The effect of class-balance and class-overlap in the training set for multivariate and product-adapted grading of Scots pine sawn timber

Abstract

Using multivariate partial least squares regression (PLS) to perform visual quality grading of sawn timber requires a training set with known quality grades for the training of a grading model. This study evaluated the grading accuracy of an independent test set of sawn timber when changing the aspects of classbalance and class-overlap of the training set consisting of 251 planks. The study also compared two ways of expressing the reference-grade of the training set; by grading images picturing the planks, and by grading the product produced from the planks. Two grading models were trained using each reference-grade to establish a baseline for comparison. Both models achieved a 76% grading accuracy of the test set, indicating that both reference-grades can be used to train comparable models. To study the class-balance and class-overlap aspects of the training set, 25% of the training set was removed in two training scenarios. The models trained on class-balanced data indicated that classimbalance of the training set was not a problem. The models trained on data with less class-overlap using the product-grade reference suffered a 4%-points grading accuracy loss due to the smaller training set, while the model trained using the image-grade reference retained its grading accuracy.

Evaluation of Yield Improvements in Machine vs. Visual Strength Grading for Softwood Species

“…However, the percentage of rejection depends on the strength class combination considered, being the maximum increment of percentage of rejection (16%) reached for Scots pine in the combination C24/C18. For all the cases, it was observed that combinations with strength classes close to each other resulted in lower yields of the lower strength class and higher percentage of rejections, in agreement with that Olofsson et al [27] reached for Scots pine in Sweden. For example, for maritime pine, the yield of the strength class combination C27/C16/R resulted in values of 42%/57%/1% for in-line grading while the yield for C24/C16/R resulted in values of 64%/20%/16%; that is, a decrease of 22% of the yield of the second strength class and an increase of 15% of rejected specimens.…”