Ensemble of surrogates and cross-validation for rapid and accurate predictions using small data sets

Abstract

In engineering design, surrogate models are often used instead of costly computer simulations. Typically, a single surrogate model is selected based on the previous experience. We observe, based on an analysis of the published literature, that fitting an ensemble of surrogates (EoS) based on cross-validation errors is more accurate but requires more computational time. In this paper, we propose a method to build an EoS that is both accurate and less computationally expensive. In the proposed method, the EoS is a weighted average surrogate of response surface models, kriging, and radial basis functions based on overall cross-validation error. We demonstrate that created EoS is accurate than individual surrogates even when fewer data points are used, so computationally efficient with relatively insensitive predictions. We demonstrate the use of an EoS using hot rod rolling as an example. Finally, we include a rule-based template which can be used for other problems with similar requirements, for example, the computational time, required accuracy, and the size of the data.

Machine learning using multi-modal data predicts the production of selective laser sintered 3D printed drug products

“…Thus, highlighting the benefit of using multi-modal data to make predictions. 'Consulting' multiple MLTs has been reported to improve model performance, which is analogous to consulting multiple human experts (Alizadeh et al, 2019;Phung and Rhee, 2019). Overall, the present study provides a compelling impetus for the use of multi-modal data for ML development to help improve the F1 score.…”

An approach to human iris recognition using quantitative analysis of image features and machine learning

“…10) using Keras library in python. Nowadays, neural networks and deep learning models are important parts of detection, prediction, classification, and recognition systems with different applications [35][36][37][38][39][40][41]. Our designed model was built by applying two hidden layers (with 1000 and 400 neurons, respectively) followed by one output classifier with 200 output class labels matching to 200 people in our dataset.…”

An active learning Bayesian ensemble surrogate model for structural reliability analysis

“…The ensemble modeling technique is a powerful tool, which can make full use of the prediction ability of multiple models. [21][22][23][24][25] Compared with the single surrogate model, the prediction performance of ensemble surrogate model (ESM) is more robust and reliable. Reliability analysis methods based on ESM are attracting more and more attention in recent years.…”