Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313144868> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4313144868 abstract "This paper focuses on the detection of Parkinson’s disease based on the analysis of a patient’s gait. The growing popularity and success of Transformer networks in natural language processing and image recognition motivated us to develop a novel method for this problem based on an automatic features extraction via Transformers. The use of Transformers in 1D signal is not really widespread yet, but we show in this paper that they are effective in extracting relevant features from 1D signals. As Transformers require a lot of memory, we decoupled temporal and spatial information to make the model smaller. Our architecture used temporal Transformers, dimension reduction layers to reduce the dimension of the data, a spatial Transformer, two fully connected layers and an output layer for the final prediction. Our model outperforms the current state-of-the-art algorithm with 95.2% accuracy in distinguishing a Parkinsonian patient from a healthy one on the Physionet dataset. A key learning from this work is that Transformers allow for greater stability in results. The source code and pre-trained models are released in https://github.com/DucMinhDimitriNguyen <sup xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>1</sup> ." @default.
- W4313144868 created "2023-01-06" @default.
- W4313144868 creator A5000251216 @default.
- W4313144868 creator A5018675704 @default.
- W4313144868 creator A5048668237 @default.
- W4313144868 creator A5069984230 @default.
- W4313144868 date "2022-08-21" @default.
- W4313144868 modified "2023-10-01" @default.
- W4313144868 title "Transformers for 1D signals in Parkinson’s disease detection from gait" @default.
- W4313144868 cites W2052513666 @default.
- W4313144868 cites W2064675550 @default.
- W4313144868 cites W2084483836 @default.
- W4313144868 cites W2095634651 @default.
- W4313144868 cites W2134886133 @default.
- W4313144868 cites W2156150820 @default.
- W4313144868 cites W2162800060 @default.
- W4313144868 cites W2171056747 @default.
- W4313144868 cites W2298634118 @default.
- W4313144868 cites W2794295133 @default.
- W4313144868 cites W2886929342 @default.
- W4313144868 cites W2899053767 @default.
- W4313144868 cites W2954978348 @default.
- W4313144868 cites W2980180565 @default.
- W4313144868 cites W2992186472 @default.
- W4313144868 cites W3005709509 @default.
- W4313144868 cites W3027772394 @default.
- W4313144868 cites W3036247675 @default.
- W4313144868 cites W3090639436 @default.
- W4313144868 cites W3138516171 @default.
- W4313144868 cites W3170611527 @default.
- W4313144868 cites W3190828139 @default.
- W4313144868 cites W3211269841 @default.
- W4313144868 cites W4211044101 @default.
- W4313144868 cites W4241136696 @default.
- W4313144868 doi "https://doi.org/10.1109/icpr56361.2022.9956330" @default.
- W4313144868 hasPublicationYear "2022" @default.
- W4313144868 type Work @default.
- W4313144868 citedByCount "2" @default.
- W4313144868 countsByYear W43131448682022 @default.
- W4313144868 countsByYear W43131448682023 @default.
- W4313144868 crossrefType "proceedings-article" @default.
- W4313144868 hasAuthorship W4313144868A5000251216 @default.
- W4313144868 hasAuthorship W4313144868A5018675704 @default.
- W4313144868 hasAuthorship W4313144868A5048668237 @default.
- W4313144868 hasAuthorship W4313144868A5069984230 @default.
- W4313144868 hasBestOaLocation W43131448682 @default.
- W4313144868 hasConcept C119599485 @default.
- W4313144868 hasConcept C127413603 @default.
- W4313144868 hasConcept C153180895 @default.
- W4313144868 hasConcept C154945302 @default.
- W4313144868 hasConcept C165801399 @default.
- W4313144868 hasConcept C41008148 @default.
- W4313144868 hasConcept C52622490 @default.
- W4313144868 hasConcept C66322947 @default.
- W4313144868 hasConceptScore W4313144868C119599485 @default.
- W4313144868 hasConceptScore W4313144868C127413603 @default.
- W4313144868 hasConceptScore W4313144868C153180895 @default.
- W4313144868 hasConceptScore W4313144868C154945302 @default.
- W4313144868 hasConceptScore W4313144868C165801399 @default.
- W4313144868 hasConceptScore W4313144868C41008148 @default.
- W4313144868 hasConceptScore W4313144868C52622490 @default.
- W4313144868 hasConceptScore W4313144868C66322947 @default.
- W4313144868 hasLocation W43131448681 @default.
- W4313144868 hasLocation W43131448682 @default.
- W4313144868 hasLocation W43131448683 @default.
- W4313144868 hasOpenAccess W4313144868 @default.
- W4313144868 hasPrimaryLocation W43131448681 @default.
- W4313144868 hasRelatedWork W1964120219 @default.
- W4313144868 hasRelatedWork W2000165426 @default.
- W4313144868 hasRelatedWork W2114557664 @default.
- W4313144868 hasRelatedWork W2136054869 @default.
- W4313144868 hasRelatedWork W2144059113 @default.
- W4313144868 hasRelatedWork W2146076056 @default.
- W4313144868 hasRelatedWork W2385132419 @default.
- W4313144868 hasRelatedWork W2772780115 @default.
- W4313144868 hasRelatedWork W2811390910 @default.
- W4313144868 hasRelatedWork W3003836766 @default.
- W4313144868 isParatext "false" @default.
- W4313144868 isRetracted "false" @default.
- W4313144868 workType "article" @default.