Please use this identifier to cite or link to this item:
Title: Brain-computer interface and visual perception
Authors: Cheoh, Xin Mei
Keywords: DRNTU::Engineering::Computer science and engineering::Computer applications
Issue Date: 2015
Abstract: There has been an increasing amount of research and development done in the field of brain-computer interface (BCI) technology. Both the generation of visual images and the perception of the actual images activate practically the same brain centres. Hence, the research on examining the efficacy of the classification of brain signals based on two different categories of images (faces and houses) is of significance because it helps to address BCI-related issues that concern with the trigger of brain centres during imagination. The purpose of the project is to recognise electroencephalography (EEG) patterns according to the types of images that the subject is supposed to visualise. The experiments were conducted using the Emotiv EPOC headset, and VisualX, a software developed for the study. The Bayesian approach was implemented to evaluate the results, and it was determined that EEG artifacts would not have a substantial effect on the outcome. It was discovered that the overall classification accuracy of the study was 47%. In order to enhance the classification quality, the number of images to imagine in the training and test phases could be increase, so that additional input would be accessible for analysis. Moreover, it seemed plausible to examine not only the images of faces and houses, but also other types of visual images. It was recommended that alternative classifiers could be further explored to attain a higher precision during the classification process.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
Final Year Project Report.pdf
  Restricted Access
1.67 MBAdobe PDFView/Open

Page view(s)

Updated on Nov 26, 2020

Download(s) 50

Updated on Nov 26, 2020

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.