Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210705716> ?p ?o ?g. }
Showing items 1 to 70 of
70
with 100 items per page.
- W4210705716 abstract "Human Activity Recognition (HAR) from sensor measurements is still challenging due to noisy or lack of la-belled examples and issues concerning data privacy. Training a traditional centralized machine learning (ML) model for HAR is constrained by infrastructure availability, network connectivity, latency issues etc. Issues regarding labels of user measurements can be tackled by using semi-supervised learning while issues regarding privacy concerns can be addressed by increasingly popular Federated Learning (FL). In this work, we propose a novel algorithm GraFeHTy, a Graph Convolution Network (GCN) trained in a federated setting to alleviate these key obstructions for HAR. We construct a similarity graph from sensor measurements for each user and apply a GCN to perform semi-supervised classification of human activities by leveraging inter-relatedness and closeness of activities. The weights of the GCN are trained using federated learning where each user performs gradient descent using their local data and share only the updated weights with a central server for aggregation. The GCN helps in accurate detection of unlabelled or noisy labels in the activity sequence by borrowing information from similar labelled nodes. The federated setting for training these models ensures that user privacy is respected by transferring only the learned representations out of the device to a central server. By avoiding transfer of raw data, the algorithm also ensures that training a HAR model is not constrained by infrastructure availability in central server or low network bandwidth from edge devices. Our proposed algorithm performs better than the baseline feed-forward federated learning model in terms of both accuracy and computational complexity." @default.
- W4210705716 created "2022-02-08" @default.
- W4210705716 creator A5003307931 @default.
- W4210705716 creator A5037633480 @default.
- W4210705716 creator A5069515948 @default.
- W4210705716 date "2021-12-01" @default.
- W4210705716 modified "2023-10-16" @default.
- W4210705716 title "GraFeHTy: Graph Neural Network using Federated Learning for Human Activity Recognition" @default.
- W4210705716 cites W1852728451 @default.
- W4210705716 cites W2017634428 @default.
- W4210705716 cites W2103388129 @default.
- W4210705716 cites W2753238659 @default.
- W4210705716 cites W2794717185 @default.
- W4210705716 cites W2804739511 @default.
- W4210705716 cites W2922569945 @default.
- W4210705716 cites W3129932124 @default.
- W4210705716 doi "https://doi.org/10.1109/icmla52953.2021.00184" @default.
- W4210705716 hasPublicationYear "2021" @default.
- W4210705716 type Work @default.
- W4210705716 citedByCount "4" @default.
- W4210705716 countsByYear W42107057162022 @default.
- W4210705716 countsByYear W42107057162023 @default.
- W4210705716 crossrefType "proceedings-article" @default.
- W4210705716 hasAuthorship W4210705716A5003307931 @default.
- W4210705716 hasAuthorship W4210705716A5037633480 @default.
- W4210705716 hasAuthorship W4210705716A5069515948 @default.
- W4210705716 hasConcept C108827166 @default.
- W4210705716 hasConcept C119857082 @default.
- W4210705716 hasConcept C123201435 @default.
- W4210705716 hasConcept C124101348 @default.
- W4210705716 hasConcept C132525143 @default.
- W4210705716 hasConcept C134306372 @default.
- W4210705716 hasConcept C153258448 @default.
- W4210705716 hasConcept C154945302 @default.
- W4210705716 hasConcept C2779545769 @default.
- W4210705716 hasConcept C2992525071 @default.
- W4210705716 hasConcept C33923547 @default.
- W4210705716 hasConcept C41008148 @default.
- W4210705716 hasConcept C50644808 @default.
- W4210705716 hasConcept C80444323 @default.
- W4210705716 hasConceptScore W4210705716C108827166 @default.
- W4210705716 hasConceptScore W4210705716C119857082 @default.
- W4210705716 hasConceptScore W4210705716C123201435 @default.
- W4210705716 hasConceptScore W4210705716C124101348 @default.
- W4210705716 hasConceptScore W4210705716C132525143 @default.
- W4210705716 hasConceptScore W4210705716C134306372 @default.
- W4210705716 hasConceptScore W4210705716C153258448 @default.
- W4210705716 hasConceptScore W4210705716C154945302 @default.
- W4210705716 hasConceptScore W4210705716C2779545769 @default.
- W4210705716 hasConceptScore W4210705716C2992525071 @default.
- W4210705716 hasConceptScore W4210705716C33923547 @default.
- W4210705716 hasConceptScore W4210705716C41008148 @default.
- W4210705716 hasConceptScore W4210705716C50644808 @default.
- W4210705716 hasConceptScore W4210705716C80444323 @default.
- W4210705716 hasLocation W42107057161 @default.
- W4210705716 hasOpenAccess W4210705716 @default.
- W4210705716 hasPrimaryLocation W42107057161 @default.
- W4210705716 hasRelatedWork W2386387936 @default.
- W4210705716 hasRelatedWork W2961085424 @default.
- W4210705716 hasRelatedWork W3046775127 @default.
- W4210705716 hasRelatedWork W3170094116 @default.
- W4210705716 hasRelatedWork W4205958290 @default.
- W4210705716 hasRelatedWork W4285260836 @default.
- W4210705716 hasRelatedWork W4286629047 @default.
- W4210705716 hasRelatedWork W4306321456 @default.
- W4210705716 hasRelatedWork W4306674287 @default.
- W4210705716 hasRelatedWork W4224009465 @default.
- W4210705716 isParatext "false" @default.
- W4210705716 isRetracted "false" @default.
- W4210705716 workType "article" @default.