V-awake: a visual analytics approach for correcting sleep predictions from deep learning models

Humberto Garcia Caballero, Michel Westenberg, Binyam Gebre, Jack van Wijk

Onderzoeksoutput: Bijdrage aan tijdschriftCongresartikelpeer review

18 Citaten (Scopus)
287 Downloads (Pure)

Samenvatting

The usage of deep learning models for tagging input data has increased over the past years because of their accuracy and high performance. A successful application is to score sleep stages. In this scenario, models are trained to predict the sleep stages of individuals. Although their predictive accuracy is high, there are still misclassifications that prevent doctors from properly diagnosing sleep-related disorders. This paper presents a system that allows users to explore the output of deep learning models in a real-life scenario to spot and analyze faulty predictions. These can be corrected by users to generate a sequence of sleep stages to be examined by doctors. Our approach addresses a real-life scenario with absence of ground truth. It differs from others in that our goal is not to improve the model itself, but to correct the predictions it provides. We demonstrate that our approach is effective in identifying faulty predictions and helping users to fix them in the proposed use case.
Originele taal-2Engels
Pagina's (van-tot)1-12
Aantal pagina's12
TijdschriftComputer Graphics Forum
Volume38
Nummer van het tijdschrift3
DOI's
StatusGepubliceerd - 21 mrt. 2019
Evenement21st Eurographics/IEEE VGTC Conference on Visualization - Alfandega do Porto Congress Centre, Porto, Portugal
Duur: 3 jun. 20197 jun. 2019
https://www.eurovis.org/

Vingerafdruk

Duik in de onderzoeksthema's van 'V-awake: a visual analytics approach for correcting sleep predictions from deep learning models'. Samen vormen ze een unieke vingerafdruk.
  • Eurovis 2019 Honorable Mention

    Garcia Caballero, H. (Ontvanger), Westenberg, M. (Ontvanger), Gebre, B. (Ontvanger) & van Wijk, J. (Ontvanger), 7 jun. 2019

    Prijs: AndersWerk, activiteit of publicatie gerelateerde prijzen (lifetime, best paper, poster etc.)Wetenschappelijk

    Bestand

Citeer dit