Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.12386/28080
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Antonio D'Isanto | en_US |
dc.contributor.author | CAVUOTI, STEFANO | en_US |
dc.contributor.author | Fabian Gieseke | en_US |
dc.contributor.author | Kai Lars Polsterer | en_US |
dc.date.accessioned | 2020-10-29T12:13:32Z | - |
dc.date.available | 2020-10-29T12:13:32Z | - |
dc.date.issued | 2018 | en_US |
dc.identifier.issn | 0004-6361 | en_US |
dc.identifier.uri | http://hdl.handle.net/20.500.12386/28080 | - |
dc.description.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. | en_US |
dc.language.iso | eng | en_US |
dc.title | Return of the features. Efficient feature selection and interpretation for photometric redshifts | en_US |
dc.type | Article | - |
dc.identifier.doi | 10.1051/0004-6361/201833103 | en_US |
dc.identifier.scopus | 2-s2.0-85050397083 | en_US |
dc.identifier.isi | 000442856200001 | en_US |
dc.identifier.url | https://www.aanda.org/articles/aa/abs/2018/08/aa33103-18/aa33103-18.html | en_US |
dc.relation.medium | STAMPA | en_US |
dc.relation.volume | 616 | en_US |
dc.relation.firstpage | 1 | en_US |
dc.relation.lastpage | 21 | en_US |
dc.relation.numberofpages | 21 | en_US |
dc.relation.article | A97 | en_US |
dc.type.referee | REF_1 | en_US |
dc.description.numberofauthors | 4 | en_US |
dc.description.international | sì | en_US |
dc.contributor.country | ITA | en_US |
dc.contributor.country | DEU | en_US |
dc.relation.scientificsector | FIS/05 - ASTRONOMIA E ASTROFISICA | en_US |
dc.relation.journal | ASTRONOMY & ASTROPHYSICS | en_US |
dc.type.miur | 262 Articolo in rivista | - |
dc.identifier.adsbibcode | 2018A&A...616A..97D | en_US |
dc.relation.ercsector | ERC sectors::Physical Sciences and Engineering::PE9 Universe sciences: astro-physics/chemistry/biology; solar systems; stellar, galactic and extragalactic astronomy, planetary systems, cosmology, space science, instrumentation::PE9_6 Stars and stellar systems | en_US |
dc.description.apc | no | en_US |
dc.description.oa | 1 – prodotto con file in versione Open Access (allegare il file al passo 5-Carica) | en_US |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.openairetype | Article | - |
item.languageiso639-1 | en | - |
item.cerifentitytype | Publications | - |
item.grantfulltext | open | - |
item.fulltext | With Fulltext | - |
crisitem.author.dept | O.A. Capodimonte | - |
crisitem.author.orcid | 0000-0002-3787-4196 | - |
crisitem.journal.journalissn | 0004-6361 | - |
crisitem.journal.ance | E016240 | - |
Appears in Collections: | 1.01 Articoli in rivista |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
aa33103-18.pdf | PDF editoriale | 6.01 MB | Adobe PDF | View/Open |
Page view(s)
32
checked on Mar 29, 2024
Download(s)
68
checked on Mar 29, 2024
Google ScholarTM
Check
Altmetric
Altmetric
Items in DSpace are published in Open Access, unless otherwise indicated.