Comparison of MLP and RBF Neural Models on the Example Graphical Classification

In the paper, the classification capabilities of perceptron and radial neural networks are compared the example process identification of graphical compost quality. The classification was based on graphical information coded as selected quality features of the compost quality, presented in colour digital images. In the paper, MLP (MultiLayer Perceptrons) and RBF (Radial Basis Function) neural classification models are compared, generated using learning sets acquired on the basis of information contained in digital photographs of compost. In order to classify the compost pictures, modern neural modelling methods were used, including digital image analysis techniques. The qualitative analysis of the neural models enabled the compare of the MLP and RBF neuron topology and identification ANN that was characterised by the highest classification capability. Characteristic features enabling effective identification of a pest were 16 selected graphical parameters. The created neuron model is dedicated as a core for computer systems supporting decision processes occurring during compost production.

Automated summary

This paper compares the classification capabilities of perceptron and radial neural networks in the identification of graphical compost quality, using modern neural modelling techniques and digital image analysis. The study highlights the effectiveness of the neural models for identifying pests in compost pictures, with a focus on specific graphical parameters. The created neuron model serves as the core for computer systems supporting decision-making processes in compost production.