Title
Analysis of galvanic skin responses with principal components and clustering techniques
Abstract
An advanced method for analyzing the pattern- ing of successive galvanic skin responses (GSR) is presented. The proposed method is based on principal component anal- ysis (PCA) in which the vector containing the measured signal is presented as a weighted sum of orthogonal basis vectors. The method is tested using measurements from 20 healthy controls and 13 psychotic patients. For each subject 11 surprising auditory stimuli were delivered to right ear at irregular intervals and evoked GSRs were recorded from the hand. For most of the healthy controls there was a clear pat- tern in successive GSRs, whereas within psychotic patients the lack of time-locking of GSRs seemed to be characteristi- cal. These between group dierences can be revealed by the proposed method. With application to clustering a signi- cant discrimination, with overall correct ratings of 82%, of healthy controls and psychotic patients is achieved. A sig- nican t fact is that all patients were ranked correctly giving the proposed method a sensitivity of 100%.
Year
DOI
Venue
2001
10.1109/10.951509
IEEE Trans. Biomed. Engineering
Keywords
Field
DocType
galvanic skin response, hierarchical clustering, principal component analysis
Computer vision,Auditory stimuli,Pattern clustering,Psychology,Speech recognition,Artificial intelligence,Audiology,Cluster analysis,Principal component analysis,Skin conductance
Journal
Volume
Issue
ISSN
48
10
0018-9294
Citations 
PageRank 
References 
10
4.93
0
Authors
5
Name
Order
Citations
PageRank
Mika P. Tarvainen128952.33
Anu S. Koistinen2196.46
Minna Valkonen-Korhonen3104.93
Juhani Partanen4196.46
Pasi A. Karjalainen535461.15