Condition-Based Classification of EEG Signal With Pauli Test Stimuli and Social Media Content Using Discrete Wavelet Transform

Distraction denotes a state wherein an individual encounters a stimulus that deviates attention from a given activity. Each activity exhibits distinctive characteristics when scrutinized through EEG signals, thereby implying that variations in brain signal responses are inherent across different conditions. Conversely, a multitude of studies has scrutinized the impact of external stimuli on an individual's psychological state, encompassing relaxation, concentration, and even anxiety. This study endeavors to classify EEG signals contingent upon specific conditions. The stimuli encompass social media content and Pauli tests, designed to induce respondents into states of relaxation, distraction, and non-distraction. The EEG signals recorded under these three conditions were subjected to processing utilizing DWT Daubechies 4 (db4). Subsequently, a backpropagation neural network facilitated the classification process. A dataset comprising a total of 180 instances, with 150 allocated for training and 30 for testing, demonstrated an accuracy rate of 88.89%.