Data augmentation technique for construction engineering regression surrogate model

Abstract

The objective of this study is to predict the degree of danger to the human body from motion information such as acceleration, velocity and displacement during a collision between a car and a human body. As a preliminary step, the maximum bending moment that occurs in the leg was predicted using a convolutional neural network. The responses which are represented by learning data generated by 1D-CAE system. A number of training data sets are varied in order to show the enough number to predict. The predictor's accuracy is evaluated by the test data sets. We'd like to discuss necessisty of a total number of training data sets and effectiveness of data augmentation technique. In addition, the technique to utilize classification by the t-SNE method to improve accuracy is also examined. t-SNE is based on classification algorithm, however an engineering interpolation should be computed based on physical meanings and influential parameters.

Full Paper