Skip navigation
  • INAF logo
  • Home
  • Communities
    & Collections
  • Research outputs
  • Researchers
  • Organization units
  • Projects
  • Explore by
    • Research outputs
    • Researchers
    • Organization units
    • Projects
  • Login:
    • My DSpace
    • Receive email
      updates
    • Edit Account details
  • Italian
  • English

  1. OA@INAF
  2. PRODOTTI RICERCA INAF
  3. 1 CONTRIBUTI IN RIVISTE (Journal articles)
  4. 1.01 Articoli in rivista
Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.12386/28080
Title: Return of the features. Efficient feature selection and interpretation for photometric redshifts
Authors: Antonio D'Isanto
CAVUOTI, STEFANO 
Fabian Gieseke
Kai Lars Polsterer
Issue Date: 2018
Journal: ASTRONOMY & ASTROPHYSICS 
Number: 616
First Page: 1
Abstract: The explosion of data in recent years has generated an increasing need for new analysis techniques in order to extract knowledge from massive datasets. Machine learning has proved particularly useful to perform this task. Fully automatized methods have recently gathered great popularity, even though those methods often lack physical interpretability. In contrast, feature based approaches can provide both well-performing models and understandable causalities with respect to the correlations found between features and physical processes. Efficient feature selection is an essential tool to boost the performance of machine learning models. In this work, we propose a forward selection method in order to compute, evaluate, and characterize better performing features for regression and classification problems. Given the importance of photometric redshift estimation, we adopt it as our case study. We synthetically created 4,520 features by combining magnitudes, errors, radii, and ellipticities of quasars, taken from the SDSS. We apply a forward selection process, a recursive method in which a huge number of feature sets is tested through a kNN algorithm, leading to a tree of feature sets. The branches of the tree are then used to perform experiments with the random forest, in order to validate the best set with an alternative model. We demonstrate that the sets of features determined with our approach improve the performances of the regression models significantly when compared to the performance of the classic features from the literature. The found features are unexpected and surprising, being very different from the classic features. Therefore, a method to interpret some of the found features in a physical context is presented. The methodology described here is very general and can be used to improve the performance of machine learning models for any regression or classification task.
URI: http://hdl.handle.net/20.500.12386/28080
URL: https://www.aanda.org/articles/aa/abs/2018/08/aa33103-18/aa33103-18.html
ISSN: 0004-6361
DOI: 10.1051/0004-6361/201833103
Bibcode ADS: 2018A&A...616A..97D
Fulltext: open
Appears in Collections:1.01 Articoli in rivista

Files in This Item:
File Description SizeFormat 
aa33103-18.pdfPDF editoriale6.01 MBAdobe PDFView/Open
Show full item record

Page view(s)

7
checked on Jan 19, 2021

Download(s)

7
checked on Jan 19, 2021

Google ScholarTM

Check

Altmetric


Items in DSpace are published in Open Access, unless otherwise indicated.


Explore by
  • Communities
    & Collections
  • Research outputs
  • Researchers
  • Organization units
  • Projects

Informazioni e guide per autori

https://openaccess-info.inaf.it: tutte le informazioni sull'accesso aperto in INAF

Come si inserisce un prodotto: le guide a OA@INAF

La Policy INAF sull'accesso aperto

Documenti e modelli scaricabili

Feedback
Built with DSpace-CRIS - Extension maintained and optimized by Logo 4SCIENCE