IDENTIFICATION OF CHILDREN AT RISK OF SCHIZOPHRENIA VIA DEEP LEARNING AND EEG RESPONSES

Information Technology

For early intervention and better results, it is essential to identify children who may be at risk of schizophrenia, anxiety, stress disorder, autism, and other mental problems as early as possible. The non-invasive brain imaging method known as electroencephalography (EEG) may be used to assess the electrical activity of the brain. It has been demonstrated that EEG data can be helpful in detecting kids who may have mental health issues. EEG data is complicated and high-dimensional, which makes analysis difficult. This study suggests a unique method that combines PCA with the Naive Bayes algorithm to identify children who may be at risk of developing schizophrenia, anxiety, stress disorder, autism, or other mental problems. Initially, the dimensionality of the EEG data is decreased using PCA. The EEG data is then categorized into several categories using the Naive Bayes algorithm according to the child's likelihood of acquiring a mental condition. The suggested method was assessed using an EEG dataset containing the data of kids with and without mental health issues. The findings demonstrate that the suggested method is very accurate in identifying kids who may be at risk for mental health issues.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.