2.7. Network specifications

The predictive model employed in this study is based on the Multilayer Perceptron (MLP) architecture. MLPs are a class of artificial neural networks consisting of interconnected layers of nodes, where each node performs a weighted sum of inputs and applies an activation function to produce an output. The model architecture includes an Input Layer, two Hidden Layers, and an Output Layer. The Input Layer contains 18 units, representing the covariates and input factors. The two Hidden Layers consist of 8 and 6 units, respectively, and are activated using the hyperbolic tangent activation function. The Output Layer comprises 2 units, representing the binary classification of social dysfunction, and uses the identity activation function. Specifications of MLP artificial neural network have been presented in Table 1.

Specifications of MLP artificial neural networks used in this research.