Extracting coherent emotion elicited segments from physiological signals

研究成果: Conference contribution

5 引文 (Scopus)

摘要

The feasibility of real life affective detection using physiological signals is usually limited by biosensor noise and artifact. This is challenging in extracting the representative emotion features. In this paper a quasi-homogeneous segmentation algorithm based on Top-Down homogeneous splitting and Bottom-Up Merging using Bhattacharyya distance is proposed to partition the signal and remove artifacts. Furthermore, since physiological responses may also vary within one emotion elicited period, features extracted from segmented segments can better describe recent physiological patterns. In this paper a constraint-based clustering analysis based on estimating best seed of K-means is developed to discover representative emotion-elicited segments at all cross subject partitions which include labeled and unlabelled feature vectors.

原文English
主出版物標題IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011
主出版物子標題2011 Workshop on Affective Computational Intelligence
頁面55-61
頁數7
DOIs
出版狀態Published - 2011 八月 10
事件Symposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 Workshop on Affective Computational Intelligence, WACI 2011 - Paris, France
持續時間: 2011 四月 112011 四月 15

出版系列

名字IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence

Other

OtherSymposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 Workshop on Affective Computational Intelligence, WACI 2011
國家France
城市Paris
期間11-04-1111-04-15

指紋

Merging
Biosensors
Seed

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computational Theory and Mathematics

引用此文

Wu, C. K., Chung, P-C., & Wang, C-J. (2011). Extracting coherent emotion elicited segments from physiological signals. 於 IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence (頁 55-61). [5953149] (IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence). https://doi.org/10.1109/WACI.2011.5953149
Wu, Chi Keng ; Chung, Pau-Choo ; Wang, Chi-Jen. / Extracting coherent emotion elicited segments from physiological signals. IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence. 2011. 頁 55-61 (IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence).
@inproceedings{71926c7e5dbd474baf95d8506c5fb2d1,
title = "Extracting coherent emotion elicited segments from physiological signals",
abstract = "The feasibility of real life affective detection using physiological signals is usually limited by biosensor noise and artifact. This is challenging in extracting the representative emotion features. In this paper a quasi-homogeneous segmentation algorithm based on Top-Down homogeneous splitting and Bottom-Up Merging using Bhattacharyya distance is proposed to partition the signal and remove artifacts. Furthermore, since physiological responses may also vary within one emotion elicited period, features extracted from segmented segments can better describe recent physiological patterns. In this paper a constraint-based clustering analysis based on estimating best seed of K-means is developed to discover representative emotion-elicited segments at all cross subject partitions which include labeled and unlabelled feature vectors.",
author = "Wu, {Chi Keng} and Pau-Choo Chung and Chi-Jen Wang",
year = "2011",
month = "8",
day = "10",
doi = "10.1109/WACI.2011.5953149",
language = "English",
isbn = "9781612840840",
series = "IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence",
pages = "55--61",
booktitle = "IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011",

}

Wu, CK, Chung, P-C & Wang, C-J 2011, Extracting coherent emotion elicited segments from physiological signals. 於 IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence., 5953149, IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence, 頁 55-61, Symposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 Workshop on Affective Computational Intelligence, WACI 2011, Paris, France, 11-04-11. https://doi.org/10.1109/WACI.2011.5953149

Extracting coherent emotion elicited segments from physiological signals. / Wu, Chi Keng; Chung, Pau-Choo; Wang, Chi-Jen.

IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence. 2011. p. 55-61 5953149 (IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence).

研究成果: Conference contribution

TY - GEN

T1 - Extracting coherent emotion elicited segments from physiological signals

AU - Wu, Chi Keng

AU - Chung, Pau-Choo

AU - Wang, Chi-Jen

PY - 2011/8/10

Y1 - 2011/8/10

N2 - The feasibility of real life affective detection using physiological signals is usually limited by biosensor noise and artifact. This is challenging in extracting the representative emotion features. In this paper a quasi-homogeneous segmentation algorithm based on Top-Down homogeneous splitting and Bottom-Up Merging using Bhattacharyya distance is proposed to partition the signal and remove artifacts. Furthermore, since physiological responses may also vary within one emotion elicited period, features extracted from segmented segments can better describe recent physiological patterns. In this paper a constraint-based clustering analysis based on estimating best seed of K-means is developed to discover representative emotion-elicited segments at all cross subject partitions which include labeled and unlabelled feature vectors.

AB - The feasibility of real life affective detection using physiological signals is usually limited by biosensor noise and artifact. This is challenging in extracting the representative emotion features. In this paper a quasi-homogeneous segmentation algorithm based on Top-Down homogeneous splitting and Bottom-Up Merging using Bhattacharyya distance is proposed to partition the signal and remove artifacts. Furthermore, since physiological responses may also vary within one emotion elicited period, features extracted from segmented segments can better describe recent physiological patterns. In this paper a constraint-based clustering analysis based on estimating best seed of K-means is developed to discover representative emotion-elicited segments at all cross subject partitions which include labeled and unlabelled feature vectors.

UR - http://www.scopus.com/inward/record.url?scp=79961160070&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79961160070&partnerID=8YFLogxK

U2 - 10.1109/WACI.2011.5953149

DO - 10.1109/WACI.2011.5953149

M3 - Conference contribution

AN - SCOPUS:79961160070

SN - 9781612840840

T3 - IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence

SP - 55

EP - 61

BT - IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011

ER -

Wu CK, Chung P-C, Wang C-J. Extracting coherent emotion elicited segments from physiological signals. 於 IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence. 2011. p. 55-61. 5953149. (IEEE SSCI 2011 - Symposium Series on Computational Intelligence - WACI 2011: 2011 Workshop on Affective Computational Intelligence). https://doi.org/10.1109/WACI.2011.5953149