Systematic hybrid feature selection using optimal filter classifier pairing and parallel evaluation
Deepak Kumar Rakesh, Shashi Kant Tiwari, Nallakaruppan Kailasanathan, Abhinav Pathak, Aniket S Nagane · 2026
Read Systematic hybrid feature selection using optimal filter classifier pairing and parallel evaluation by Deepak Kumar Rakesh, Shashi Kant Tiwari, Nallakaruppan Kailasanathan, Abhinav Pathak, Aniket S Nagane (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13572466.txt.
Description
Deepak Kumar Rakesh, with four colleagues, presents a 2026 framework for picking the most useful features in a data set before training a model. Feature selection cuts noise and run time, but hybrid methods often pair their parts with no clear reason. The framework aims to make the pairing rule open and testable.
The method joins a filter step, which ranks features by relevance and low overlap, with a classifier step in a paired search. Twelve hybrid pairings were run against classic and recent rivals, and a master-worker layout let the tests run in parallel for speed. The hybrids won on several scores, and a variance test backed the gaps as real. The authors pitch the pairing rule as a guide that does not lock users to one filter or one classifier.
Catalog record
| CREATOR | Deepak Kumar Rakesh, Shashi Kant Tiwari, Nallakaruppan Kailasanathan, Abhinav Pathak, Aniket S Nagane |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 80759 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |