A hybrid method for classifying cognitive states from fMRI data

S. Parida, S. Dehuri, Sung-Bae Cho, L. A. Cacha, R. R. Poznanski

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Functional magnetic resonance imaging (fMRI) makes it possible to detect brain activities in order to elucidate cognitive-states. The complex nature of fMRI data requires under-standing of the analyses applied to produce possible avenues for developing models of cognitive state classification and improving brain activity prediction. While many models of classification task of fMRI data analysis have been developed, in this paper, we present a novel hybrid technique through combining the best attributes of genetic algorithms (GAs) and ensemble decision tree technique that consistently outperforms all other methods which are being used for cognitive-state classification. Specifically, this paper illustrates the combined effort of decision-trees ensemble and GAs for feature selection through an extensive simulation study and discusses the classification performance with respect to fMRI data. We have shown that our proposed method exhibits significant reduction of the number of features with clear edge classification accuracy over ensemble of decision-trees.

Original languageEnglish
Pages (from-to)355-368
Number of pages14
JournalJournal of Integrative Neuroscience
Volume14
Issue number3
DOIs
Publication statusPublished - 2015 Jan 1

Fingerprint

Decision Trees
Magnetic Resonance Imaging
Brain

All Science Journal Classification (ASJC) codes

  • Neuroscience(all)

Cite this

Parida, S. ; Dehuri, S. ; Cho, Sung-Bae ; Cacha, L. A. ; Poznanski, R. R. / A hybrid method for classifying cognitive states from fMRI data. In: Journal of Integrative Neuroscience. 2015 ; Vol. 14, No. 3. pp. 355-368.
@article{36078a1452cc4865af0797251260a713,
title = "A hybrid method for classifying cognitive states from fMRI data",
abstract = "Functional magnetic resonance imaging (fMRI) makes it possible to detect brain activities in order to elucidate cognitive-states. The complex nature of fMRI data requires under-standing of the analyses applied to produce possible avenues for developing models of cognitive state classification and improving brain activity prediction. While many models of classification task of fMRI data analysis have been developed, in this paper, we present a novel hybrid technique through combining the best attributes of genetic algorithms (GAs) and ensemble decision tree technique that consistently outperforms all other methods which are being used for cognitive-state classification. Specifically, this paper illustrates the combined effort of decision-trees ensemble and GAs for feature selection through an extensive simulation study and discusses the classification performance with respect to fMRI data. We have shown that our proposed method exhibits significant reduction of the number of features with clear edge classification accuracy over ensemble of decision-trees.",
author = "S. Parida and S. Dehuri and Sung-Bae Cho and Cacha, {L. A.} and Poznanski, {R. R.}",
year = "2015",
month = "1",
day = "1",
doi = "10.1142/S0219635215500223",
language = "English",
volume = "14",
pages = "355--368",
journal = "Journal of Integrative Neuroscience",
issn = "0219-6352",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "3",

}

A hybrid method for classifying cognitive states from fMRI data. / Parida, S.; Dehuri, S.; Cho, Sung-Bae; Cacha, L. A.; Poznanski, R. R.

In: Journal of Integrative Neuroscience, Vol. 14, No. 3, 01.01.2015, p. 355-368.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A hybrid method for classifying cognitive states from fMRI data

AU - Parida, S.

AU - Dehuri, S.

AU - Cho, Sung-Bae

AU - Cacha, L. A.

AU - Poznanski, R. R.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Functional magnetic resonance imaging (fMRI) makes it possible to detect brain activities in order to elucidate cognitive-states. The complex nature of fMRI data requires under-standing of the analyses applied to produce possible avenues for developing models of cognitive state classification and improving brain activity prediction. While many models of classification task of fMRI data analysis have been developed, in this paper, we present a novel hybrid technique through combining the best attributes of genetic algorithms (GAs) and ensemble decision tree technique that consistently outperforms all other methods which are being used for cognitive-state classification. Specifically, this paper illustrates the combined effort of decision-trees ensemble and GAs for feature selection through an extensive simulation study and discusses the classification performance with respect to fMRI data. We have shown that our proposed method exhibits significant reduction of the number of features with clear edge classification accuracy over ensemble of decision-trees.

AB - Functional magnetic resonance imaging (fMRI) makes it possible to detect brain activities in order to elucidate cognitive-states. The complex nature of fMRI data requires under-standing of the analyses applied to produce possible avenues for developing models of cognitive state classification and improving brain activity prediction. While many models of classification task of fMRI data analysis have been developed, in this paper, we present a novel hybrid technique through combining the best attributes of genetic algorithms (GAs) and ensemble decision tree technique that consistently outperforms all other methods which are being used for cognitive-state classification. Specifically, this paper illustrates the combined effort of decision-trees ensemble and GAs for feature selection through an extensive simulation study and discusses the classification performance with respect to fMRI data. We have shown that our proposed method exhibits significant reduction of the number of features with clear edge classification accuracy over ensemble of decision-trees.

UR - http://www.scopus.com/inward/record.url?scp=84947036607&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947036607&partnerID=8YFLogxK

U2 - 10.1142/S0219635215500223

DO - 10.1142/S0219635215500223

M3 - Article

VL - 14

SP - 355

EP - 368

JO - Journal of Integrative Neuroscience

JF - Journal of Integrative Neuroscience

SN - 0219-6352

IS - 3

ER -