Model Accuracy of the IDS Method for Three-input Systems and a Basic Constructive Algorithm for Structural Optimization

The ink drop spread (IDS) method is a modeling technique that has several advantages in real-time capabilities, tractability, and interpretability of models; thus, it has a good potential to be a useful soft computing tool. This paper presents an inferential process of the IDS method in order to deal with more than two input variables and the accuracy of IDS models for three-input nonlinear systems. In addition, a basic constructive algorithm is proposed for the structural optimization of IDS models, and it is used in the evaluation of regression performance.