Matches in SemOpenAlex for { <https://semopenalex.org/work/W4294789909> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4294789909 abstract "In this paper, we propose a self-supervised learning solution for human activity recognition with smartphone accelerometer data. We aim to develop a model that learns strong representations from accelerometer signals, in order to perform robust human activity classification, while reducing the model's reliance on class labels. Specifically, we intend to enable cross-dataset transfer learning such that our network pre-trained on a particular dataset can perform effective activity classification on other datasets (successive to a small amount of fine-tuning). To tackle this problem, we design our solution with the intention of learning as much information from the accelerometer signals as possible. As a result, we design two separate pipelines, one that learns the data in time-frequency domain, and the other in time-domain alone. In order to address the issues mentioned above in regards to cross-dataset transfer learning, we use self-supervised contrastive learning to train each of these streams. Next, each stream is fine-tuned for final classification, and eventually the two are fused to provide the final results. We evaluate the performance of the proposed solution on three datasets, namely MotionSense, HAPT, and HHAR, and demonstrate that our solution outperforms prior works in this field. We further evaluate the performance of the method in learning generalized features, by using MobiAct dataset for pre-training and the remaining three datasets for the downstream classification task, and show that the proposed solution achieves better performance in comparison with other self-supervised methods in cross-dataset transfer learning." @default.
- W4294789909 created "2022-09-06" @default.
- W4294789909 creator A5036602603 @default.
- W4294789909 creator A5039812985 @default.
- W4294789909 creator A5064074057 @default.
- W4294789909 date "2022-08-26" @default.
- W4294789909 modified "2023-10-16" @default.
- W4294789909 title "Self-Supervised Human Activity Recognition with Localized Time-Frequency Contrastive Representation Learning" @default.
- W4294789909 doi "https://doi.org/10.48550/arxiv.2209.00990" @default.
- W4294789909 hasPublicationYear "2022" @default.
- W4294789909 type Work @default.
- W4294789909 citedByCount "0" @default.
- W4294789909 crossrefType "posted-content" @default.
- W4294789909 hasAuthorship W4294789909A5036602603 @default.
- W4294789909 hasAuthorship W4294789909A5039812985 @default.
- W4294789909 hasAuthorship W4294789909A5064074057 @default.
- W4294789909 hasBestOaLocation W42947899091 @default.
- W4294789909 hasConcept C111919701 @default.
- W4294789909 hasConcept C119857082 @default.
- W4294789909 hasConcept C121687571 @default.
- W4294789909 hasConcept C134306372 @default.
- W4294789909 hasConcept C136389625 @default.
- W4294789909 hasConcept C150899416 @default.
- W4294789909 hasConcept C153180895 @default.
- W4294789909 hasConcept C154945302 @default.
- W4294789909 hasConcept C162324750 @default.
- W4294789909 hasConcept C17744445 @default.
- W4294789909 hasConcept C187736073 @default.
- W4294789909 hasConcept C199539241 @default.
- W4294789909 hasConcept C202444582 @default.
- W4294789909 hasConcept C2776359362 @default.
- W4294789909 hasConcept C2777212361 @default.
- W4294789909 hasConcept C2780451532 @default.
- W4294789909 hasConcept C33923547 @default.
- W4294789909 hasConcept C36503486 @default.
- W4294789909 hasConcept C41008148 @default.
- W4294789909 hasConcept C50644808 @default.
- W4294789909 hasConcept C89805583 @default.
- W4294789909 hasConcept C94625758 @default.
- W4294789909 hasConcept C9652623 @default.
- W4294789909 hasConceptScore W4294789909C111919701 @default.
- W4294789909 hasConceptScore W4294789909C119857082 @default.
- W4294789909 hasConceptScore W4294789909C121687571 @default.
- W4294789909 hasConceptScore W4294789909C134306372 @default.
- W4294789909 hasConceptScore W4294789909C136389625 @default.
- W4294789909 hasConceptScore W4294789909C150899416 @default.
- W4294789909 hasConceptScore W4294789909C153180895 @default.
- W4294789909 hasConceptScore W4294789909C154945302 @default.
- W4294789909 hasConceptScore W4294789909C162324750 @default.
- W4294789909 hasConceptScore W4294789909C17744445 @default.
- W4294789909 hasConceptScore W4294789909C187736073 @default.
- W4294789909 hasConceptScore W4294789909C199539241 @default.
- W4294789909 hasConceptScore W4294789909C202444582 @default.
- W4294789909 hasConceptScore W4294789909C2776359362 @default.
- W4294789909 hasConceptScore W4294789909C2777212361 @default.
- W4294789909 hasConceptScore W4294789909C2780451532 @default.
- W4294789909 hasConceptScore W4294789909C33923547 @default.
- W4294789909 hasConceptScore W4294789909C36503486 @default.
- W4294789909 hasConceptScore W4294789909C41008148 @default.
- W4294789909 hasConceptScore W4294789909C50644808 @default.
- W4294789909 hasConceptScore W4294789909C89805583 @default.
- W4294789909 hasConceptScore W4294789909C94625758 @default.
- W4294789909 hasConceptScore W4294789909C9652623 @default.
- W4294789909 hasLocation W42947899091 @default.
- W4294789909 hasOpenAccess W4294789909 @default.
- W4294789909 hasPrimaryLocation W42947899091 @default.
- W4294789909 hasRelatedWork W2157140950 @default.
- W4294789909 hasRelatedWork W2752124967 @default.
- W4294789909 hasRelatedWork W2883074505 @default.
- W4294789909 hasRelatedWork W2949389179 @default.
- W4294789909 hasRelatedWork W3099805903 @default.
- W4294789909 hasRelatedWork W3204733840 @default.
- W4294789909 hasRelatedWork W4213165337 @default.
- W4294789909 hasRelatedWork W4226361678 @default.
- W4294789909 hasRelatedWork W4283732260 @default.
- W4294789909 hasRelatedWork W4285307088 @default.
- W4294789909 isParatext "false" @default.
- W4294789909 isRetracted "false" @default.
- W4294789909 workType "article" @default.