Unifying genetic algorithm and clustering method for recognizing activated fMRI time series

Lin Shi; Pheng Ann Heng; Tien-Tsin Wong

doi:10.1007/11739685_25

Unifying genetic algorithm and clustering method for recognizing activated fMRI time series

Lin Shi, Pheng Ann Heng, Tien-Tsin Wong

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

1 Citation (Scopus)

Abstract

In order to get more reliable activation detection result in functional MRI data, we attempt to bring together the advantages of the genetic algorithm, which is deterministic and able to escape from the local optimal solution, and the K-means clustering, which is fast. Thus a novel clustering approach, namely the genetic K-means algorithm, is proposed to detect fMRI activation. It is more likely to find a global optimal solution to the K-means clustering, and is independent of the initial assignments of the cluster centroids. The experimental results show that the proposed method recognizes fMRI activation regions with higher accuracy than ordinary K-means clustering.

Original language	English
Title of host publication	Advances in Machine Learning and Cybernetics - 4th International Conference, ICMLC 2005, Revised Selected Papers
Publisher	Springer
Pages	239-248
Number of pages	10
ISBN (Print)	3540335846, 9783540335849
DOIs	https://doi.org/10.1007/11739685_25
Publication status	Published - 2006
Externally published	Yes
Event	International Conference on Machine Learning and Cybernetics 2005 - Guangzhou, China Duration: 18 Aug 2005 → 21 Aug 2005 Conference number: 4th https://link.springer.com/book/10.1007/11739685 (Proceedings)

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	3930
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	International Conference on Machine Learning and Cybernetics 2005
Abbreviated title	ICMLC 2005
Country/Territory	China
City	Guangzhou
Period	18/08/05 → 21/08/05
Internet address	https://link.springer.com/book/10.1007/11739685 (Proceedings)

Access to Document

10.1007/11739685_25

Cite this

@inproceedings{0c29845a4fbc4464a19316f42cca36db,

title = "Unifying genetic algorithm and clustering method for recognizing activated fMRI time series",

abstract = "In order to get more reliable activation detection result in functional MRI data, we attempt to bring together the advantages of the genetic algorithm, which is deterministic and able to escape from the local optimal solution, and the K-means clustering, which is fast. Thus a novel clustering approach, namely the genetic K-means algorithm, is proposed to detect fMRI activation. It is more likely to find a global optimal solution to the K-means clustering, and is independent of the initial assignments of the cluster centroids. The experimental results show that the proposed method recognizes fMRI activation regions with higher accuracy than ordinary K-means clustering.",

author = "Lin Shi and Heng, {Pheng Ann} and Tien-Tsin Wong",

year = "2006",

doi = "10.1007/11739685_25",

language = "English",

isbn = "3540335846",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "239--248",

booktitle = "Advances in Machine Learning and Cybernetics - 4th International Conference, ICMLC 2005, Revised Selected Papers",

note = "International Conference on Machine Learning and Cybernetics 2005, ICMLC 2005 ; Conference date: 18-08-2005 Through 21-08-2005",

url = "https://link.springer.com/book/10.1007/11739685",

}

Shi, L, Heng, PA & Wong, T-T 2006, Unifying genetic algorithm and clustering method for recognizing activated fMRI time series. in Advances in Machine Learning and Cybernetics - 4th International Conference, ICMLC 2005, Revised Selected Papers. Lecture Notes in Computer Science, vol. 3930, Springer, pp. 239-248, International Conference on Machine Learning and Cybernetics 2005, Guangzhou, China, 18/08/05. https://doi.org/10.1007/11739685_25

Unifying genetic algorithm and clustering method for recognizing activated fMRI time series. / Shi, Lin; Heng, Pheng Ann; Wong, Tien-Tsin.
Advances in Machine Learning and Cybernetics - 4th International Conference, ICMLC 2005, Revised Selected Papers. Springer, 2006. p. 239-248 (Lecture Notes in Computer Science; Vol. 3930).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Unifying genetic algorithm and clustering method for recognizing activated fMRI time series

AU - Shi, Lin

AU - Heng, Pheng Ann

AU - Wong, Tien-Tsin

N1 - Conference code: 4th

PY - 2006

Y1 - 2006

N2 - In order to get more reliable activation detection result in functional MRI data, we attempt to bring together the advantages of the genetic algorithm, which is deterministic and able to escape from the local optimal solution, and the K-means clustering, which is fast. Thus a novel clustering approach, namely the genetic K-means algorithm, is proposed to detect fMRI activation. It is more likely to find a global optimal solution to the K-means clustering, and is independent of the initial assignments of the cluster centroids. The experimental results show that the proposed method recognizes fMRI activation regions with higher accuracy than ordinary K-means clustering.

AB - In order to get more reliable activation detection result in functional MRI data, we attempt to bring together the advantages of the genetic algorithm, which is deterministic and able to escape from the local optimal solution, and the K-means clustering, which is fast. Thus a novel clustering approach, namely the genetic K-means algorithm, is proposed to detect fMRI activation. It is more likely to find a global optimal solution to the K-means clustering, and is independent of the initial assignments of the cluster centroids. The experimental results show that the proposed method recognizes fMRI activation regions with higher accuracy than ordinary K-means clustering.

UR - http://www.scopus.com/inward/record.url?scp=33745776293&partnerID=8YFLogxK

U2 - 10.1007/11739685_25

DO - 10.1007/11739685_25

M3 - Conference Paper

AN - SCOPUS:33745776293

SN - 3540335846

SN - 9783540335849

T3 - Lecture Notes in Computer Science

SP - 239

EP - 248

BT - Advances in Machine Learning and Cybernetics - 4th International Conference, ICMLC 2005, Revised Selected Papers

PB - Springer

T2 - International Conference on Machine Learning and Cybernetics 2005

Y2 - 18 August 2005 through 21 August 2005

ER -

Unifying genetic algorithm and clustering method for recognizing activated fMRI time series

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this