Distinguishing cognitive states using iterative classification

P. K. Rakshatha, Vishal Vijayakumar, Neelam Sinha, Phaneendra K. Yalavarthy

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

To understand human brain functioning, task-specific analyses are extensively used. Functional Magnetic Resonance (fMR) images of subjects performing well-defined tasks are utilized. Here, for categorization of distinct cognitive states, a novel scheme that determines the most relevant voxels, using iterative classification, is proposed. In the proposed method, to distinguish between the chosen tasks, baseline classification performance using all active voxels is obtained initially. Subsequently, the brain volume is divided into 4 granules, where voxels belonging to each, are separately used for classification. The best-performing granule is weighted correspondingly higher, in the next iteration. The process of division is continued within the best-performing region. Classification is iteratively carried out till there is no significant change in performance. 10 real scan volumes from 2 public datasets are used to illustrate the performance of the proposed method. The performance of the proposed scheme in distinguishing cognitive tasks considered for the experiment is evaluated to be 99%.

Original languageEnglish
Title of host publicationProceedings - 8th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012
DOIs
Publication statusPublished - 01-12-2012
Externally publishedYes
Event8th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012 - Mumbai, India
Duration: 16-12-201219-12-2012

Conference

Conference8th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012
CountryIndia
CityMumbai
Period16-12-1219-12-12

Fingerprint

Brain
Magnetic resonance
Experiments

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Networks and Communications
  • Computer Vision and Pattern Recognition
  • Software

Cite this

Rakshatha, P. K., Vijayakumar, V., Sinha, N., & Yalavarthy, P. K. (2012). Distinguishing cognitive states using iterative classification. In Proceedings - 8th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012 https://doi.org/10.1145/2425333.2425354
Rakshatha, P. K. ; Vijayakumar, Vishal ; Sinha, Neelam ; Yalavarthy, Phaneendra K. / Distinguishing cognitive states using iterative classification. Proceedings - 8th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012. 2012.
@inproceedings{0e72ae969df34c0387f4018c7ee66898,
title = "Distinguishing cognitive states using iterative classification",
abstract = "To understand human brain functioning, task-specific analyses are extensively used. Functional Magnetic Resonance (fMR) images of subjects performing well-defined tasks are utilized. Here, for categorization of distinct cognitive states, a novel scheme that determines the most relevant voxels, using iterative classification, is proposed. In the proposed method, to distinguish between the chosen tasks, baseline classification performance using all active voxels is obtained initially. Subsequently, the brain volume is divided into 4 granules, where voxels belonging to each, are separately used for classification. The best-performing granule is weighted correspondingly higher, in the next iteration. The process of division is continued within the best-performing region. Classification is iteratively carried out till there is no significant change in performance. 10 real scan volumes from 2 public datasets are used to illustrate the performance of the proposed method. The performance of the proposed scheme in distinguishing cognitive tasks considered for the experiment is evaluated to be 99{\%}.",
author = "Rakshatha, {P. K.} and Vishal Vijayakumar and Neelam Sinha and Yalavarthy, {Phaneendra K.}",
year = "2012",
month = "12",
day = "1",
doi = "10.1145/2425333.2425354",
language = "English",
isbn = "9781450316606",
booktitle = "Proceedings - 8th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012",

}

Rakshatha, PK, Vijayakumar, V, Sinha, N & Yalavarthy, PK 2012, Distinguishing cognitive states using iterative classification. in Proceedings - 8th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012. 8th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012, Mumbai, India, 16-12-12. https://doi.org/10.1145/2425333.2425354

Distinguishing cognitive states using iterative classification. / Rakshatha, P. K.; Vijayakumar, Vishal; Sinha, Neelam; Yalavarthy, Phaneendra K.

Proceedings - 8th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012. 2012.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Distinguishing cognitive states using iterative classification

AU - Rakshatha, P. K.

AU - Vijayakumar, Vishal

AU - Sinha, Neelam

AU - Yalavarthy, Phaneendra K.

PY - 2012/12/1

Y1 - 2012/12/1

N2 - To understand human brain functioning, task-specific analyses are extensively used. Functional Magnetic Resonance (fMR) images of subjects performing well-defined tasks are utilized. Here, for categorization of distinct cognitive states, a novel scheme that determines the most relevant voxels, using iterative classification, is proposed. In the proposed method, to distinguish between the chosen tasks, baseline classification performance using all active voxels is obtained initially. Subsequently, the brain volume is divided into 4 granules, where voxels belonging to each, are separately used for classification. The best-performing granule is weighted correspondingly higher, in the next iteration. The process of division is continued within the best-performing region. Classification is iteratively carried out till there is no significant change in performance. 10 real scan volumes from 2 public datasets are used to illustrate the performance of the proposed method. The performance of the proposed scheme in distinguishing cognitive tasks considered for the experiment is evaluated to be 99%.

AB - To understand human brain functioning, task-specific analyses are extensively used. Functional Magnetic Resonance (fMR) images of subjects performing well-defined tasks are utilized. Here, for categorization of distinct cognitive states, a novel scheme that determines the most relevant voxels, using iterative classification, is proposed. In the proposed method, to distinguish between the chosen tasks, baseline classification performance using all active voxels is obtained initially. Subsequently, the brain volume is divided into 4 granules, where voxels belonging to each, are separately used for classification. The best-performing granule is weighted correspondingly higher, in the next iteration. The process of division is continued within the best-performing region. Classification is iteratively carried out till there is no significant change in performance. 10 real scan volumes from 2 public datasets are used to illustrate the performance of the proposed method. The performance of the proposed scheme in distinguishing cognitive tasks considered for the experiment is evaluated to be 99%.

UR - http://www.scopus.com/inward/record.url?scp=84872760624&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872760624&partnerID=8YFLogxK

U2 - 10.1145/2425333.2425354

DO - 10.1145/2425333.2425354

M3 - Conference contribution

SN - 9781450316606

BT - Proceedings - 8th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012

ER -

Rakshatha PK, Vijayakumar V, Sinha N, Yalavarthy PK. Distinguishing cognitive states using iterative classification. In Proceedings - 8th Indian Conference on Computer Vision, Graphics and Image Processing, ICVGIP 2012. 2012 https://doi.org/10.1145/2425333.2425354