Filters








2,567 Hits in 7.3 sec

1-dimensional splines as building blocks for improving accuracy of risk outcomes models

David S. Vogel, Morgan C. Wang
2004 Proceedings of the 2004 ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '04  
A case study of how the transformed variables can be fed into a simple linear regression model to predict risk outcomes is presented.  ...  Data used for predicting health outcomes contains an abundance of non-linear relationships between predictors and the outcomes requiring an algorithm for modeling them accurately.  ...  TRANSFORMATION Splines are generally good only for small dimensional problems as their complexity grows geometrically for each additional dimension.  ... 
doi:10.1145/1014052.1016924 dblp:conf/kdd/VogelW04 fatcat:ungg5qe2hnbdnjprofmsq5ztly

Extending Statistical Boosting

H. Binder, O. Gefeller, M. Schmid, A. Mayr
2014 Methods of Information in Medicine  
Objectives: This review highlights recent methodological developments regarding boosting algorithms for statistical modelling especially focusing on topics relevant for biomedical research.  ...  setting in combination with a large amount of different types of predictor effects.  ...  The authors thank Birgit Deutsch for her help with the literature search as well as Diana Pereira for the linguistic revision of the manuscript.  ... 
doi:10.3414/me13-01-0123 pmid:25112429 fatcat:dwrayx5vq5hfxbg2df2f5s3edu

Improvement Screening for Ultra-High Dimensional Data with Censored Survival Outcomes and Varying Coefficients

Mu Yue, Jialiang Li
2017 The International Journal of Biostatistics  
In this paper, we will examine these improvement statistics as well as the norm-based approach for evaluating the incremental values of new markers and compare these four measures by analyzing ultra-high  ...  AbstractMotivated by risk prediction studies with ultra-high dimensional bio markers, we propose a novel improvement screening methodology.  ...  Several basic concepts in biostatistics constitute the building block for this thesis.Cox proportional hazards model is applied to model the survival time, with ultra-high dimensional biomarkers.  ... 
doi:10.1515/ijb-2017-0024 pmid:28541925 fatcat:wihjncj7erccbhb6elnooytswi

Research on Intelligent Fault Diagnosis of Rolling Bearing Based on Improved Deep Residual Network

Xinyu Hao, Yuan Zheng, Li Lu, Hong Pan
2021 Applied Sciences  
Experiments show that the accuracy of fault diagnosis of the improved algorithm reaches 99.83%, training time has been shortened.  ...  It effectively solves the problem of too many parameters of the traditional RESNET model, and uses data enhancement, dropout, and other deep learning training techniques to prevent the model from overfitting  ...  as larger faults, which is meaningful for risk prediction.  ... 
doi:10.3390/app112210889 fatcat:c4xtjapxqjhanoy4fk22zdb26q

Prediction of Mechanical Properties for High Strength Low Alloyed Steels in a Commercial Hot Dip Galvanizing Line without Soaking Section

Ángel García-Martino, César García, María Manuela Prieto, José Díaz
2020 Metals  
It is concluded that the introduction of the time–temperature parameter improves the accuracy of the predictions over 10% in most of the cases.  ...  Four different types of numerical models (linear and polynomial regressions, artificial neural networks, and Multivariate Adaptive Regression Splines), are applied to predict the yield strength and the  ...  In light of previous research, the trend is to combine different tools and build more complex models to improve the accuracy of the predictions.  ... 
doi:10.3390/met10050561 fatcat:qrqohnd7trfn7ju2p3r4wmuyq4

Statistical emulators for pricing and hedging longevity risk products

J. Risk, M. Ludkovski
2016 Insurance, Mathematics & Economics  
Such models typically require (nested) evaluation of expected values of nonlinear functionals of multi-dimensional stochastic processes.  ...  We propose the use of statistical emulators for the purpose of valuing mortalitylinked contracts in stochastic mortality models.  ...  As mentioned, the building block of pricing a life annuity is usually embedded in a larger setting which requires repeated evaluation of the former quantity.  ... 
doi:10.1016/j.insmatheco.2016.02.006 fatcat:ljvlnxwwevdpfgtvardr43x4je

A structured approach to predictive modeling of a two-class problem using multidimensional data sets

Heidi Spratt, Hyunsu Ju, Allan R. Brasier
2013 Methods  
This standardized approach is illustrated by an example from a proteomic data analysis that has been used to predict the risk of infectious disease outcome.  ...  Strategies for model selection and post-hoc model diagnostics are presented and applied to the case illustration.  ...  Clinical and Translational Science Award (UL1TR000071) from the National Center for Advancing Translational Sciences, NIH (ARB).  ... 
doi:10.1016/j.ymeth.2013.01.002 pmid:23321025 pmcid:PMC3661737 fatcat:g5onqq7s35duhlwc7gk76vrrg4

Evaluating the Differences of Gridding Techniques for Digital Elevation Models Generation and Their Influence on the Modeling of Stony Debris Flows Routing: A Case Study From Rovina di Cancia Basin (North-Eastern Italian Alps)

Mauro Boreggio, Martino Bernard, Carlo Gregoretti
2018 Frontiers in Earth Science  
Anyway, the evaluation of the effects of gridding techniques on debris flow routing modeling reveals that the choice of the interpolation algorithm does not significantly affect the model outcomes.  ...  We also thank the Environmental Protection Agency of Veneto (ARPAV) for providing the meteorological data used in the hydrological modeling.  ...  ACKNOWLEDGMENTS The authors wish to thank the Regional Civil Work Agency of Veneto for the ortho-photos and full-waveform LiDAR data.  ... 
doi:10.3389/feart.2018.00089 fatcat:iao7umcp3vagzo7r2jki7kgrpe

Heterogeneous Effects in the Built Environment [article]

Adam Peterson and Emma Sanchez-Vaznaugh and Brisa Sanchez
2021 arXiv   pre-print
We study this method in simulations and apply our model to study heterogeneity in the association between fast food restaurant availability and weight status of children attending schools in Los Angeles  ...  The key innovation of our method is to combine ideas from the non-parametric function estimation literature and the Bayesian Dirichlet process literature.  ...  This results in outcome Y ij (i = 1, ..., N, j = 1, ..., n i ) modeled as a function of covariates X ij , and their corresponding coefficients γ.  ... 
arXiv:2107.05805v1 fatcat:5j4hsrqxxneodb2tgrivrlueim

A Framework for Building Comprehensive Driver Profiles

Rashmi P. Payyanadan, Linda S. Angell
2022 Information  
Conventional approaches to modelling driver risk have incorporated measures such as driver gender, age, place of residence, vehicle model, and annual miles driven.  ...  This paper proposes a systematic feature extraction and selection framework for building Comprehensive Driver Profiles that serves as a foundation for driver behavior analysis and building whole driver  ...  The authors thank colleagues at Touchstone, the MIT AgeLab, and the Consortia for their reviews of earlier drafts. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/info13020061 fatcat:w2ohnqddavdkpc3m3ldouzfib4

Predictive Modeling of Short-Term Rockburst for the Stability of Subsurface Structures Using Machine Learning Approaches: t-SNE, K-Means Clustering and XGBoost

Barkat Ullah, Muhammad Kamran, Yichao Rui
2022 Mathematics  
The results of the proposed model serve as a great benchmark for future short-term rockburst levels prediction with high accuracy.  ...  Accurate prediction of short-term rockburst has a significant role in improving the safety of workers in mining and geotechnical projects.  ...  Boosting improves the estimation precision of the model by constructing multiple trees as an alternative to constructing a single tree, and then combining them to build a consensus prediction framework  ... 
doi:10.3390/math10030449 fatcat:mpskeuwafneoriotz4iw6t2gz4

Machine learning, statistical learning and the future of biological research in psychiatry

R. Iniesta, D. Stahl, P. McGuffin
2016 Psychological Medicine  
The analysis of these datasets is challenging, especially when the number of measurements exceeds the number of individuals, and may be further complicated by missing data for some subjects and variables  ...  In addition, the predictive capability of such models promises to be useful in developing decision support systems.  ...  Acknowledgements We gratefully thank Robert Tibshirani, Stanford University, for critically reading this manuscript and providing substantial comments that greatly improved the work.  ... 
doi:10.1017/s0033291716001367 pmid:27406289 pmcid:PMC4988262 fatcat:7dr5hbvcnjbcvlcfov5zhg5veu

Deselection of Base-Learners for Statistical Boosting – with an Application to Distributional Regression [article]

Annika Strömer, Christian Staerk, Nadja Klein, Leonie Weinhold, Stephanie Titze, Andreas Mayr
2022 arXiv   pre-print
As a result, more variables get included into the final model without altering the prediction accuracy.  ...  This occurs particularly for low-dimensional data (p<n), where we observe a slow overfitting behavior of boosting.  ...  Acknowledgment We thank Benjamin Hofner for fruitful discussions on the underlying methodology of the new deselection procedure.  ... 
arXiv:2202.01657v1 fatcat:q5sgb3aehfgpzd6tcm4c7w647a

Intraoperative Imaging Modalities and Compensation for Brain Shift in Tumor Resection Surgery

Siming Bayer, Andreas Maier, Martin Ostermeier, Rebecca Fahrig
2017 International Journal of Biomedical Imaging  
For the use of image-guided systems, this phenomenon greatly affects the accuracy of the guidance. During the last several decades, researchers have investigated how to overcome this problem.  ...  The purpose of this paper is to present a review of publications concerning different aspects of intraoperative brain shift especially in a tumor resection surgery such as intraoperative imaging systems  ...  The Free Form Deformation can be written as the three dimensional tensor product of the one dimensional cubic B-splines [92] .  ... 
doi:10.1155/2017/6028645 pmid:28676821 pmcid:PMC5476838 fatcat:hb3tljwacnc2po4dbmibs27x3e

Prediction of exchange rates using averaging intrinsic mode function and multiclass support vector regression

Bhsana Premanode, Jumlong Vonprasert, Christofer Toumazou
2013 Artificial intelligence research  
To improve the accuracy, we propose a new model 'averaging intrinsic mode function' which is a derivative of empirical mode decomposition to filter datasets of an exchange rate, followed by using a new  ...  Simulation results show that the proposed model significantly improves prediction yields of the exchange rates, compared to simulation of SVR model without filtering and multiclass.  ...  Acknowledgements This work is fully inspired by the collaborations of The Department of Electrical and Electronic Engineering and Centre of Bio-Inspired Technology, Imperial College London.  ... 
doi:10.5430/air.v2n2p47 fatcat:ftetbkpmnbf5zke64jvzgrkrii
« Previous Showing results 1 — 15 out of 2,567 results