Learning Sensor Sample-Reweighting for Dynamic Early-Exit Activity Recognition Via Meta Learning
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Journal of Biomedical and Health Informatics"
DOI: 10.1109/jbhi.2024.3524252
Abstract: During recent years, dynamic early-exit has provided a promising paradigm to improve the computational efficiency of deep neural networks by constructing multiple classifiers to let easy samples exit at shallow layers while avoiding redundant computations… read more here.
Keywords: exit; early exit; activity samples; dynamic early ... See more keywords
A dynamic early-warning method for bridge structural safety based on data reconstruction and depth prediction
Sign Up to like & getrecommendations! Published in 2025 at "PLOS One"
DOI: 10.1371/journal.pone.0324816
Abstract: The structural response of bridges involves a complex interplay of various coupled effects, rendering the identification of long-term variation trends inherently challenging. Consequently, effectively detecting and alerting abnormal monitoring data for bridge structures under complex… read more here.
Keywords: bridge; prediction; early warning; dynamic early ... See more keywords