Evaluating feature selection for stress identification

Yong Deng, Zhonghai Wu, Chao Hsien Chu, Tao Yang

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

14 Citations (Scopus)

Abstract

In modern society, more and more people are suffering from stress. The accumulation of stress will result in poor health condition to people. Effectively detecting the stress of human being in time provides a helpful way for people to better manage their stress. Much work has been done on recognizing the stress level of people by extracting features from the bio-signals acquired by physiological sensors. However, little work has been focused on the feature selection. In this paper, we propose a feature selection method based on Principal Component Analysis (PCA). After the features are selected, their effectiveness in terms of correct rate and computational time are evaluated using five classification algorithms, Linear Discriminant Function, C4.5 induction tree, Support Vector Machine (SVM), Naïve Bayes and K Nearest Neighbor (KNN). We use the driver stress database contributed by MIT Media lab for our experiments. Leaving one out as well as 10-fold data preparation approach is implemented as the cross validation method for our evaluation. Paired t-test is then performed to analyze and compare the experimental results, as well as for their statistical significance. Our study demonstrates the importance of feature selection and the effectiveness of the methods used in accurately classifying stress levels.

Original languageEnglish (US)
Title of host publicationProceedings of the 2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012
Pages584-591
Number of pages8
DOIs
StatePublished - Nov 8 2012
Event2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012 - Las Vegas, NV, United States
Duration: Aug 8 2012Aug 10 2012

Other

Other2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012
CountryUnited States
CityLas Vegas, NV
Period8/8/128/10/12

Fingerprint

Feature extraction
Trees (mathematics)
Principal component analysis
Support vector machines
Health
Sensors
Experiments

All Science Journal Classification (ASJC) codes

  • Information Systems

Cite this

Deng, Y., Wu, Z., Chu, C. H., & Yang, T. (2012). Evaluating feature selection for stress identification. In Proceedings of the 2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012 (pp. 584-591). [6303062] https://doi.org/10.1109/IRI.2012.6303062
Deng, Yong ; Wu, Zhonghai ; Chu, Chao Hsien ; Yang, Tao. / Evaluating feature selection for stress identification. Proceedings of the 2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012. 2012. pp. 584-591
@inproceedings{f698cc70accb46f4be9cf1694106ac23,
title = "Evaluating feature selection for stress identification",
abstract = "In modern society, more and more people are suffering from stress. The accumulation of stress will result in poor health condition to people. Effectively detecting the stress of human being in time provides a helpful way for people to better manage their stress. Much work has been done on recognizing the stress level of people by extracting features from the bio-signals acquired by physiological sensors. However, little work has been focused on the feature selection. In this paper, we propose a feature selection method based on Principal Component Analysis (PCA). After the features are selected, their effectiveness in terms of correct rate and computational time are evaluated using five classification algorithms, Linear Discriminant Function, C4.5 induction tree, Support Vector Machine (SVM), Na{\"i}ve Bayes and K Nearest Neighbor (KNN). We use the driver stress database contributed by MIT Media lab for our experiments. Leaving one out as well as 10-fold data preparation approach is implemented as the cross validation method for our evaluation. Paired t-test is then performed to analyze and compare the experimental results, as well as for their statistical significance. Our study demonstrates the importance of feature selection and the effectiveness of the methods used in accurately classifying stress levels.",
author = "Yong Deng and Zhonghai Wu and Chu, {Chao Hsien} and Tao Yang",
year = "2012",
month = "11",
day = "8",
doi = "10.1109/IRI.2012.6303062",
language = "English (US)",
isbn = "9781467322843",
pages = "584--591",
booktitle = "Proceedings of the 2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012",

}

Deng, Y, Wu, Z, Chu, CH & Yang, T 2012, Evaluating feature selection for stress identification. in Proceedings of the 2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012., 6303062, pp. 584-591, 2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012, Las Vegas, NV, United States, 8/8/12. https://doi.org/10.1109/IRI.2012.6303062

Evaluating feature selection for stress identification. / Deng, Yong; Wu, Zhonghai; Chu, Chao Hsien; Yang, Tao.

Proceedings of the 2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012. 2012. p. 584-591 6303062.

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

TY - GEN

T1 - Evaluating feature selection for stress identification

AU - Deng, Yong

AU - Wu, Zhonghai

AU - Chu, Chao Hsien

AU - Yang, Tao

PY - 2012/11/8

Y1 - 2012/11/8

N2 - In modern society, more and more people are suffering from stress. The accumulation of stress will result in poor health condition to people. Effectively detecting the stress of human being in time provides a helpful way for people to better manage their stress. Much work has been done on recognizing the stress level of people by extracting features from the bio-signals acquired by physiological sensors. However, little work has been focused on the feature selection. In this paper, we propose a feature selection method based on Principal Component Analysis (PCA). After the features are selected, their effectiveness in terms of correct rate and computational time are evaluated using five classification algorithms, Linear Discriminant Function, C4.5 induction tree, Support Vector Machine (SVM), Naïve Bayes and K Nearest Neighbor (KNN). We use the driver stress database contributed by MIT Media lab for our experiments. Leaving one out as well as 10-fold data preparation approach is implemented as the cross validation method for our evaluation. Paired t-test is then performed to analyze and compare the experimental results, as well as for their statistical significance. Our study demonstrates the importance of feature selection and the effectiveness of the methods used in accurately classifying stress levels.

AB - In modern society, more and more people are suffering from stress. The accumulation of stress will result in poor health condition to people. Effectively detecting the stress of human being in time provides a helpful way for people to better manage their stress. Much work has been done on recognizing the stress level of people by extracting features from the bio-signals acquired by physiological sensors. However, little work has been focused on the feature selection. In this paper, we propose a feature selection method based on Principal Component Analysis (PCA). After the features are selected, their effectiveness in terms of correct rate and computational time are evaluated using five classification algorithms, Linear Discriminant Function, C4.5 induction tree, Support Vector Machine (SVM), Naïve Bayes and K Nearest Neighbor (KNN). We use the driver stress database contributed by MIT Media lab for our experiments. Leaving one out as well as 10-fold data preparation approach is implemented as the cross validation method for our evaluation. Paired t-test is then performed to analyze and compare the experimental results, as well as for their statistical significance. Our study demonstrates the importance of feature selection and the effectiveness of the methods used in accurately classifying stress levels.

UR - http://www.scopus.com/inward/record.url?scp=84868325945&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84868325945&partnerID=8YFLogxK

U2 - 10.1109/IRI.2012.6303062

DO - 10.1109/IRI.2012.6303062

M3 - Conference contribution

SN - 9781467322843

SP - 584

EP - 591

BT - Proceedings of the 2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012

ER -

Deng Y, Wu Z, Chu CH, Yang T. Evaluating feature selection for stress identification. In Proceedings of the 2012 IEEE 13th International Conference on Information Reuse and Integration, IRI 2012. 2012. p. 584-591. 6303062 https://doi.org/10.1109/IRI.2012.6303062