Benchmarking Encoders and Self-Supervised Learning for Smartphone-Based Human Activity Recognition

Smartphone-based Human Activity Recognition (HAR) typically relies on deep learning models. However, performance varies with encoder architecture and the availability of labeled data. To address label scarcity, Self-Supervised Learning (SSL) exploits unlabeled data. However, existing benchmarks eval...

תיאור מלא

מידע ביבליוגרפי

Principais autores:	Gustavo P. C. P. Da Luz, Darlinne H. P. Soto, Otavio O. Napoli, Anderson Rocha, Levy Boccato, Edson Borin
פורמט:	Artigo
שפה:	Inglês
יצא לאור:	IEEE 2026-01-01
סדרה:	IEEE Access
נושאים:	Deep learning human activity recognition (HAR) representation learning self-supervised learning (SSL)
גישה מקוונת:	https://ieeexplore.ieee.org/document/11417778/
תגים:	הוספת תג אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!