| |
 |
| Paper: |
ALLStars: Overcoming Multi-Survey Selection Bias using Crowd-Sourced Active Learning |
| Volume: |
461, Astronomical Data Analysis Software and Systems XXI |
| Page: |
581 |
| Authors: |
Starr, D. L.; Richards, J. W.; Brink, H.; Miller, A. A.; Bloom, J. S.; Butler, N. R.; James, J. B.; Long, J. P. |
| Abstract: |
Developing a multi-survey time-series classifier presents several
challenges. One problem is overcoming the sample selection bias which arises
when the instruments or observing cadences differ between the training and
testing datasets. In this case, the probabilistic distributions characterizing
the sources in the training survey dataset differ from the source distributions
in the other survey, resulting in poor results when a classifier is naively
applied. To resolve this, we have developed the ALLStars active learning
framework which allows us to bootstrap a classifier onto a new survey using a
small set of optimally chosen sources which are then presented to users for
manual classification. Several iterations of this crowd-sourcing process results
in a significantly improved classifier. Using this procedure, we have built a
variable star light-curve classifier using OGLE, Hipparcos, and ASAS survey
data. |
|
|
|
|
|
