An RL agent on a wearable selects low- or high-power features online; extending the Advise algorithm to multiple, reliability-estimated feedback sources improves the power/accuracy trade-off on the SPHERE dataset.
This is evidenced by the vast amount of studies undertaken utiliz- ing accelerometers [2, 3], perhaps the most commonly used device for detecting ADL
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Online Feature Selection for Activity Recognition using Reinforcement Learning with Multiple Feedback
An RL agent on a wearable selects low- or high-power features online; extending the Advise algorithm to multiple, reliability-estimated feedback sources improves the power/accuracy trade-off on the SPHERE dataset.