Trigger pattern detection method for assisting in ambulation rehabilitation based on EEG analysis

This paper proposes a method to detect the trigger pattern of walking motion from an electroencephalogram (EEG). Our final goal is to develop a rehabilitation assistance system that can assist in ambulation exercise and be used on a daily basis by watching for the patient´s degree of functional recovery. Due to assist in ambulation rehabilitation, it needs to detect the feature signal related to the voluntary walking. As a first step, we detected an EEG feature pattern that has the potential to become the starting point of walking motion. The proposed method involves EEG recording, noise reduction, and EEG pattern classification. The EEG device had dry-type sensors and several electrodes with a headphone. Morphological filters were used to reduce EEG noise. The EEG patterns related to walking motion were classified using a support vector machine. To demonstrate the effectiveness of the proposed method, we conducted experiments using real EEG data.