Core Concepts
CODA proposes a cost-efficient domain adaptation mechanism for mobile sensing, ensuring robust adaptation to uncertain conditions.
Abstract
The paper introduces CODA, a domain adaptation mechanism for mobile sensing.
Existing solutions struggle with real-time drifts in human-centric sensing scenarios.
CODA addresses these challenges through active learning and clustering loss.
The framework is evaluated across diverse datasets, showcasing its potential for online adaptation.
Baseline comparisons and system implementation details are provided.
Stats
"In recent years, emerging research on mobile sensing has led to novel scenarios that enhance daily life for humans."
"Through meticulous evaluations across diverse datasets, including phone-based, watch-based, and integrated sensor-based sensing tasks..."
"The promising results achieved by CODA, even without learnable parameters..."