Modulus of rupture prediction in Pinus sylvestris with multivariate models constructed with resonance, ultrasound, and wood heterogeneity variables

Multivariate models with multiple linear regression (MLR), artificial neural network (ANN), and k-nearest neighbors (KNN) were developed to predict the modulus of rupture Pinus sylvestris structural timber. The aim this study was develop compare these obtained from resonance ultrasound tests, static elasticity different measured wood feature. Resonance tests performed in three vibration modes (edgewise, flatwise, longitudinal) obtain fundamental resonant frequencies. To goodness-of-fit models, 10-fold cross-validation method used, which proved be an adequate strategy avoid overfitting. variable best predictive capacity knottiness. error notably lower multivariate than univariate models. ANN KNN algorithms showed no improvement over MLR. most suitable MLR for prediction model four variables: knottiness, edgewise dynamic elasticity, velocity ultrasounds, longitudinal frequency.