Application of Hybrid Metaheuristic Algorithms for Feature Selection in Event-Related Potential Classification in Problematic Gamers Using Electroencephalograph Signal

Online games have become a popular form of entertainment, particularly for relieving stress, and the rise in online gaming has led to an increase in problematic gaming behaviors. Excessive use of the internet for gaming has raised concerns about its neurophysiological impact, particularly on cognitive and emotional functions. Electroencephalogram signal and Event-Related Potential analysis are valuable tools for monitoring these effects. Given the vast amount of features that can be extracted from EEG signals, it is crucial to apply efficient feature selection methods to identify the most informative ones. This study utilizes the Go/No-Go Association Task combined with the recording of 16-channel EEG signals, chosen as the data-recording method to observe the response of individuals who are problematic online gamers to several stimulus themes. In this context, metaheuristic algorithms like Genetic Algorithm, Ant Colony Optimization, and Particle Swarm Optimization are employed to enhance feature selection. A hybrid approach, combining one of these methods with Binary Stochastic Fractal Search is proposed to improve classification accuracy and optimize feature selection. The results demonstrate that the hybridization of the best algorithm with B-SFS successfully selects the optimal features, achieving perfect classification performance, with an accuracy, sensitivity, and specificity of 1.00 for all respondents. This emphasizes the effectiveness of B-SFS, particularly its diffusion process, where Gaussian distribution facilitates the search for the best solution, thereby improving the reliability of feature selection for detecting problematic gaming behavior.