Classifying Instantaneous Cognitive States from fMRI using Discriminant based Feature Selection and Adaboost

• 발행기관: 한국스마트미디어학회
• 저자명: Tien Duong Vu Hyung-Jeong Yang Luu Ngoc Do Thao Nguyen Thieu
• 간행물 정보: 『스마트미디어저널』Vol5, No.1, 1~8쪽, 전체 8쪽
• 주제분류: 공학 > 컴퓨터학
• 파일형태: PDF
• 발행일자: 2016.03.30

영문 초록

In recent decades, the study of human brain function has dramatically increased thanks to the advent of Functional Magnetic Resonance Imaging. This is a powerful tool which provides a deep view of the activities of the brain. From fMRI data, the neuroscientists analyze which parts of the brain have responsibility for a particular action and finding the common pattern representing each state involved in these tasks. This is one of the most challenges in neuroscience area because of noisy, sparsity of data as well as the differences of anatomical brain structure of each person. In this paper, we propose the use of appropriate discriminant methods, such as Fisher Discriminant Ratio and hypothesis testing, together with strong boosting ability of Adaboost classifier. We prove that discriminant methods are effective in classifying cognitive states. The experiment results show significant better accuracy than previous works. We also show that it is possible to train a successful classifier without prior anatomical knowledge and use only a small number of features.

목차

I. INTRODUCTION

II. RELATED WORK

III. PROPOSED METHOD

IV. EXPERIMENT

V. CONCLUSION

키워드

cognitive states|Adaboost|Fisher Discriminant Ratio|hypothesis testing|classification