A two-stage machine learning pipeline (logistic regression pre-filter plus CNN on vibration spectrograms) can separate crash-test-dummy falls from other bed vibrations in the lab, with precision around 65% at forced perfect recall.
, et al., year 2012
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bed-Attached Vibration Sensor System: A Machine Learning Approach for Fall Detection in Nursing Homes
A two-stage machine learning pipeline (logistic regression pre-filter plus CNN on vibration spectrograms) can separate crash-test-dummy falls from other bed vibrations in the lab, with precision around 65% at forced perfect recall.