Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387487041> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4387487041 abstract "The widespread usage of wearables set the foundations for many new applications that process the wearable sensor data. Human Activity Recognition (HAR) is a well-studied application that targets to classify the data captured by multiple wearable sensors into one of a predefined set of activity classes. Earlier approaches in the area relied on Machine Learning (ML) classifiers, while many researchers proposed solutions based on Deep Neural Networks (DNNs), e.g., using Long Short-Term Memory (LSTMs) or Convolution Neural Network (CNNs). Even though the usage of DNNs for HAR is a widely explored field, the problem of compressing (thus reducing the computational requirements) the resulting DNN models has been disregarded by the research community. This is of paramount importance if we consider that wearables are characterized by scarce memory and computational resources. In this work, we first analyze the impact of the size of the various CNN components (focusing on the convolution and dense layers) to the model validation performance. As a second step, we focus on two CNN models with diverse memory characteristics (the lean and the fat model) and we employ three different compression techniques (Filter-Based Pruning –FBP,– Low Rank Factorization –LRF,– and dynamic range quantization) assuming various compressibility scenarios." @default.
- W4387487041 created "2023-10-11" @default.
- W4387487041 creator A5056501771 @default.
- W4387487041 creator A5074371053 @default.
- W4387487041 creator A5090157400 @default.
- W4387487041 creator A5093034185 @default.
- W4387487041 creator A5093034186 @default.
- W4387487041 date "2023-09-20" @default.
- W4387487041 modified "2023-10-16" @default.
- W4387487041 title "Towards Highly Compressed CNN Models for Human Activity Recognition in Wearable Devices" @default.
- W4387487041 cites W1993482030 @default.
- W4387487041 cites W2560606776 @default.
- W4387487041 cites W2747590145 @default.
- W4387487041 cites W2759690896 @default.
- W4387487041 cites W2791825650 @default.
- W4387487041 cites W2941266383 @default.
- W4387487041 cites W2941733427 @default.
- W4387487041 cites W2946298178 @default.
- W4387487041 cites W2947411064 @default.
- W4387487041 cites W2962851801 @default.
- W4387487041 cites W2972660824 @default.
- W4387487041 cites W2974827766 @default.
- W4387487041 cites W3016856208 @default.
- W4387487041 cites W3041735433 @default.
- W4387487041 cites W3088411822 @default.
- W4387487041 cites W3098749638 @default.
- W4387487041 cites W3132950445 @default.
- W4387487041 cites W3193652037 @default.
- W4387487041 cites W3200122785 @default.
- W4387487041 cites W4200194496 @default.
- W4387487041 cites W4291214065 @default.
- W4387487041 cites W4306391190 @default.
- W4387487041 cites W4308650754 @default.
- W4387487041 cites W4310147199 @default.
- W4387487041 cites W4316661233 @default.
- W4387487041 cites W4324118479 @default.
- W4387487041 doi "https://doi.org/10.23919/spa59660.2023.10274441" @default.
- W4387487041 hasPublicationYear "2023" @default.
- W4387487041 type Work @default.
- W4387487041 citedByCount "0" @default.
- W4387487041 crossrefType "proceedings-article" @default.
- W4387487041 hasAuthorship W4387487041A5056501771 @default.
- W4387487041 hasAuthorship W4387487041A5074371053 @default.
- W4387487041 hasAuthorship W4387487041A5090157400 @default.
- W4387487041 hasAuthorship W4387487041A5093034185 @default.
- W4387487041 hasAuthorship W4387487041A5093034186 @default.
- W4387487041 hasConcept C108583219 @default.
- W4387487041 hasConcept C119857082 @default.
- W4387487041 hasConcept C121687571 @default.
- W4387487041 hasConcept C149635348 @default.
- W4387487041 hasConcept C150594956 @default.
- W4387487041 hasConcept C153180895 @default.
- W4387487041 hasConcept C154945302 @default.
- W4387487041 hasConcept C177264268 @default.
- W4387487041 hasConcept C199360897 @default.
- W4387487041 hasConcept C23224414 @default.
- W4387487041 hasConcept C28855332 @default.
- W4387487041 hasConcept C31972630 @default.
- W4387487041 hasConcept C41008148 @default.
- W4387487041 hasConcept C50644808 @default.
- W4387487041 hasConcept C54290928 @default.
- W4387487041 hasConcept C81363708 @default.
- W4387487041 hasConceptScore W4387487041C108583219 @default.
- W4387487041 hasConceptScore W4387487041C119857082 @default.
- W4387487041 hasConceptScore W4387487041C121687571 @default.
- W4387487041 hasConceptScore W4387487041C149635348 @default.
- W4387487041 hasConceptScore W4387487041C150594956 @default.
- W4387487041 hasConceptScore W4387487041C153180895 @default.
- W4387487041 hasConceptScore W4387487041C154945302 @default.
- W4387487041 hasConceptScore W4387487041C177264268 @default.
- W4387487041 hasConceptScore W4387487041C199360897 @default.
- W4387487041 hasConceptScore W4387487041C23224414 @default.
- W4387487041 hasConceptScore W4387487041C28855332 @default.
- W4387487041 hasConceptScore W4387487041C31972630 @default.
- W4387487041 hasConceptScore W4387487041C41008148 @default.
- W4387487041 hasConceptScore W4387487041C50644808 @default.
- W4387487041 hasConceptScore W4387487041C54290928 @default.
- W4387487041 hasConceptScore W4387487041C81363708 @default.
- W4387487041 hasFunder F4320323894 @default.
- W4387487041 hasLocation W43874870411 @default.
- W4387487041 hasOpenAccess W4387487041 @default.
- W4387487041 hasPrimaryLocation W43874870411 @default.
- W4387487041 hasRelatedWork W103069296 @default.
- W4387487041 hasRelatedWork W2095299560 @default.
- W4387487041 hasRelatedWork W2117913171 @default.
- W4387487041 hasRelatedWork W2582769230 @default.
- W4387487041 hasRelatedWork W2797760888 @default.
- W4387487041 hasRelatedWork W2943851981 @default.
- W4387487041 hasRelatedWork W2951851360 @default.
- W4387487041 hasRelatedWork W3090300519 @default.
- W4387487041 hasRelatedWork W3105278570 @default.
- W4387487041 hasRelatedWork W4250401876 @default.
- W4387487041 isParatext "false" @default.
- W4387487041 isRetracted "false" @default.
- W4387487041 workType "article" @default.