Abstract:
Objective: Our overall research goal is to use electroencephalography (EEG) to identify recognition of faces by patients with dementia to improve reminiscence therapy. The objective of this paper was to evaluate the performance of a g.tec EEG system using a facial recognition event related potential (ERP) task. Previous work has used the Emotiv off-The-shelf system which resulted in lack of classification. For this work, we sought to use a g.tec system with the same electrode placement as the Emotiv Insight to evaluate whether a reduced electrode set would provide sufficient classification accuracy. Methods: EEG was recorded with the same electrode montage as the Insight while obscure and famous facial stimuli were presented; participants confirmed recognition with a button press and oral confirmation. ERPs were averaged across five presentations of each facial stimuli to improve the signal to noise ratio. Classifiers were trained on one session, tested on another session. Results: Using the same electrode montage as the Insight, the g.tec achieved an average accuracy of 80%. Conclusion and Significance: A new research quality system with only the Pz electrode may provide sufficient classification to develop a system for reminiscence therapy.