Decoding Cognitive States from fMRI Data Using Single Hidden-Layer Feedforward Neural Networks

Author

Huynh, Hieu Trung ; Won, Yonggwan

Author_Institution

Dept. of Comput. Eng., Chonnam Nat. Univ., Gwangju

Volume

1

fYear

2008

fDate

2-4 Sept. 2008

Firstpage

256

Lastpage

260

Abstract

The development of functional magnetic resonance imaging (fMRI) offers promising approaches in the study of human brain function. It dramatically improves an ability to collect large amount of data about brain activity in human subjects performing tasks. Analysis of fMRI is essential for successful detection of cognitive states. This paper presents the use of single hidden-layer feedforward neural networks (SLFNs) to decode cognitive states from fMRI data. The SLFNs are trained by an improved extreme learning machine (ELM) which is named as regularized least-squares ELM (RLS-ELM). Experimental results show that the proposed method can give better performance compared to the Gaussian Naive Bayes (GNB) classifier that is known as one of the best classifiers for decoding cognitive states.

Keywords

Bayes methods; Gaussian processes; biomedical MRI; feedforward neural nets; image classification; least squares approximations; Gaussian naive Bayes classifier; cognitive states; decoding; extreme learning machine; fMRI data; functional magnetic resonance imaging; hidden-layer feedforward neural networks; human brain function; regularized least-squares ELM; Biological neural networks; Brain; Decoding; Feedforward neural networks; Gaussian processes; Humans; Machine learning; Magnetic analysis; Magnetic resonance imaging; Neural networks; Decoding cognitive states; Neural Network; RLS-ELM; SLFN; fMRI;

fLanguage

English

Publisher

ieee

Conference_Titel

Networked Computing and Advanced Information Management, 2008. NCM '08. Fourth International Conference on

Conference_Location

Gyeongju

Print_ISBN

978-0-7695-3322-3

Type

conf

DOI

10.1109/NCM.2008.76

Filename

4624014