Feature selection and combination for stress identification using correlation and diversity

Yong Deng; D. Frank Hsu; Zhonghai Wu; Chao Hsien Chu

doi:10.1109/I-SPAN.2012.12

Feature selection and combination for stress identification using correlation and diversity

Yong Deng
, D. Frank Hsu
, Zhonghai Wu
, Chao Hsien Chu

College of Information Sciences and Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

19 Scopus citations

Abstract

Using multiple physiological sensors to detect different stress level has become an important and popular task in improving human health and well-being. In the process, the selection of a smaller set of independent features is a necessary, yet challenging, step for feature combination, situation analysis and decision making. In this paper, we investigate feature selection methods using both concepts of correlation and diversity. Six feature combination methods (C4.5, Naïve Bayes, Linear Discriminant Function, Support Vector Machine, K Nearest Neighbors and Combinatorial Fusion) are applied to the selected features in the detection of the stress levels. Our results demonstrated that (a) diversity based feature selection is as good as correlation based selection across all six combination methods, and (b) combinatorial fusion method performs better than five other combination methods across all features selected by using both correlation and diversity.

Original language	English (US)
Title of host publication	Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012
Pages	37-43
Number of pages	7
DOIs	https://doi.org/10.1109/I-SPAN.2012.12
State	Published - Dec 1 2012
Event	12th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012 - San Marcos, TX, United States Duration: Dec 13 2012 → Dec 15 2012

Publication series

Name	Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012

Other

Other	12th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012
Country/Territory	United States
City	San Marcos, TX
Period	12/13/12 → 12/15/12

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Applied Mathematics

Access to Document

10.1109/I-SPAN.2012.12

Cite this

Deng, Y., Hsu, D. F., Wu, Z., & Chu, C. H. (2012). Feature selection and combination for stress identification using correlation and diversity. In Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012 (pp. 37-43). Article 6428803 (Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012). https://doi.org/10.1109/I-SPAN.2012.12

Deng, Yong ; Hsu, D. Frank ; Wu, Zhonghai et al. / Feature selection and combination for stress identification using correlation and diversity. Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012. 2012. pp. 37-43 (Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012).

@inproceedings{990dd319e95f446fa49fa85df88af305,

title = "Feature selection and combination for stress identification using correlation and diversity",

abstract = "Using multiple physiological sensors to detect different stress level has become an important and popular task in improving human health and well-being. In the process, the selection of a smaller set of independent features is a necessary, yet challenging, step for feature combination, situation analysis and decision making. In this paper, we investigate feature selection methods using both concepts of correlation and diversity. Six feature combination methods (C4.5, Na{\"i}ve Bayes, Linear Discriminant Function, Support Vector Machine, K Nearest Neighbors and Combinatorial Fusion) are applied to the selected features in the detection of the stress levels. Our results demonstrated that (a) diversity based feature selection is as good as correlation based selection across all six combination methods, and (b) combinatorial fusion method performs better than five other combination methods across all features selected by using both correlation and diversity.",

author = "Yong Deng and Hsu, \{D. Frank\} and Zhonghai Wu and Chu, \{Chao Hsien\}",

year = "2012",

month = dec,

day = "1",

doi = "10.1109/I-SPAN.2012.12",

language = "English (US)",

isbn = "9780769549309",

series = "Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012",

pages = "37--43",

booktitle = "Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012",

note = "12th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012 ; Conference date: 13-12-2012 Through 15-12-2012",

}

Deng, Y, Hsu, DF, Wu, Z & Chu, CH 2012, Feature selection and combination for stress identification using correlation and diversity. in Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012., 6428803, Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012, pp. 37-43, 12th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012, San Marcos, TX, United States, 12/13/12. https://doi.org/10.1109/I-SPAN.2012.12

Feature selection and combination for stress identification using correlation and diversity. / Deng, Yong; Hsu, D. Frank; Wu, Zhonghai et al.
Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012. 2012. p. 37-43 6428803 (Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Feature selection and combination for stress identification using correlation and diversity

AU - Deng, Yong

AU - Hsu, D. Frank

AU - Wu, Zhonghai

AU - Chu, Chao Hsien

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Using multiple physiological sensors to detect different stress level has become an important and popular task in improving human health and well-being. In the process, the selection of a smaller set of independent features is a necessary, yet challenging, step for feature combination, situation analysis and decision making. In this paper, we investigate feature selection methods using both concepts of correlation and diversity. Six feature combination methods (C4.5, Naïve Bayes, Linear Discriminant Function, Support Vector Machine, K Nearest Neighbors and Combinatorial Fusion) are applied to the selected features in the detection of the stress levels. Our results demonstrated that (a) diversity based feature selection is as good as correlation based selection across all six combination methods, and (b) combinatorial fusion method performs better than five other combination methods across all features selected by using both correlation and diversity.

AB - Using multiple physiological sensors to detect different stress level has become an important and popular task in improving human health and well-being. In the process, the selection of a smaller set of independent features is a necessary, yet challenging, step for feature combination, situation analysis and decision making. In this paper, we investigate feature selection methods using both concepts of correlation and diversity. Six feature combination methods (C4.5, Naïve Bayes, Linear Discriminant Function, Support Vector Machine, K Nearest Neighbors and Combinatorial Fusion) are applied to the selected features in the detection of the stress levels. Our results demonstrated that (a) diversity based feature selection is as good as correlation based selection across all six combination methods, and (b) combinatorial fusion method performs better than five other combination methods across all features selected by using both correlation and diversity.

UR - https://www.scopus.com/pages/publications/84874589587

UR - https://www.scopus.com/pages/publications/84874589587#tab=citedBy

U2 - 10.1109/I-SPAN.2012.12

DO - 10.1109/I-SPAN.2012.12

M3 - Conference contribution

AN - SCOPUS:84874589587

SN - 9780769549309

T3 - Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012

SP - 37

EP - 43

BT - Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012

T2 - 12th International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012

Y2 - 13 December 2012 through 15 December 2012

ER -

Deng Y, Hsu DF, Wu Z, Chu CH. Feature selection and combination for stress identification using correlation and diversity. In Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012. 2012. p. 37-43. 6428803. (Proceedings of the 2012 International Symposium on Pervasive Systems, Algorithms, and Networks, I-SPAN 2012). doi: 10.1109/I-SPAN.2012.12

Feature selection and combination for stress identification using correlation and diversity

Abstract

Publication series

Other

UN SDGs

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this