Feature space reduction method for ultrahigh-dimensional, multiclass data: random forest-based multiround screening (RFMS)
In recent years, several screening methods have been published for ultrahigh-dimensional data that contain hundreds of thousands of features, many of which are irrelevant or redundant. However, most of these methods cannot handle data with thousands of classes. Prediction models built to authenticat...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2023-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ad020e |
| _version_ | 1797656006448119808 |
|---|---|
| author | Gergely Hanczár Marcell Stippinger Dávid Hanák Marcell T Kurbucz Olivér M Törteli Ágnes Chripkó Zoltán Somogyvári |
| author_facet | Gergely Hanczár Marcell Stippinger Dávid Hanák Marcell T Kurbucz Olivér M Törteli Ágnes Chripkó Zoltán Somogyvári |
| author_sort | Gergely Hanczár |
| collection | DOAJ |
| description | In recent years, several screening methods have been published for ultrahigh-dimensional data that contain hundreds of thousands of features, many of which are irrelevant or redundant. However, most of these methods cannot handle data with thousands of classes. Prediction models built to authenticate users based on multichannel biometric data result in this type of problem. In this study, we present a novel method known as random forest-based multiround screening (RFMS) that can be effectively applied under such circumstances. The proposed algorithm divides the feature space into small subsets and executes a series of partial model builds. These partial models are used to implement tournament-based sorting and the selection of features based on their importance. This algorithm successfully filters irrelevant features and also discovers binary and higher-order feature interactions. To benchmark RFMS, a synthetic biometric feature space generator known as BiometricBlender is employed. Based on the results, the RFMS is on par with industry-standard feature screening methods, while simultaneously possessing many advantages over them. |
| first_indexed | 2024-03-11T17:22:55Z |
| format | Article |
| id | doaj.art-b9e76c4766c04692a96738a53f464413 |
| institution | Directory Open Access Journal |
| issn | 2632-2153 |
| language | English |
| last_indexed | 2024-03-11T17:22:55Z |
| publishDate | 2023-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj.art-b9e76c4766c04692a96738a53f4644132023-10-19T09:24:08ZengIOP PublishingMachine Learning: Science and Technology2632-21532023-01-014404501210.1088/2632-2153/ad020eFeature space reduction method for ultrahigh-dimensional, multiclass data: random forest-based multiround screening (RFMS)Gergely Hanczár0https://orcid.org/0000-0002-0222-1400Marcell Stippinger1https://orcid.org/0000-0002-9954-8089Dávid Hanák2https://orcid.org/0000-0003-0678-9885Marcell T Kurbucz3https://orcid.org/0000-0002-0121-6781Olivér M Törteli4https://orcid.org/0000-0002-2148-9189Ágnes Chripkó5https://orcid.org/0000-0002-2863-5257Zoltán Somogyvári6https://orcid.org/0000-0002-4385-3025Cursor Insight Ltd , 20-22 Wenlock Road, N17GU London, United KingdomDepartment of Computational Sciences, Wigner Research Centre for Physics , 29-33 Konkoly Thege Miklós Street, H-1121 Budapest, HungaryCursor Insight Ltd , 20-22 Wenlock Road, N17GU London, United KingdomDepartment of Computational Sciences, Wigner Research Centre for Physics , 29-33 Konkoly Thege Miklós Street, H-1121 Budapest, Hungary; Institute of Data Analytics and Information Systems, Corvinus University of Budapest , 8 Fővám Square, H-1093 Budapest, HungaryCursor Insight Ltd , 20-22 Wenlock Road, N17GU London, United KingdomCursor Insight Ltd , 20-22 Wenlock Road, N17GU London, United KingdomDepartment of Computational Sciences, Wigner Research Centre for Physics , 29-33 Konkoly Thege Miklós Street, H-1121 Budapest, HungaryIn recent years, several screening methods have been published for ultrahigh-dimensional data that contain hundreds of thousands of features, many of which are irrelevant or redundant. However, most of these methods cannot handle data with thousands of classes. Prediction models built to authenticate users based on multichannel biometric data result in this type of problem. In this study, we present a novel method known as random forest-based multiround screening (RFMS) that can be effectively applied under such circumstances. The proposed algorithm divides the feature space into small subsets and executes a series of partial model builds. These partial models are used to implement tournament-based sorting and the selection of features based on their importance. This algorithm successfully filters irrelevant features and also discovers binary and higher-order feature interactions. To benchmark RFMS, a synthetic biometric feature space generator known as BiometricBlender is employed. Based on the results, the RFMS is on par with industry-standard feature screening methods, while simultaneously possessing many advantages over them.https://doi.org/10.1088/2632-2153/ad020efeature screeningultrahigh dimensionalitymulticlass classificationrandom forestbiometrics |
| spellingShingle | Gergely Hanczár Marcell Stippinger Dávid Hanák Marcell T Kurbucz Olivér M Törteli Ágnes Chripkó Zoltán Somogyvári Feature space reduction method for ultrahigh-dimensional, multiclass data: random forest-based multiround screening (RFMS) Machine Learning: Science and Technology feature screening ultrahigh dimensionality multiclass classification random forest biometrics |
| title | Feature space reduction method for ultrahigh-dimensional, multiclass data: random forest-based multiround screening (RFMS) |
| title_full | Feature space reduction method for ultrahigh-dimensional, multiclass data: random forest-based multiround screening (RFMS) |
| title_fullStr | Feature space reduction method for ultrahigh-dimensional, multiclass data: random forest-based multiround screening (RFMS) |
| title_full_unstemmed | Feature space reduction method for ultrahigh-dimensional, multiclass data: random forest-based multiround screening (RFMS) |
| title_short | Feature space reduction method for ultrahigh-dimensional, multiclass data: random forest-based multiround screening (RFMS) |
| title_sort | feature space reduction method for ultrahigh dimensional multiclass data random forest based multiround screening rfms |
| topic | feature screening ultrahigh dimensionality multiclass classification random forest biometrics |
| url | https://doi.org/10.1088/2632-2153/ad020e |
| work_keys_str_mv | AT gergelyhanczar featurespacereductionmethodforultrahighdimensionalmulticlassdatarandomforestbasedmultiroundscreeningrfms AT marcellstippinger featurespacereductionmethodforultrahighdimensionalmulticlassdatarandomforestbasedmultiroundscreeningrfms AT davidhanak featurespacereductionmethodforultrahighdimensionalmulticlassdatarandomforestbasedmultiroundscreeningrfms AT marcelltkurbucz featurespacereductionmethodforultrahighdimensionalmulticlassdatarandomforestbasedmultiroundscreeningrfms AT olivermtorteli featurespacereductionmethodforultrahighdimensionalmulticlassdatarandomforestbasedmultiroundscreeningrfms AT agneschripko featurespacereductionmethodforultrahighdimensionalmulticlassdatarandomforestbasedmultiroundscreeningrfms AT zoltansomogyvari featurespacereductionmethodforultrahighdimensionalmulticlassdatarandomforestbasedmultiroundscreeningrfms |