Compact target-aware stability-based feature selection for cross-dataset wearable activity monitoring

Sarra Ayouni, Maha Sliti, Abeer Abdulaziz Alghanem, Fatimah Alhayan, Mohamed Maddeh · 2026

Read Compact target-aware stability-based feature selection for cross-dataset wearable activity monitoring by Sarra Ayouni, Maha Sliti, Abeer Abdulaziz Alghanem, Fatimah Alhayan, Mohamed Maddeh (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/plos-pone-0359300.txt.

Description

Sarra Ayouni, Maha Sliti, Abeer Alghanem, Fatimah Alhayan, and Mohamed Maddeh published this research article in PLOS ONE in 2026. It works on wearable activity monitoring, where wrist or body sensors record movement. The authors present a feature selection method, a way to choose which sensor signals matter, that is compact, target-aware, and stability-based.

The test is cross-dataset: a method tuned on one group of wearers must still work on another. Choosing fewer, steadier features can make activity recognition cheaper and more reliable on real devices. Engineers building fitness trackers and health monitors are the audience for selection methods that survive a change of dataset.

Catalog record

CREATORSarra Ayouni, Maha Sliti, Abeer Abdulaziz Alghanem, Fatimah Alhayan, Mohamed Maddeh
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE124249
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0359300

Browse the full library · About the Tower of Babel