Abstract

Brain activity recognition based on functional magnetic resonance image (fMRI) as a vital problem in computer vision has been applied to many fields. Chinese character processing is one of the most remarkable applications of brain activity recognition at present, it has shown great performance using activation data and cognitive experiment in different brain regions. Inspired by new machine learning methods, this paper proposes an extraction method of human brain data with region of interest (ROI) and a activity recognition method of classifying Chinese character processing with support vector machine (SVM) and random forest (RF). By comparison, the SVM approach and RF approach achieve the average correct classification rate of Left Inferior Frontal Gyrus (LIFG) region of human brain with 74.1% and 80.5% after the ROI extraction, respectively. The experiments indicate that the brain's processing mechanism does differ when facing the Chinese characters of different structures, the LIFG brain region plays an important role in this process, and the RF approach would achieve better performance than SVM in term of average correct classification rate.

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.