Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313482655> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4313482655 endingPage "960" @default.
- W4313482655 startingPage "955" @default.
- W4313482655 abstract "We consider a network of controlled sensors that monitor the unknown health state of a patient. We assume that the health state process is a Markov chain with a transition matrix that is unknown to the controller. At each timestep, the controller chooses a subset of sensors to activate, which incurs an energy (i.e., battery) cost. Activating more sensors improves the estimation of the unknown state, which introduces an energy-accuracy tradeoff. Our goal is to minimize the combined energy and state misclassification costs over time. Activating sensors now also provides measurements that can be used to learn the model, improving future decisions. Therefore, the learning aspect is intertwined with the energy-accuracy tradeoff. While Reinforcement Learning (RL) is often used when the model is unknown, it cannot be directly applied in health monitoring since the controller does not know the (health) state. Therefore, the monitoring problem is a partially observable Markov decision process (POMDP) where the cost feedback is also only partially available since the misclassification cost is unknown. To overcome this difficulty, we propose a monitoring algorithm that combines RL for POMDPs and online estimation of the expected misclassification cost based on a Hidden Markov Model (HMM). We show empirically that our algorithm achieves comparable performance with a monitoring system that assumes a known transition matrix and quantizes the belief state. It also outperforms the model-based approach where the estimated transition matrix is used for value iteration. Thus, our algorithm can be useful in designing energy-efficient and personalized health monitoring systems." @default.
- W4313482655 created "2023-01-06" @default.
- W4313482655 creator A5002056995 @default.
- W4313482655 creator A5020882454 @default.
- W4313482655 creator A5021334659 @default.
- W4313482655 creator A5032978198 @default.
- W4313482655 creator A5049973502 @default.
- W4313482655 date "2023-01-01" @default.
- W4313482655 modified "2023-09-26" @default.
- W4313482655 title "Personalized and Energy-Efficient Health Monitoring: A Reinforcement Learning Approach" @default.
- W4313482655 cites W1501207501 @default.
- W4313482655 cites W1570690983 @default.
- W4313482655 cites W1580557482 @default.
- W4313482655 cites W1994320166 @default.
- W4313482655 cites W2101786389 @default.
- W4313482655 cites W2167671703 @default.
- W4313482655 cites W2887137393 @default.
- W4313482655 cites W2911758520 @default.
- W4313482655 cites W2957666658 @default.
- W4313482655 cites W2963335520 @default.
- W4313482655 cites W2972732693 @default.
- W4313482655 cites W3095708005 @default.
- W4313482655 cites W3155980049 @default.
- W4313482655 cites W3183431726 @default.
- W4313482655 doi "https://doi.org/10.1109/lcsys.2022.3229074" @default.
- W4313482655 hasPublicationYear "2023" @default.
- W4313482655 type Work @default.
- W4313482655 citedByCount "0" @default.
- W4313482655 crossrefType "journal-article" @default.
- W4313482655 hasAuthorship W4313482655A5002056995 @default.
- W4313482655 hasAuthorship W4313482655A5020882454 @default.
- W4313482655 hasAuthorship W4313482655A5021334659 @default.
- W4313482655 hasAuthorship W4313482655A5032978198 @default.
- W4313482655 hasAuthorship W4313482655A5049973502 @default.
- W4313482655 hasConcept C105795698 @default.
- W4313482655 hasConcept C106189395 @default.
- W4313482655 hasConcept C111919701 @default.
- W4313482655 hasConcept C11413529 @default.
- W4313482655 hasConcept C119857082 @default.
- W4313482655 hasConcept C124101348 @default.
- W4313482655 hasConcept C154945302 @default.
- W4313482655 hasConcept C159886148 @default.
- W4313482655 hasConcept C163836022 @default.
- W4313482655 hasConcept C17098449 @default.
- W4313482655 hasConcept C186370098 @default.
- W4313482655 hasConcept C203479927 @default.
- W4313482655 hasConcept C23224414 @default.
- W4313482655 hasConcept C33923547 @default.
- W4313482655 hasConcept C41008148 @default.
- W4313482655 hasConcept C48103436 @default.
- W4313482655 hasConcept C6557445 @default.
- W4313482655 hasConcept C86803240 @default.
- W4313482655 hasConcept C97541855 @default.
- W4313482655 hasConcept C98045186 @default.
- W4313482655 hasConcept C98763669 @default.
- W4313482655 hasConceptScore W4313482655C105795698 @default.
- W4313482655 hasConceptScore W4313482655C106189395 @default.
- W4313482655 hasConceptScore W4313482655C111919701 @default.
- W4313482655 hasConceptScore W4313482655C11413529 @default.
- W4313482655 hasConceptScore W4313482655C119857082 @default.
- W4313482655 hasConceptScore W4313482655C124101348 @default.
- W4313482655 hasConceptScore W4313482655C154945302 @default.
- W4313482655 hasConceptScore W4313482655C159886148 @default.
- W4313482655 hasConceptScore W4313482655C163836022 @default.
- W4313482655 hasConceptScore W4313482655C17098449 @default.
- W4313482655 hasConceptScore W4313482655C186370098 @default.
- W4313482655 hasConceptScore W4313482655C203479927 @default.
- W4313482655 hasConceptScore W4313482655C23224414 @default.
- W4313482655 hasConceptScore W4313482655C33923547 @default.
- W4313482655 hasConceptScore W4313482655C41008148 @default.
- W4313482655 hasConceptScore W4313482655C48103436 @default.
- W4313482655 hasConceptScore W4313482655C6557445 @default.
- W4313482655 hasConceptScore W4313482655C86803240 @default.
- W4313482655 hasConceptScore W4313482655C97541855 @default.
- W4313482655 hasConceptScore W4313482655C98045186 @default.
- W4313482655 hasConceptScore W4313482655C98763669 @default.
- W4313482655 hasFunder F4320306406 @default.
- W4313482655 hasLocation W43134826551 @default.
- W4313482655 hasOpenAccess W4313482655 @default.
- W4313482655 hasPrimaryLocation W43134826551 @default.
- W4313482655 hasRelatedWork W1515117609 @default.
- W4313482655 hasRelatedWork W1551379884 @default.
- W4313482655 hasRelatedWork W2005003293 @default.
- W4313482655 hasRelatedWork W2026691440 @default.
- W4313482655 hasRelatedWork W2095807485 @default.
- W4313482655 hasRelatedWork W2146763310 @default.
- W4313482655 hasRelatedWork W2156371714 @default.
- W4313482655 hasRelatedWork W2356987663 @default.
- W4313482655 hasRelatedWork W4285429136 @default.
- W4313482655 hasRelatedWork W2096496337 @default.
- W4313482655 hasVolume "7" @default.
- W4313482655 isParatext "false" @default.
- W4313482655 isRetracted "false" @default.
- W4313482655 workType "article" @default.