TY  - CONF
ID  - Setz_Using_Ensemble_Classifier_Systems_for_Handling_Missing_Data_in_Emotion_Recognition_from_Physiology_One_Step_Towards_a_Practical_System_2009
T1  - Using Ensemble Classifier Systems for Handling Missing Data in Emotion Recognition from Physiology: One Step Towards a Practical System
A1  - Setz, Cornelia
A1  - Schumm, Johannes
A1  - Lorenz, Claudia
A1  - Arnrich, Bert
A1  - Tröster, Gerhard
TI  - Proceedings of the 2009 3rd International Conference on Affective Computing and Intelligent Interaction, ACII
Y1  - 2009
SP  - 187
EP  - 194
UR  - http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=5349590&isnumber=5349257
M2  - doi: 10.1109/ACII.2009.5349590
KW  - arnrich_physio
KW  - SEAT
N2  - Previous work on emotion recognition from physiology
has not addressed the problem of missing data. However,
data loss due to artifacts is a frequent phenomenon in practical
applications. Discarding the whole data instance if
only a part is corrupted results in a substantial loss of data.
To address this problem, two methods for handling missing
data (imputation and reduced-feature models) in combination
with two classifier fusion approaches (majority and
confidence voting) are investigated in this work. The five
emotions amusement, anger, contentment, neutral and sadness
were elicited in 20 subjects by film clips while six physiological
signals (ECG, EMG, EOG, EDA, respiration and
finger temperature) were recorded. Results show that classifier
fusion significantly increases the recognition accuracy
in comparison to single classifiers by up to 16.3%. Regarding
the methods for handling missing data, reduced-feature
models are competitive or even slightly better than models
which employ imputation. This is beneficial for practical
applications where computational complexity is critical.
ER  -