainable machine learning is used in their respective application areas. Copyright © 2019, The Authors. All rights reserved.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

On the effect of local search in the multi-objective evolutionary discovery of software architectures

On the effect of local search in the multi-objective evoluti...

引用

2017 IEEE Congress on Evolutionary Computation, CEC 2017

作者： Ramirez, Aurora Romero, Jose Raul Ventura, Sebastian Dept. of Computer Science and Numerical Analysis University of Córdoba Campus of Rabanales Córdoba14071 Spain

ISBN: (纸本)9781509046010

Software architects devote substantial efforts to find the most fitting architectural description for their system, which should not only specify its structure, but is also required to meet multiple, simultaneous quality criteria. Evolutionary computation has recently demonstrated to provide insightful support during the design phase by automatically deciding how to organise internal software components and how they should interact each other. Observed from a multi-objective perspective, particular care has to be taken in order to reach an appropriate trade-off among design metrics, while providing the software engineer with diverse alternatives to choose among. However, multi-objective evolutionary algorithms may find difficulties to control both aspects and, at the same time, to explore the entire search space in dept.. Under these circumstances, local search can be applied to complement the evolution by scrutinising the most promising search directions. This paper proposes two different approaches that take advantage of the benefits of local search within the multi-objective evolutionary discovery of component-based software architectures. A detailed analysis and comparative study provides interesting findings like the importance of assigning a sufficient number of evaluations to the local improvement. The way in which local search explores and compares solutions for acceptance is a relevant aspect to promote diversity during the discovery process as well. © 2017 IEEE.

关键词： Software architecture

来源：评论

学校读者我要写书评

暂无评论

Characterization of Sub-Bandgap Plasmon Excitations in Transparent Conducting Oxides with Electron Energy-Loss Spectroscopy

引用

Microscopy and Microanalysis 2019年第S2期25卷 600-601页

作者： Julia I. Deitz John M. Walls Jake W. Bowers Tyler J. Grassman David W. McComb Center for Electron Microscopy and Analysis Department of Materials Science and Engineering The Ohio State University Columbus OH United States. Centre for Renewable Energy Systems Technology Dept. of Mechanical Electrical and Manufacturing Engineering Loughborough University Loughborough Leicestershire UK. Dept. of Electrical & Computer Engineering The Ohio State University Columbus OH USA. Dept. of Materials Science & Engineering The Ohio State University Columbus OH USA.

来源：评论

学校读者我要写书评

暂无评论

Risk Management using Cyber-Threat Information Sharing and Cyber-Insurance

SSRN

引用

SSRN 2019年

作者： Tosh, Deepak K. Shetty, Sachin Sengupta, Shamik Kesan, Jay P. Kamhoua, Charles A. Dept. of Computer Science Norfolk State University VA United States Virginia Modeling Analysis and Simulation Center Old Dominion University VA United States Dept. of Computer Science and Engineering University of Nevada RenoNV United States College of Law University of Illinois Urbana ChampaignIL United States Cyber Assurance Branch Air Force Research Laboratory RomeNY United States

Critical infrastructure systems spanning from transportation to nuclear operations are vulnerable to cyber attacks. Cyber-insurance and cyber-threat information sharing are two prominent mechanisms to defend cybersecurity issues proactively. However, standardization and realization of these choices have many bottlenecks. In this paper, we discuss the benefits and importance of cybersecurity information sharing and cyber-insurance in the current cyber-warfare situation. We model a standard game theoretic participation model for cybersecurity information exchange (CYBEX) and discuss the applicability of economic tools in addressing important issues related to CYBEX and cyber-insurance. We also pose several open research challenges, which need to be addressed for developing a robust cyber-risk management capability. © 2019, The Authors. All rights reserved.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Prediction of Mid to Long Term Habitual Transportation Mode Use

Machine Learning for Prediction of Mid to Long Term Habitual...

引用

IEEE International Conference on Big Data

作者： Alina Lazar Alexandra Ballow Ling Jin C. Anna Spurlock Alexander Sim Kesheng Wu Dept. of Computer Science and Information Systems Youngstown State University Youngstown OH Dept. of Physics and Astronomy Youngstown State University Youngstown OH Energy Analysis and Environmental Impacts Division Lawrence Berkeley National Laboratory Berkeley CA Computational Research Division Lawrence Berkeley National Laboratory Berkeley CA

ISBN: (数字)9781728108582

ISBN: (纸本)9781728108599

Prediction of daily transportation mode use (car, public transit, or active travel) is a important task in transportation research. Unlike statistical models that impose a predetermined model structure, machine learning models are learned from the data, making them more flexible with higher prediction accuracy. However, prediction of mid-to long-term habitual modes still largely relies on traditional statistical analysis using small samples of cross-sectional data. Low interpretability of “black-box” machine learning models limits their usefulness for generating behavior insights needed for designing appropriate interventions. This paper, leveraging a set of unique longitudinal life course data, is the first use case to demonstrate machine learning methods applied for both predicting and interpreting regularly used travel modes. We combine sequence clustering and tree-based machine learning methods coupled with TreeExplainer to predict and interpret habitual travel modes using mid-to long-term predictors. Five life course clusters are derived to provide evaluation and interpretation contexts. This allows us to improve upon a recently developed TreeExplainer method to better distinguish predictor importance locally and globally; and predictor interactions across subpopulations within distinctive life history contexts. Our results demonstrate a promising step toward interpretable machine learning applications to mid-to long-term prediction of travel modes for transportation planning.

关键词： Machine learning Automobiles Predictive models History Data models Trajectory

来源：评论

学校读者我要写书评

暂无评论

Agent-Based Model Characterization Using Natural Language Processing

Agent-Based Model Characterization Using Natural Language Pr...

引用

Simulation Winter Conference

作者： Jose J Padilla David Shuttleworth Kevin O’Brien Virginia Modeling Analysis and Simulation Center Old Dominion University Suffolk VA USA Comp. Modeling and Simulation Eng. Dept. Old Dominion University Norfolk VA USA Computer Science Department Old Dominion University Norfolk VA USA

ISBN: (数字)9781728132839

ISBN: (纸本)9781728120522

This paper reports on Natural Language Processing (NLP) as a technique to analyze phenomena towards specifying agent-based models (ABM). The objective of the ABM NLP Analyzer is to facilitate non-simulationists to actively engage in the learning and collaborative designing of ABMs. The NLP model identifies candidate agents, candidate agent attributes, and candidate rules all of which non-simulationists can later evaluate for feasibility. IBM's Watson Natural Language Understanding (NLU) and Knowledge Studio were used in order to annotate, evaluate, extract agents, agent attributes, and agent rules from unstructured descriptions of phenomena. The software, and related agent-attribute-rule characterization, provides insight into a simple but useful means of conceptualizing and specifying baseline ABMs. Further, it emphasizes on how to approach the design of ABMs without the use of NLP by focusing on the identification of agent, attributes and rules.

关键词： Unified modeling language Object oriented modeling Natural language processing Biological system modeling Computational modeling Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Ergodic Capacity Optimization of FSO Systems over Gamma-Gamma Atmospheric Turbulence Channels with Generalized Pointing Errors 11

Ergodic Capacity Optimization of FSO Systems over Gamma-Gamm...

引用

11th International Symposium on Communication Systems, Networks and Digital Signal Processing, CSNDSP 2018

作者： Boluda-Ruiz, Ruben Garcia-Zambrana, Antonio Castillo-Vazquez, Beatriz Castillo-Vazquez, Carmen Gao, Qian Qaraqe, Khalid Dept. of Electrical and Computer Engineering Texas AM University Doha Qatar Dept. of Communications Engineering University of Málaga Málaga Spain Dept. of Mathematical Analysis Statistics and Operations Research and Applied Mathematics University of Málaga Málaga Spain Key Laboratory of Wireless-Optical Communications Chinese Academy of Sciences University of Science and Technology of China Hefei China

ISBN: (纸本)9781538613351

A novel approximate closed-form expression for the ergodic capacity of free-space optical (FSO) communication links over gamma-gamma (GG) atmospheric turbulence channels with generalized pointing errors is presented. The obtained expression is entirely valid from low to high signal-to-noise-ratio (SNR). It is concluded that despite generalized pointing errors cannot be ignored in capacity performance;they can be considerably mitigated by selecting an optimum beam width at the transmitter-side. In other words, there is an optimum normalized beam width value that minimizes the effect of pointing errors on capacity performance at high SNR that does not depend on atmospheric turbulence. © 2018 IEEE.

关键词： Atmospheric turbulence

来源：评论

学校读者我要写书评

暂无评论

Overcoming the disconnect between energy system and climate modelling

arXiv

引用

arXiv 2022年

作者： Craig, Michael T. Wohland, Jan Stoop, Laurens P. Kies, Alexander Pickering, Bryn Bloomfield, Hannah C. Browell, Jethro De Felice, Matteo Dent, Chris J. Deroubaix, Adrien Frischmuth, Felix Gonzalez, Paula L.M. Grochowicz, Aleksander Gruber, Katharina Härtel, Philipp Kittel, Martin Kotzur, Leander Labuhn, Inga Lundquist, Julie K. Pflugradt, Noah van der Wiel, Karin Zeyringer, Marianne Brayshaw, David J. School for Environment and Sustainability University of Michigan United States Institute for Environmental Decisions ETH Zurich Switzerland Helmholtz-Zentrum Hereon Germany Information and Computing Science Copernicus Institute of Sustainable Development Utrecht University Netherlands TenneT TSO B.V. Arnhem Netherlands Royal Netherlands Meteorological Institute Netherlands Frankfurt Institute for Advanced Studies Germany Department of Electrical and Computer Engineering Aarhus University Denmark ETH Zürich Switzerland School of Geographical Sciences University of Bristol United Kingdom Department of Meteorology University of Reading United Kingdom University of Glasgow United Kingdom European Commission Joint Research Centre Netherlands School of Mathematics University of Edinburg United Kingdom The Alan Turing Institute United Kingdom Max Planck Institute Germany Fraunhofer Institute for Energy Economics and Energy System Technology Germany Department of Mathematics University of Oslo Norway University of Natural Resources and Life Sciences Austria German Institute for Economic Research Germany Institute of Energy and Climate Research Techno-economic Systems Analysis Germany University of Bremen Institute of Geography Germany Dept. of Atmospheric and Oceanic Science University of Colorado Boulder United States National Renewable Energy Laboratory United States Renewable and Sustainable Energy Institute United States Forschungszentrum Jülich Germany Department of Technology Systems University of Oslo Norway

Energy system models underpin decisions by energy system planners and operators. Energy system modelling faces a transformation: accounting for changing meteorological conditions imposed by climate change. To enable that transformation, a community of practice in energy-climate modelling has started to form that aims to better integrate energy system models with weather and climate models. Here, we evaluate the disconnects between the energy system and climate modelling communities, then lay out a research agenda to bridge those disconnects. In the near-term, we propose interdisciplinary activities for expediting uptake of future climate data in energy system modelling. In the long-term, we propose a transdisciplinary approach to enable development of (1) energy-system-tailored climate datasets for historical and future meteorological conditions and (2) energy system models that can effectively leverage those datasets. This agenda increases the odds of meeting ambitious climate mitigation goals by systematically capturing and mitigating climate risk in energy sector decision making. © 2022, CC BY-NC-ND.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Correcting the bias in least squares regression with volume-rescaled sampling

arXiv

引用

arXiv 2018年

作者： Dereziński, Michal Warmuth, Manfred K. Hsu, Daniel Foundations of Data Analysis Institute University of California Berkeley United States Dept. of Computer Science University of California Santa Cruz United States Dept. of Computer Science Columbia University New York United States

Consider linear regression where the examples are generated by an unknown distribution on Rd× R. Without any assumptions on the noise, the linear least squares solution for any i.i.d. sample will typically be biased w.r.t. the least squares optimum over the entire distribution. However, we show that if an i.i.d. sample of any size k is augmented by a certain small additional sample, then the solution of the combined sample becomes unbiased. We show this when the additional sample consists of d points drawn jointly according to the input distribution that is rescaled by the squared volume spanned by the points. Furthermore, we propose algorithms to sample from this volume-rescaled distribution when the data distribution is only known through an i.i.d sample. Copyright © 2018, The Authors. All rights reserved.

关键词： Machine learning

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：