scholarly journals Circular regression trees and forests with an application to probabilistic wind direction forecasting

2020 ◽  
Vol 69 (5) ◽  
pp. 1357-1374
Author(s):  
Moritz N. Lang ◽  
Lisa Schlosser ◽  
Torsten Hothorn ◽  
Georg J. Mayr ◽  
Reto Stauffer ◽  
...  
Keyword(s):  
Wind Direction ◽  
Regression Trees ◽  
Circular Regression

scholarly journals A system for airport weather forecasting based on circular regression trees

2018 ◽  
Vol 100 ◽  
pp. 24-32
Author(s):  
Pablo Rozas Larraondo ◽  
Iñaki Inza ◽  
Jose A. Lozano
Keyword(s):  
Weather Forecasting ◽  
Regression Trees ◽  
Circular Regression

scholarly journals Ensemble of bagged regression trees for concrete dam deformation predicting

2019 ◽  
Vol 376 ◽  
pp. 012040 ◽  
Author(s):  
Jiemin Xie ◽  
Jun Zhang ◽  
Xuan Xie ◽  
Zhiwei Bi ◽  
Zhuoheng Li
Keyword(s):  
Regression Trees ◽  
Concrete Dam ◽  
Dam Deformation

scholarly journals The diurnal variation of wind direction at Calgary

Atmosphere ◽  
1968 ◽  
Vol 6 (2) ◽  
pp. 23-38 ◽  
Author(s):  
Richmond W. Longley
Keyword(s):  
Diurnal Variation ◽  
Wind Direction

Wind Pressure and Wind-Induced Vibration of Heliostat

2008 ◽  
Vol 400-402 ◽  
pp. 935-940 ◽  
Author(s):  
Ying Ge Wang ◽  
Zheng Nong Li ◽  
Bo Gong ◽  
Qiu Sheng Li
Keyword(s):  
Dynamic Response ◽  
Wind Direction ◽  
Wind Load ◽  
Wind Pressure ◽  
Induced Response ◽  
Vertical Angle ◽  
Lateral Direction ◽  
Direction Angle ◽  
Wind Pressures ◽  
Fluctuating Wind

Heliostat is the key part of Solar Tower power station, which requires extremely high accuracy in use. But it’s sensitive to gust because of its light structure, so effect of wind load should be taken into account in design. Since structure of heliostat is unusual and different from common ones, experimental investigation on rigid heliostat model using technology of surface pressure mensuration to test 3-dimensional wind loads in wind tunnel was conducted. The paper illustrates distribution and characteristics of reflector’s mean and fluctuating wind pressure while wind direction angle varied from 0° to 180° and vertical angle varied from 0° to 90°. Moreover, a finite element model was constructed to perform calculation on wind-induced dynamic response. The results show that the wind load power spectral change rulers are influenced by longitudinal wind turbulence and vortex and are related with Strouhal number; the fluctuating wind pressures between face and back mainly appear positive correlation, and the correlation coefficients at longitudinal wind direction are smaller than those at lateral direction; the fluctuating wind pressures preferably agree with Gaussian distribution at smaller vertical angle and wind direction angle. The wind-induced response and its spectrums reveal that: when vertical angle is small, the background responsive values of reflector’s different parts are approximately similar; in addition, multi-phased resonant response occurring at the bottom. With the increase of , airflow separates at the near side and reunites at the other, as produces vortex which enhances dynamic response at the upper part.

scholarly journals Lower Extremity Biomechanics Predicts Major League Baseball Player Performance

2021 ◽  
Vol 9 (7) ◽  
pp. 232596712110152
Author(s):  
Lucas G. Teske ◽  
Edward C. Beck ◽  
Garrett S. Bullock ◽  
Kristen F. Nicholson ◽  
Brian R. Waterman
Keyword(s):  
Lower Extremity ◽  
Major League Baseball ◽  
Reaction Force ◽  
Regression Trees ◽  
Minimal Detectable Change ◽  
Vertical Force ◽  
Baseball Players ◽  
Major League ◽  
Lower Extremity Biomechanics ◽  
Statistical Metrics

Background: Although lower extremity biomechanics has been correlated with traditional metrics among baseball players, its association with advanced statistical metrics has not been evaluated. Purpose: To establish normative biomechanical parameters during the countermovement jump (CMJ) among Major League Baseball (MLB) players and evaluate the relationship between CMJ-developed algorithms and advanced statistical metrics. Study Design: Cohort study; Level of evidence, 3. Methods: MLB players in 2 professional organizations performed the CMJ at the beginning of each baseball season from 2013 to 2017. We collected ground-reaction force data including the eccentric rate of force development (“load”), concentric vertical force (“explode”), and concentric vertical impulse (“drive”) as well as the Sparta Score. The advanced statistical metrics from each baseball season (eg, fielding independent pitching [FIP], weighted stolen base runs [wSB], and weighted on-base average) were also gathered for the study participants. The minimal detectable change (MDC) was calculated for each CMJ variable to establish normative parameters. Pearson coefficient analysis and regression trees were used to evaluate associations between CMJ data and advanced statistical metrics for the players. Results: A total of 151 pitchers and 138 batters were included in the final analysis. The MDC for “load,” “explode,” “drive,” and the Sparta Score was 10.3, 8.1, 8.7, and 4.6, respectively, and all demonstrated good reliability (intraclass correlation coefficient > 0.75). There was a weak but statistically significant correlation between the Sparta Score and wSB ( r = 0.23; P = .007); however, there were no significant correlations with any other advanced metrics. Regression trees demonstrated superior FIP with higher Sparta Scores in older pitchers compared with younger pitchers. Conclusion: There was a positive but weak correlation between the Sparta Score and base-stealing performance among professional baseball players. Additionally, older pitchers with a higher Sparta Score had statistically superior FIP compared with younger pitchers with a similar Sparta Score after adjusting for age.

scholarly journals SAT0587 MACHINE-LEARNING DERIVED ALGORITHMS FOR OUTCOMES PREDICTION IN RHEUMATIC DISEASES: APPLICATION TO RADIOGRAPHIC PROGRESSION IN EARLY AXIAL SPONDYLOARTHRITIS

2020 ◽  
Vol 79 (Suppl 1) ◽  
pp. 1252.2-1253
Author(s):  
R. Garofoli ◽  
M. Resche-Rigon ◽  
M. Dougados ◽  
D. Van der Heijde ◽  
C. Roux ◽  
...  
Keyword(s):  
Machine Learning ◽  
Radiographic Progression ◽  
Generalized Additive Models ◽  
Regression Trees ◽  
Information Criterion ◽  
Additive Models ◽  
Super Learner ◽  
Additive Regression ◽  
Selection Operator ◽  
Lasso Method

Background:Axial spondyloarthritis (axSpA) is a chronic rheumatic disease that encompasses various clinical presentations: inflammatory chronic back pain, peripheral manifestations and extra-articular manifestations. The current nomenclature divides axSpA in radiographic (in the presence of radiographic sacroiliitis) and non-radiographic (in the absence of radiographic sacroiliitis, with or without MRI sacroiliitis. Given that the functional burden of the disease appears to be greater in patients with radiographic forms, it seems crucial to be able to predict which patients will be more likely to develop structural damage over time. Predictive factors for radiographic progression in axSpA have been identified through use of traditional statistical models like logistic regression. However, these models present some limitations. In order to overcome these limitations and to improve the predictive performance, machine learning (ML) methods have been developed.Objectives:To compare ML models to traditional models to predict radiographic progression in patients with early axSpA.Methods:Study design: prospective French multicentric cohort study (DESIR cohort) with 5years of follow-up. Patients: all patients included in the cohort, i.e. 708 patients with inflammatory back pain for >3 months but <3 years, highly suggestive of axSpA. Data on the first 5 years of follow-up was used. Statistical analyses: radiographic progression was defined as progression either at the spine (increase of at least 1 point per 2 years of mSASSS scores) or at the sacroiliac joint (worsening of at least one grade of the mNY score between 2 visits). Traditional modelling: we first performed a bivariate analysis between our outcome (radiographic progression) and explanatory variables at baseline to select the variables to be included in our models and then built a logistic regression model (M1). Variable selection for traditional models was performed with 2 different methods: stepwise selection based on Akaike Information Criterion (stepAIC) method (M2), and the Least Absolute Shrinkage and Selection Operator (LASSO) method (M3). We also performed sensitivity analysis on all patients with manual backward method (M4) after multiple imputation of missing data. Machine learning modelling: using the “SuperLearner” package on R, we modelled radiographic progression with stepAIC, LASSO, random forest, Discrete Bayesian Additive Regression Trees Samplers (DBARTS), Generalized Additive Models (GAM), multivariate adaptive polynomial spline regression (polymars), Recursive Partitioning And Regression Trees (RPART) and Super Learner. Finally, the accuracy of traditional and ML models was compared based on their 10-foldcross-validated AUC (cv-AUC).Results:10-fold cv-AUC for traditional models were 0.79 and 0.78 for M2 and M3, respectively. The 3 best models in the ML algorithm were the GAM, the DBARTS and the Super Learner models, with 10-fold cv-AUC of: 0.77, 0.76 and 0.74, respectively (Table 1).Table 1.Comparison of 10-fold cross-validated AUC between best traditional and machine learning models.Best modelsCross-validated AUCTraditional models M2 (step AIC method)0.79 M3 (LASSO method)0.78Machine learning approach SL Discrete Bayesian Additive Regression Trees Samplers (DBARTS)0.76 SL Generalized Additive Models (GAM)0.77 Super Learner0.74AUC: Area Under the Curve; AIC: Akaike Information Criterion; LASSO: Least Absolute Shrinkage and Selection Operator; SL: SuperLearner. N = 295.Conclusion:Traditional models predicted better radiographic progression than ML models in this early axSpA population. Further ML algorithms image-based or with other artificial intelligence methods (e.g. deep learning) might perform better than traditional models in this setting.Acknowledgments:Thanks to the French National Society of Rheumatology and the DESIR cohort.Disclosure of Interests:Romain Garofoli: None declared, Matthieu resche-rigon: None declared, Maxime Dougados Grant/research support from: AbbVie, Eli Lilly, Merck, Novartis, Pfizer and UCB Pharma, Consultant of: AbbVie, Eli Lilly, Merck, Novartis, Pfizer and UCB Pharma, Speakers bureau: AbbVie, Eli Lilly, Merck, Novartis, Pfizer and UCB Pharma, Désirée van der Heijde Consultant of: AbbVie, Amgen, Astellas, AstraZeneca, BMS, Boehringer Ingelheim, Celgene, Cyxone, Daiichi, Eisai, Eli-Lilly, Galapagos, Gilead Sciences, Inc., Glaxo-Smith-Kline, Janssen, Merck, Novartis, Pfizer, Regeneron, Roche, Sanofi, Takeda, UCB Pharma; Director of Imaging Rheumatology BV, Christian Roux: None declared, Anna Moltó Grant/research support from: Pfizer, UCB, Consultant of: Abbvie, BMS, MSD, Novartis, Pfizer, UCB

scholarly journals Two Independent Light Dilution Corrections for the SO2 Camera Retrieve Comparable Emission Rates at Masaya Volcano, Nicaragua

2021 ◽  
Vol 13 (5) ◽  
pp. 935
Author(s):  
Matthew Varnam ◽  
Mike Burton ◽  
Ben Esse ◽  
Giuseppe Salerno ◽  
Ryunosuke Kazahaya ◽  
...  
Keyword(s):  
Light Scattering ◽  
Optical Depth ◽  
Camera Calibration ◽  
Wind Direction ◽  
Emission Rate ◽  
Emission Rates ◽  
Depth Images ◽  
Masaya Volcano ◽  
Rapid Changes ◽  
Volcanic Emission

SO2 cameras are able to measure rapid changes in volcanic emission rate but require accurate calibrations and corrections to convert optical depth images into slant column densities. We conducted a test at Masaya volcano of two SO2 camera calibration approaches, calibration cells and co-located spectrometer, and corrected both calibrations for light dilution, a process caused by light scattering between the plume and camera. We demonstrate an advancement on the image-based correction that allows the retrieval of the scattering efficiency across a 2D area of an SO2 camera image. When appropriately corrected for the dilution, we show that our two calibration approaches produce final calculated emission rates that agree with simultaneously measured traverse flux data and each other but highlight that the observed distribution of gas within the image is different. We demonstrate that traverses and SO2 camera techniques, when used together, generate better plume speed estimates for traverses and improved knowledge of wind direction for the camera, producing more reliable emission rates. We suggest combining traverses and the SO2 camera should be adopted where possible.

Sign in / Sign up

Export Citation Format

Share Document