scholarly journals Predictive Performance of Artificial Neural Network and Multiple Linear Regression Models in Predicting Adhesive Bonding Strength of Wood

2016 ◽  
Vol 48 (6) ◽  
pp. 811-824 ◽  
Author(s):  
S. Bardak ◽  
S. Tiryaki ◽  
T. Bardak ◽  
A. Aydin
2017 ◽  
Vol 44 (12) ◽  
pp. 994-1004 ◽  
Author(s):  
Ivica Androjić ◽  
Ivan Marović

The oscillation of asphalt mix composition on a daily basis significantly affects the achieved properties of the asphalt during production, thus resulting in conducting expensive laboratory tests to determine existing properties and predicting the future results. To decrease the amount of such tests, a development of artificial neural network and multiple linear regression models in the prediction process of predetermined dependent variables air void and soluble binder content is presented. The input data were obtained from a single laboratory and consists of testing 386 mixes of hot mix asphalt (HMA). It was found that it is possible and desirable to apply such models in the prediction process of the HMA properties. The final aim of the research was to compare results of the prediction models on an independent dataset and analyze them through the boundary conditions of technical regulations and the standard EN 13108-21.


2012 ◽  
Vol 27 (1) ◽  
pp. 240-250 ◽  
Author(s):  
Si Gao ◽  
Long S. Chiu

Abstract A statistical–dynamical model has been used for operational guidance for tropical cyclone (TC) intensity prediction. In this study, several multiple linear regression models and neural network (NN) models are developed for the intensity prediction of western North Pacific TCs at 24-, 48-, and 72-h intervals. The multiple linear regression models include a model of climatology and persistence (CLIPER), a model based on the Statistical Typhoon Intensity Prediction System (STIPS), which serves as the base regression model (BASE), and a model of STIPS with additional satellite estimates of surface evaporation (SLHF) and inner-core rain rate (IRR, STIPER model). A revised equation for the TC maximum potential intensity is derived using Tropical Rainfall Measuring Mission Microwave Imager optimally interpolated sea surface temperature data, which have higher temporal and spatial resolutions. Analyses of the resulting models show the marginal improvement of STIPER over BASE. However, IRR and SLHF are found to be significant predictors in the predictor pool. Neural network models using the same predictors as STIPER show reductions of the mean absolute errors of 7%, 11%, and 16% relative to STIPER for 24-, 48-, and 72-h forecasts, respectively. The largest improvement is found for the intensity forecasts of the rapidly intensifying and rapidly decaying TCs.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Erik Frykholm ◽  
Sarah Gephine ◽  
Didier Saey ◽  
Arthur Lemson ◽  
Peter Klijn ◽  
...  

AbstractKnowledge about modifiable determinants of daily physical activity (PA) in patients with chronic obstructive pulmonary disease (COPD) is crucial to design effective PA interventions. The present study aimed to determine the contribution of quadriceps strength, power and endurance to daily PA in COPD. Additionally, for quadriceps endurance, we also aimed to determine to what extent the association varies according to the mode of movement (isotonic, isometric, or isokinetic). Using a multicentre cross-sectional trial design we determined the contribution of quadriceps function to daily PA (steps, sedentary time and time spent doing moderate-to-very-vigorous physical activity [MVPA]) using bivariate and partial Pearson correlation analysis (r) and multiple linear regression models (ΔR2). Pre-determined controlling factors were sex, age, body mass index (BMI), COPD-assessment test, forced expiratory volume in one second in percent of the predicted value (FEV1pred), and distance walked on the 6-minute walk test. Eighty-one patients with COPD (mean ± SD: age 67 ± 8 years, FEV1pred 57 ± 19%, daily steps 4968 ± 3319, daily sedentary time 1016 ± 305 min, and MVPA time 83 ± 45 min) were included. Small to moderate bivariate correlations (r = .225 to .452, p < .05) were found between quadriceps function and measures of PA. The best multiple linear regression models explained 38–49% of the variance in the data. Isotonic endurance was the only muscle contributor that improved all PA models; daily steps (ΔR2 = .04 [relative improvement 13%] p = .026), daily sedentary time (ΔR2 = .07 [23%], p = .005) and MVPA-minutes (ΔR2 = .08 [20%], p = .001). Isotonic endurance was also independently associated with most PA variables, even when controlling for strength, power or isometric-isokinetic endurance properties of the muscle (r = .246 to .384, p < .05). In contrast, neither strength, power, isometric-or isokinetic endurance properties of the muscle was independently associated with PA measures when controlling for isotonic endurance (r = .037 to .219, p > .05). To conclude, strength, power, and endurance properties of the quadriceps were low to moderately associated with PA in patients with COPD. Isotonic quadriceps endurance was the only quadriceps property that was independently associated with the different measures of PA after controlling for a basic set of known determinants of PA, quadriceps strength or power, or isometric or isokinetic quadriceps endurance. Future longitudinal studies should investigate its potential as a modifiable determinant of PA.


Sign in / Sign up

Export Citation Format

Share Document