Analysis of EEG signals using deep learning to highlight effects of vibration-based therapy on brain

Abstract

Rehabilitation of patients with neurological disorders is a life-long process accomplished through pharmacological and non-pharmacological procedures for patient management. One non-pharmacological treatment that has become increasingly popular in the last decade is brain stimulation using vibration waves. This study analyses the impact of vibration waves on the brain utilizing electroencephalogram (EEG) signal analysis and visualizations to determine how they affect the brain. The investigation is performed on the entire brain activations of 11 healthy subjects, including six males and five females, who voluntarily participated in the study. The participants were first treated with a controlled procedure by giving an illusion of vibrations, and then these subjects had an intervention phase during which vibrations were administered. EEG signals of the individuals were recorded in both phases during the pre-post therapy period using a 32-channel cap following a defined protocol. In contrast to the controlled group also called controlled group, which had no activation, topographical maps of five frequency bands of the intervention group showed clear activation in frontal theta and contra-lateral beta activities. Further evidence that vibration waves applied to particular nerve points activate various parts of the brain is provided by the outcomes of a paired sample t-test on the controlled group and intervention group. For the classification of EEG signals, we proposed a computational framework of 3D Convolutional Neural Network(CNN) architecture with a combination of efficientnet-b4. Classification is performed for five frequency bands(separately for each band) and combined clean data. The highest accuracy is achieved with combined clean data, beta, Delta, Theta and Gamma bands i-e 100%, while 98.34% for the Alpha band.