FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384202802> ?p ?o ?g. }

• W4384202802 endingPage "3054" @default.
• W4384202802 startingPage "3054" @default.
• W4384202802 abstract "Smart homes, powered mostly by Internet of Things (IoT) devices, have become very popular nowadays due to their ability to provide a holistic approach towards effective energy management. This is made feasible via the deployment of multiple sensors, which enables predicting energy consumption via machine learning approaches. In this work, we propose FedTime, a novel federated learning approach for predicting smart home consumption which takes into consideration the age of the time series datasets of each client. The proposed method is based on federated averaging but aggregates local models trained on each smart home device to produce a global prediction model via a novel weighting scheme. Each local model contributes more to the global model when the local data are more recent, or penalized when the data are older upon testing for a specific residence (client). The approach was evaluated on a real-world dataset of smart home energy consumption and compared with other machine learning models. The results demonstrate that the proposed method performs similarly or better than other models in terms of prediction error; FedTime achieved a lower mean absolute error of 0.25 compared to FedAvg. The contributions of this work present a novel federated learning approach that takes into consideration the age of the datasets that belong to the clients, experimenting with a publicly available dataset on grid import consumption prediction, while comparing with centralized and decentralized baselines, without the need for data centralization, which is a privacy concern for many households." @default.
• W4384202802 created "2023-07-14" @default.
• W4384202802 creator A5008414543 @default.
• W4384202802 creator A5015078439 @default.
• W4384202802 creator A5039352682 @default.
• W4384202802 creator A5065352009 @default.
• W4384202802 date "2023-07-12" @default.
• W4384202802 modified "2023-10-18" @default.
• W4384202802 title "Data Aging Matters: Federated Learning-Based Consumption Prediction in Smart Homes via Age-Based Model Weighting" @default.
• W4384202802 cites W2000164913 @default.
• W4384202802 cites W2037823489 @default.
• W4384202802 cites W2051607409 @default.
• W4384202802 cites W2064675550 @default.
• W4384202802 cites W2529556398 @default.
• W4384202802 cites W2752957596 @default.
• W4384202802 cites W2783596173 @default.
• W4384202802 cites W2974306260 @default.
• W4384202802 cites W3097627214 @default.
• W4384202802 cites W3105324058 @default.
• W4384202802 cites W3135032840 @default.
• W4384202802 cites W3156459836 @default.
• W4384202802 cites W3168256142 @default.
• W4384202802 cites W3170790803 @default.
• W4384202802 cites W3194504440 @default.
• W4384202802 cites W3200113042 @default.
• W4384202802 cites W3211972736 @default.
• W4384202802 cites W4205543433 @default.
• W4384202802 cites W4225161501 @default.
• W4384202802 cites W4282016372 @default.
• W4384202802 cites W4284970908 @default.
• W4384202802 cites W4294106961 @default.
• W4384202802 cites W4308448180 @default.
• W4384202802 cites W4309548074 @default.
• W4384202802 cites W4310613916 @default.
• W4384202802 cites W4312231739 @default.
• W4384202802 cites W4321610224 @default.
• W4384202802 cites W4322731240 @default.
• W4384202802 doi "https://doi.org/10.3390/electronics12143054" @default.
• W4384202802 hasPublicationYear "2023" @default.
• W4384202802 type Work @default.
• W4384202802 citedByCount "0" @default.
• W4384202802 crossrefType "journal-article" @default.
• W4384202802 hasAuthorship W4384202802A5008414543 @default.
• W4384202802 hasAuthorship W4384202802A5015078439 @default.
• W4384202802 hasAuthorship W4384202802A5039352682 @default.
• W4384202802 hasAuthorship W4384202802A5065352009 @default.
• W4384202802 hasBestOaLocation W43842028021 @default.
• W4384202802 hasConcept C105339364 @default.
• W4384202802 hasConcept C10558101 @default.
• W4384202802 hasConcept C111919701 @default.
• W4384202802 hasConcept C119599485 @default.
• W4384202802 hasConcept C119857082 @default.
• W4384202802 hasConcept C124101348 @default.
• W4384202802 hasConcept C126838900 @default.
• W4384202802 hasConcept C127413603 @default.
• W4384202802 hasConcept C144024400 @default.
• W4384202802 hasConcept C154945302 @default.
• W4384202802 hasConcept C183115368 @default.
• W4384202802 hasConcept C18762648 @default.
• W4384202802 hasConcept C2780165032 @default.
• W4384202802 hasConcept C30772137 @default.
• W4384202802 hasConcept C36289849 @default.
• W4384202802 hasConcept C41008148 @default.
• W4384202802 hasConcept C45804977 @default.
• W4384202802 hasConcept C507571656 @default.
• W4384202802 hasConcept C71924100 @default.
• W4384202802 hasConcept C76155785 @default.
• W4384202802 hasConcept C78519656 @default.
• W4384202802 hasConceptScore W4384202802C105339364 @default.
• W4384202802 hasConceptScore W4384202802C10558101 @default.
• W4384202802 hasConceptScore W4384202802C111919701 @default.
• W4384202802 hasConceptScore W4384202802C119599485 @default.
• W4384202802 hasConceptScore W4384202802C119857082 @default.
• W4384202802 hasConceptScore W4384202802C124101348 @default.
• W4384202802 hasConceptScore W4384202802C126838900 @default.
• W4384202802 hasConceptScore W4384202802C127413603 @default.
• W4384202802 hasConceptScore W4384202802C144024400 @default.
• W4384202802 hasConceptScore W4384202802C154945302 @default.
• W4384202802 hasConceptScore W4384202802C183115368 @default.
• W4384202802 hasConceptScore W4384202802C18762648 @default.
• W4384202802 hasConceptScore W4384202802C2780165032 @default.
• W4384202802 hasConceptScore W4384202802C30772137 @default.
• W4384202802 hasConceptScore W4384202802C36289849 @default.
• W4384202802 hasConceptScore W4384202802C41008148 @default.
• W4384202802 hasConceptScore W4384202802C45804977 @default.
• W4384202802 hasConceptScore W4384202802C507571656 @default.
• W4384202802 hasConceptScore W4384202802C71924100 @default.
• W4384202802 hasConceptScore W4384202802C76155785 @default.
• W4384202802 hasConceptScore W4384202802C78519656 @default.
• W4384202802 hasFunder F4320320300 @default.
• W4384202802 hasIssue "14" @default.
• W4384202802 hasLocation W43842028021 @default.
• W4384202802 hasLocation W43842028022 @default.
• W4384202802 hasOpenAccess W4384202802 @default.
• W4384202802 hasPrimaryLocation W43842028021 @default.
• W4384202802 hasRelatedWork W2021850411 @default.
• W4384202802 hasRelatedWork W2101460129 @default.
• W4384202802 hasRelatedWork W2961085424 @default.

• next