Automatic depression discrimination on FNIRS by using fastICA/WPD and SVM

Hong Song*, Weilong Du, Qingjie Zhao

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Citations (Scopus)

Abstract

A method is proposed for distinguishing patients with depression from normal controls based on data measured by FNIRS during a cognitive task. First, Fast Independent Component Analysis (FastICA) and Wavelet Package Decomposition (WPD) are used to extract features from 52-channel Functional Near- Infrared Spectroscopy (FNIRS) data of patients with depression and normal healthy persons. Then a classifier based on Support Vector Machine (SVM) is designed for classification. The experimental results indicate that the proposed method can achieve a satisfactory classification with the accuracy 86.7647% for total and 90.74% for patients. Also, the results suggested that FNIRS may be a promising clinical tool in the diagnosis and treatment of psychiatric disorders.

Original languageEnglish
Title of host publicationProceedings of the 2015 Chinese Intelligent Automation Conference - Intelligent Information Processing
EditorsZhidong Deng, Hongbo Li
PublisherSpringer Verlag
Pages257-265
Number of pages9
ISBN (Print)9783662464687
DOIs
Publication statusPublished - 2015
EventChinese Intelligent Automation Conference, 2015 - Fuzhou, China
Duration: 1 Jan 2015 → …

Publication series

NameLecture Notes in Electrical Engineering
Volume336
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceChinese Intelligent Automation Conference, 2015
Country/TerritoryChina
CityFuzhou
Period1/01/15 → …

Keywords

  • Depression discrimination
  • FNIRS
  • FastICA
  • SVM
  • WPD

Fingerprint

Dive into the research topics of 'Automatic depression discrimination on FNIRS by using fastICA/WPD and SVM'. Together they form a unique fingerprint.

Cite this