J
Juha Reunanen
Researcher at ABB Ltd
Publications - 12
Citations - 609
Juha Reunanen is an academic researcher from ABB Ltd. The author has contributed to research in topics: Feature selection & Overfitting. The author has an hindex of 7, co-authored 12 publications receiving 579 citations.
Papers
More filters
Journal Article
Overfitting in making comparisons between variable selection methods
TL;DR: This paper addresses a common methodological flaw in the comparison of variable selection methods by addressing the problem of cross-validation performance estimates of the different variable subsets used with computationally intensive search algorithms.
Proceedings Article
A Pitfall in Determining the Optimal Feature Subset Size
TL;DR: The present study shows that a feature subset can be found that is smaller but still enables building a more accurate classifier than the full set of all the candidate features, but this peak may often be just an artifact due to the still too common mistake in pattern recognition.
Journal ArticleDOI
Retrieval of aerosol optical depth from surface solar radiation measurementsusing machine learning algorithms, non-linear regression and a radiativetransfer-based look-up table
J. Huttunen,J. Huttunen,Harri Kokkola,Tero Mielonen,Mika E. Mononen,Antti Lipponen,Antti Lipponen,Juha Reunanen,Anders V. Lindfors,Santtu Mikkonen,Kari E. J. Lehtinen,Kari E. J. Lehtinen,Natalia Kouremeti,Alkiviadis F. Bais,Harri Niska,Antti Arola +15 more
TL;DR: This study indicates that machine learning methods benefit from the fact that they do not constrain the aerosol SSA in the retrieval, whereas the LUT method assumes a constant value for it.
Proceedings ArticleDOI
Model Selection and Assessment Using Cross-indexing
TL;DR: A generalization is introduced that covers the previously presented variations of cross-indexing A and B as special cases and reports the promising results of using the consequent method in three open competitions.
Patent
Method and apparatus for identifying repeated patterns
Juha Reunanen,Antti Saarela +1 more
TL;DR: In this paper, repeated patterns are identified in a strip-like product, and a search image is created of any detected anomaly and its neighbourhood, and the image is used to convolute the image signal being examined, creating a response image signal.