Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312411665> ?p ?o ?g. }
- W4312411665 endingPage "505" @default.
- W4312411665 startingPage "494" @default.
- W4312411665 abstract "Machine learning based sleep scoring methods aim to automate the process of annotating polysomnograms with sleep stages. Although sleep signals of multiple modalities and channels should contain more information according to sleep guidelines, most multi-channel multi-modal models in the literature showed only a little performance improvement compared to single-channel EEG models and sometimes even failed to outperform them. In this paper, we investigate whether the high performance of single-channel EEG models can be attributed to specific model features in their deep learning architectures and to which extent multi-channel multi-modal models take the information from different channels of modalities into account. First, we transfer the model features from single-channel EEG models, such as combinations of small and large filters in CNNs, to multi-channel multi-modal models and measure their impacts. Second, we employ two explainability methods, the layer-wise relevance propagation as post-hoc and the embedded channel attention network as intrinsic interpretability methods, to measure the contribution of different channels on predictive performance. We find that i) single-channel model features can improve the performance of multi-channel multi-modal models and ii) multi-channel multi-modal models focus on one important channel per modality and use the remaining channels to complement the information of the focused channels. Our results suggest that more advanced methods for aggregating channel information using complementary information from other channels may improve sleep scoring performance for multi-channel multi-modal models." @default.
- W4312411665 created "2023-01-04" @default.
- W4312411665 creator A5031482999 @default.
- W4312411665 creator A5054484216 @default.
- W4312411665 creator A5074888054 @default.
- W4312411665 creator A5081422074 @default.
- W4312411665 date "2023-01-01" @default.
- W4312411665 modified "2023-10-18" @default.
- W4312411665 title "Channel Contribution in Deep Learning Based Automatic Sleep Scoring—How Many Channels Do We Need?" @default.
- W4312411665 cites W1787224781 @default.
- W4312411665 cites W1902237438 @default.
- W4312411665 cites W1983256092 @default.
- W4312411665 cites W2054384069 @default.
- W4312411665 cites W2144691514 @default.
- W4312411665 cites W2162800060 @default.
- W4312411665 cites W2292242701 @default.
- W4312411665 cites W2396351021 @default.
- W4312411665 cites W2482168716 @default.
- W4312411665 cites W2604096629 @default.
- W4312411665 cites W2657631929 @default.
- W4312411665 cites W2752782242 @default.
- W4312411665 cites W2790486743 @default.
- W4312411665 cites W2802503051 @default.
- W4312411665 cites W2805033630 @default.
- W4312411665 cites W2899434936 @default.
- W4312411665 cites W2900178629 @default.
- W4312411665 cites W2920016582 @default.
- W4312411665 cites W2956993163 @default.
- W4312411665 cites W2963132934 @default.
- W4312411665 cites W2963919481 @default.
- W4312411665 cites W2964449086 @default.
- W4312411665 cites W2969159609 @default.
- W4312411665 cites W2973069650 @default.
- W4312411665 cites W3034369844 @default.
- W4312411665 cites W3034552520 @default.
- W4312411665 cites W3035374448 @default.
- W4312411665 cites W3082394918 @default.
- W4312411665 cites W3082807479 @default.
- W4312411665 cites W3133961566 @default.
- W4312411665 cites W3158818505 @default.
- W4312411665 cites W3188349400 @default.
- W4312411665 cites W3205486398 @default.
- W4312411665 doi "https://doi.org/10.1109/tnsre.2022.3227040" @default.
- W4312411665 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37015588" @default.
- W4312411665 hasPublicationYear "2023" @default.
- W4312411665 type Work @default.
- W4312411665 citedByCount "1" @default.
- W4312411665 countsByYear W43124116652023 @default.
- W4312411665 crossrefType "journal-article" @default.
- W4312411665 hasAuthorship W4312411665A5031482999 @default.
- W4312411665 hasAuthorship W4312411665A5054484216 @default.
- W4312411665 hasAuthorship W4312411665A5074888054 @default.
- W4312411665 hasAuthorship W4312411665A5081422074 @default.
- W4312411665 hasBestOaLocation W43124116651 @default.
- W4312411665 hasConcept C119857082 @default.
- W4312411665 hasConcept C127162648 @default.
- W4312411665 hasConcept C144024400 @default.
- W4312411665 hasConcept C154945302 @default.
- W4312411665 hasConcept C185592680 @default.
- W4312411665 hasConcept C188027245 @default.
- W4312411665 hasConcept C2779903281 @default.
- W4312411665 hasConcept C2781067378 @default.
- W4312411665 hasConcept C36289849 @default.
- W4312411665 hasConcept C41008148 @default.
- W4312411665 hasConcept C71139939 @default.
- W4312411665 hasConcept C76155785 @default.
- W4312411665 hasConcept C8854915 @default.
- W4312411665 hasConceptScore W4312411665C119857082 @default.
- W4312411665 hasConceptScore W4312411665C127162648 @default.
- W4312411665 hasConceptScore W4312411665C144024400 @default.
- W4312411665 hasConceptScore W4312411665C154945302 @default.
- W4312411665 hasConceptScore W4312411665C185592680 @default.
- W4312411665 hasConceptScore W4312411665C188027245 @default.
- W4312411665 hasConceptScore W4312411665C2779903281 @default.
- W4312411665 hasConceptScore W4312411665C2781067378 @default.
- W4312411665 hasConceptScore W4312411665C36289849 @default.
- W4312411665 hasConceptScore W4312411665C41008148 @default.
- W4312411665 hasConceptScore W4312411665C71139939 @default.
- W4312411665 hasConceptScore W4312411665C76155785 @default.
- W4312411665 hasConceptScore W4312411665C8854915 @default.
- W4312411665 hasLocation W43124116651 @default.
- W4312411665 hasLocation W43124116652 @default.
- W4312411665 hasLocation W43124116653 @default.
- W4312411665 hasOpenAccess W4312411665 @default.
- W4312411665 hasPrimaryLocation W43124116651 @default.
- W4312411665 hasRelatedWork W3006943036 @default.
- W4312411665 hasRelatedWork W3205552558 @default.
- W4312411665 hasRelatedWork W4200511449 @default.
- W4312411665 hasRelatedWork W4206534706 @default.
- W4312411665 hasRelatedWork W4210353198 @default.
- W4312411665 hasRelatedWork W4229079080 @default.
- W4312411665 hasRelatedWork W4299487748 @default.
- W4312411665 hasRelatedWork W4385957992 @default.
- W4312411665 hasRelatedWork W4385965371 @default.
- W4312411665 hasRelatedWork W4386025632 @default.
- W4312411665 hasVolume "31" @default.
- W4312411665 isParatext "false" @default.
- W4312411665 isRetracted "false" @default.