Decision tree ensembles in biomedical time-series classifaction

1
Decision tree ensembles in biomedical time-series
classifaction
Alan Jovic1, Karla Brkic1, Nikola Bogunovic1
1 University of Zagreb, Faculty of Electrical
Engineering and Computing, Unska 3, 10000 Zagreb,
Croatia, E-mail alan.jovic, karla.brkic,
nikola.bogunovic_at_fer.hr
Transformations and feature extraction
Biomedical time-series datasets
Biomedical time-series
Transformations
Characteristics
Fourier transform Hilbert transform Wavelet
transform
Binary class or multiclass From several features
to several hundred features Feature vectors
numbers vary Very few open, referential datasets
available
Biomedical time-series prepared datasets
Features
Morphological Statistical Frequency Time-frequency
Nonlinear Personal data
Difficult results comparison
Different data Different disorders Different
classifiers
Goal Demonstrate the potential of decision tree
ensembles in biomedical time series
classification, compare to SVM still
preliminary results
Three datasets
Seven classifiers
Classification results
Arrhythmia dataset (UCI repository) - 13
classes, 279 features, 452 instances
AdaBoostC4.5 (AB) MultiBoostC4.5 (MB) Random
forest (RF) Rotation forest (RTF) SVM SMO-based
- Linear - Squared polynomial - Radial
HRV-based arrhythmia (PhysioNet, two databases)
(HRV) - 9 classes, 230 features, 8843 instances
HRV-based heart disorder (PhysioNet, six
databases) (CHF) - 3 classes (normal,
arrhytmic, CHF), 237 features, 3317 instances
Statistically significant win/loss/tie, a0.05,
Students paired t-test for 9x10-fold
crossvalidation (first 10-fold iteration used for
finding optimal model parameters)
Conclusion
Preliminary results strongly support the use of
decision tree ensembles to improve model accuracy
in biomedical time-series classification, especial
ly AdaBoostC4.5 and MultiBoostC4.5. Further
investigations are necessary.
Average classification model construction times
(in seconds) for the three datasets