|
چکیده
|
Machine learning (ML) has been recognized as a feasible and reliable technique for the modeling of multi-parametric datasets. In real applications, there are different relationships with various complexities between sets of inputs and their corresponding outputs. As a result, various models have been developed with different levels of complexity in the input–output relationships. The group method of data handling (GMDH) employs a family of inductive algorithms for computer-based mathematical modeling grounded on a combination of quadratic and higher neurons in a certain number of variable layers. In this method, a vector of input features is mapped to the expected response by creating a multistage nonlinear pattern. Usually, each neuron of the GMDH is considered a quadratic partial function. In this paper, the basic structure of the GMDH technique is adapted by changing the partial functions to enhance the complexity modeling ability. To accomplish this, popular ML models that have shown reasonable function approximation performance, such as support vector regression and random forest, are used, and the basic polynomial functions in the GMDH are replaced by these ML models. The regression feasibility and validity of the ML-based GMDH models are confirmed by computer simulation.
|