A suite of metrics in overall dyslexia assessment: drift entropy impact.

Abstract

Contemporary neuroscience scientists are interested in dyslexia, a complicated brain neurodevelopmental disorder. This condition causes slow and imprecise word comprehension in 5%-17% of the global population across languages and cultures. People with dyslexia often discuss mental health. On the scalp, the EEG signal shows coordinated neural activity that synchronizes. The EEG signal accurately captures these cerebral activity fluctuations due to evolution and mental state. Using statistical approaches, this study will determine if EEG waves indicate sickness. For this, three measures are suggested. The first metric, power spectral density, shows signal frequency and power distribution. The second metric assesses the model's uncertainty or randomness, conveying signal information, using entropy. The third metric, the Kolmogorov-Smirnov Test, uses entropy-based measurements to identify distributions based on Kolmogorov complexity. Applying these measures to the overall EEG signal of the twenty students under study separated the seven students' information from the other thirteen.