Global Sensitivity Analysis Based on BP Neural Network for Thermal Design Parameters

Probabilistic Prediction of Unsafe Event in Air Traffic Control Department Based on the Improved Backpropagation Neural Network

“…ey proved that an ANN can learn any arithmetic or logical function [35]. Artificial neural networks have been widely used in various industries and have achieved excellent results [36,37].…”

“…e equation set formed by ( 29) has a redundant equation, which can be seen from ( 36) and (37). N unknown variables cannot be solved by N − 1 equations.…”

Global sensitivity analysis of parameters based on sPCE: The case study of a concrete face rockfill dam in northwest China

“…At present, the most effective method is to adopt a proxy model based on computer model responses. The proxy model is a statistical model used to simulate the input-output relationship of the original model, which can greatly reduce the calculation cost and improve the analysis efficiency [ 12 , 13 ]. The commonly used methods of establishing a proxy model include the regression method, Kriging method, artificial neural network, etc.…”

Global Sensitivity Analysis in Aerodynamic Design Using Shapley Effects and Polynomial Chaos Regression

“…Various surrogate models have been applied for GSA, including radial basis functions [6], Kriging/Gaussian process regression [7], [8], support vector regression [9], [10], random forest [11], and polynomial chaos expansion (PCE) [12], [13]; for most of the papers in surrogate-based GSA, Sobol indices [14] is the most widely used GSA method. Another possibility is to deploy a neural network as an approximation model [15], [16]. PCE is especially advantageous for GSA since the estimated Sobol indices can be exactly computed from the PCE coefficients [12].…”