TY - JOUR
T1 - Implementation of and experimental software for active selection of classification features[Formula presented]
AU - Kok, Thomas T.
AU - Krempl, Georg
AU - Schnack, Hugo G.
N1 - Funding Information:
We thank Rachel M. Brouwer, Rene M. Mandl, Hilleke E. Hulshoff Pol and Wiepke Cahn from UMCU Brain Center, and Ad Feelders from Utrecht University. Furthermore, we thank the SIG Applied Data Science at UU/UMCU for funding the research project “Using active learning to reduce the costs of population-based neuroimaging studies”.
Publisher Copyright:
© 2021 The Authors
PY - 2021/8
Y1 - 2021/8
N2 - In some machine learning applications, obtaining data on the most predictive features is costly, but other features are readily available. Recently, first active learning approaches for this Actively Selecting Classification Features problem (ASCF) have been proposed. In this paper, we introduce a Python package that provides a framework for ASCF, including implementations of a supervised and an unsupervised selection approach, as well as a framework for performing experimental evaluations. This framework has been used in recent publications in the context of neuroimaging research on mental disorders, where its usefulness has been demonstrated in a simulated study design with MRI data.
AB - In some machine learning applications, obtaining data on the most predictive features is costly, but other features are readily available. Recently, first active learning approaches for this Actively Selecting Classification Features problem (ASCF) have been proposed. In this paper, we introduce a Python package that provides a framework for ASCF, including implementations of a supervised and an unsupervised selection approach, as well as a framework for performing experimental evaluations. This framework has been used in recent publications in the context of neuroimaging research on mental disorders, where its usefulness has been demonstrated in a simulated study design with MRI data.
KW - Active feature acquisition
KW - Active learning
KW - Active selection of classification features
KW - Machine learning experiment evaluation framework
UR - http://www.scopus.com/inward/record.url?scp=85115876496&partnerID=8YFLogxK
U2 - 10.1016/j.simpa.2021.100103
DO - 10.1016/j.simpa.2021.100103
M3 - Article
AN - SCOPUS:85115876496
VL - 9
JO - Software Impacts
JF - Software Impacts
M1 - 100103
ER -