TY - GEN
T1 - Extracting coherent emotion elicited segments from physiological signals
AU - Wu, Chi Keng
AU - Chung, Pau Choo
AU - Wang, Chi Jen
N1 - Copyright:
Copyright 2011 Elsevier B.V., All rights reserved.
PY - 2011
Y1 - 2011
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
T2 - Symposium Series on Computational Intelligence, IEEE SSCI 2011 - 2011 Workshop on Affective Computational Intelligence, WACI 2011
Y2 - 11 April 2011 through 15 April 2011
ER -