TY  - CONF
ID  - Setz_Combining_Worthless_Sensor_Data_2009
T1  - Combining Worthless Sensor Data
A1  - Setz, Cornelia
A1  - Schumm, Johannes
A1  - Lorenz, Claudia
A1  - Arnrich, Bert
A1  - Tröster, Gerhard
TI  - Measuring Mobile Emotions Workshop at MobileHCI
Y1  - 2009
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 mobile
applications. Discarding the whole data instance if only a part is
corrupted results in a substantial loss of data. To address this
problem, we investigated two methods for handling missing data:
imputation and reduced-feature models using ensemble classifier
systems. 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 increases the recognition accuracy in
comparison to single classifiers using imputation by up to 16.3%.
We were able to analyze 100% of the data even though only 47%
of the data was artifact free. Since more artifacts are expected in a
mobile environment than in the laboratory, the proposed methods
are especially beneficial for mobile settings.
ER  -