Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385835703> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W4385835703 abstract "<p>Auditory attention decoding (AAD) algorithms process brain data such as electroencephalography (EEG) in order to decode to which of multiple competing sound sources a person attends. Example use cases are neuro-steered hearing aids or brain-computer interfaces (BCI) for patients with severe motor or cognitive impairments. Recently, it has been shown that it is possible to train such AAD decoders in an unsupervised setting, where there is no ground truth available regarding which of the sound sources is attended. However, in the absence of such ground-truth labels, it is difficult to quantify the accuracy of the decoders, in particular when working with patients who can neither communicate nor show any evidence of collaboration. In this paper, we use principles of digital communications to estimate the AAD accuracy during a competing talker listening task in a completely unsupervised manner. We show that our proposed unsupervised estimation technique can accurately determine the accuracy of the decoder in a transparent-for-the-user way, for different amounts of training data, decision window lengths, and amounts of estimation data. Furthermore, since different applications demand different targeted accuracies, our approach can estimate the required minimal amount of training required for any given target accuracy. In neuro-steered hearing aids, our approach could support time-adaptive decoding, dynamic gain control, and neurofeedback training. In BCIs, it could support a robust communication paradigm for caregivers and professionals to reach and gain insights into people who cannot communicate by any means.</p>" @default.
- W4385835703 created "2023-08-16" @default.
- W4385835703 creator A5013693318 @default.
- W4385835703 creator A5043701452 @default.
- W4385835703 creator A5065884964 @default.
- W4385835703 date "2023-08-15" @default.
- W4385835703 modified "2023-10-03" @default.
- W4385835703 title "Unsupervised Accuracy Estimation for Brain-Computer Interfaces based on Auditory Attention Decoding" @default.
- W4385835703 doi "https://doi.org/10.36227/techrxiv.23925183" @default.
- W4385835703 hasPublicationYear "2023" @default.
- W4385835703 type Work @default.
- W4385835703 citedByCount "0" @default.
- W4385835703 crossrefType "posted-content" @default.
- W4385835703 hasAuthorship W4385835703A5013693318 @default.
- W4385835703 hasAuthorship W4385835703A5043701452 @default.
- W4385835703 hasAuthorship W4385835703A5065884964 @default.
- W4385835703 hasBestOaLocation W43858357031 @default.
- W4385835703 hasConcept C111919701 @default.
- W4385835703 hasConcept C11413529 @default.
- W4385835703 hasConcept C118552586 @default.
- W4385835703 hasConcept C119857082 @default.
- W4385835703 hasConcept C154945302 @default.
- W4385835703 hasConcept C15744967 @default.
- W4385835703 hasConcept C162324750 @default.
- W4385835703 hasConcept C169760540 @default.
- W4385835703 hasConcept C169900460 @default.
- W4385835703 hasConcept C173201364 @default.
- W4385835703 hasConcept C177291462 @default.
- W4385835703 hasConcept C187736073 @default.
- W4385835703 hasConcept C2434490 @default.
- W4385835703 hasConcept C2780451532 @default.
- W4385835703 hasConcept C28490314 @default.
- W4385835703 hasConcept C41008148 @default.
- W4385835703 hasConcept C46312422 @default.
- W4385835703 hasConcept C522805319 @default.
- W4385835703 hasConcept C57273362 @default.
- W4385835703 hasConcept C98045186 @default.
- W4385835703 hasConceptScore W4385835703C111919701 @default.
- W4385835703 hasConceptScore W4385835703C11413529 @default.
- W4385835703 hasConceptScore W4385835703C118552586 @default.
- W4385835703 hasConceptScore W4385835703C119857082 @default.
- W4385835703 hasConceptScore W4385835703C154945302 @default.
- W4385835703 hasConceptScore W4385835703C15744967 @default.
- W4385835703 hasConceptScore W4385835703C162324750 @default.
- W4385835703 hasConceptScore W4385835703C169760540 @default.
- W4385835703 hasConceptScore W4385835703C169900460 @default.
- W4385835703 hasConceptScore W4385835703C173201364 @default.
- W4385835703 hasConceptScore W4385835703C177291462 @default.
- W4385835703 hasConceptScore W4385835703C187736073 @default.
- W4385835703 hasConceptScore W4385835703C2434490 @default.
- W4385835703 hasConceptScore W4385835703C2780451532 @default.
- W4385835703 hasConceptScore W4385835703C28490314 @default.
- W4385835703 hasConceptScore W4385835703C41008148 @default.
- W4385835703 hasConceptScore W4385835703C46312422 @default.
- W4385835703 hasConceptScore W4385835703C522805319 @default.
- W4385835703 hasConceptScore W4385835703C57273362 @default.
- W4385835703 hasConceptScore W4385835703C98045186 @default.
- W4385835703 hasLocation W43858357031 @default.
- W4385835703 hasOpenAccess W4385835703 @default.
- W4385835703 hasPrimaryLocation W43858357031 @default.
- W4385835703 hasRelatedWork W131149161 @default.
- W4385835703 hasRelatedWork W1964859783 @default.
- W4385835703 hasRelatedWork W1981067500 @default.
- W4385835703 hasRelatedWork W2020519896 @default.
- W4385835703 hasRelatedWork W2048874067 @default.
- W4385835703 hasRelatedWork W2050832787 @default.
- W4385835703 hasRelatedWork W2619302468 @default.
- W4385835703 hasRelatedWork W3022820084 @default.
- W4385835703 hasRelatedWork W4291149673 @default.
- W4385835703 hasRelatedWork W4313452750 @default.
- W4385835703 isParatext "false" @default.
- W4385835703 isRetracted "false" @default.
- W4385835703 workType "article" @default.