FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311157749> ?p ?o ?g. }

• W4311157749 endingPage "104429" @default.
• W4311157749 startingPage "104429" @default.
• W4311157749 abstract "Over the last few years, research in automatic sleep scoring has mainly focused on developing increasingly complex deep learning architectures. However, recently these approaches achieved only marginal improvements, often at the expense of requiring more data and more expensive training procedures. Despite all these efforts and their satisfactory performance, automatic sleep staging solutions are not widely adopted in a clinical context yet. We argue that most deep learning solutions for sleep scoring are limited in their real-world applicability as they are hard to train, deploy, and reproduce. Moreover, these solutions lack interpretability and transparency, which are often key to increase adoption rates. In this work, we revisit the problem of sleep stage classification using classical machine learning. Results show that competitive performance can be achieved with a conventional machine learning pipeline consisting of preprocessing, feature extraction, and a simple machine learning model. In particular, we analyze the performance of a linear model and a non-linear (gradient boosting) model. Our approach surpasses state-of-the-art (that uses the same data) on two public datasets: Sleep-EDF SC-20 (MF1 0.810) and Sleep-EDF ST (MF1 0.795), while achieving competitive results on Sleep-EDF SC-78 (MF1 0.775) and MASS SS3 (MF1 0.817). We show that, for the sleep stage scoring task, the expressiveness of an engineered feature vector is on par with the internally learned representations of deep learning models. This observation opens the door to clinical adoption, as a representative feature vector allows to leverage both the interpretability and successful track record of traditional machine learning models." @default.
• W4311157749 created "2022-12-24" @default.
• W4311157749 creator A5003657036 @default.
• W4311157749 creator A5019986708 @default.
• W4311157749 creator A5023583322 @default.
• W4311157749 creator A5025315149 @default.
• W4311157749 creator A5026901904 @default.
• W4311157749 creator A5059752990 @default.
• W4311157749 creator A5086602135 @default.
• W4311157749 date "2023-03-01" @default.
• W4311157749 modified "2023-10-14" @default.
• W4311157749 title "Do not sleep on traditional machine learning" @default.
• W4311157749 cites W1545241942 @default.
• W4311157749 cites W1826713356 @default.
• W4311157749 cites W1983256092 @default.
• W4311157749 cites W1995200202 @default.
• W4311157749 cites W2000938010 @default.
• W4311157749 cites W2017689092 @default.
• W4311157749 cites W2019241323 @default.
• W4311157749 cites W2020958128 @default.
• W4311157749 cites W2023817852 @default.
• W4311157749 cites W2054384069 @default.
• W4311157749 cites W2058807024 @default.
• W4311157749 cites W2102376611 @default.
• W4311157749 cites W2143159308 @default.
• W4311157749 cites W2144691514 @default.
• W4311157749 cites W2161336914 @default.
• W4311157749 cites W2180889008 @default.
• W4311157749 cites W2539353608 @default.
• W4311157749 cites W2588327383 @default.
• W4311157749 cites W2604096629 @default.
• W4311157749 cites W2612047884 @default.
• W4311157749 cites W2754591458 @default.
• W4311157749 cites W2790486743 @default.
• W4311157749 cites W2793841943 @default.
• W4311157749 cites W2802314367 @default.
• W4311157749 cites W2805033630 @default.
• W4311157749 cites W2900178629 @default.
• W4311157749 cites W2902751862 @default.
• W4311157749 cites W2908603469 @default.
• W4311157749 cites W2920016582 @default.
• W4311157749 cites W2927147597 @default.
• W4311157749 cites W2945976633 @default.
• W4311157749 cites W2946507061 @default.
• W4311157749 cites W2963919481 @default.
• W4311157749 cites W2964959984 @default.
• W4311157749 cites W2969159609 @default.
• W4311157749 cites W3008174708 @default.
• W4311157749 cites W3035374448 @default.
• W4311157749 cites W3040939498 @default.
• W4311157749 cites W3044656331 @default.
• W4311157749 cites W3102476541 @default.
• W4311157749 cites W3109650690 @default.
• W4311157749 cites W3133961566 @default.
• W4311157749 cites W3156463266 @default.
• W4311157749 cites W3158818505 @default.
• W4311157749 cites W3165396901 @default.
• W4311157749 cites W3205486398 @default.
• W4311157749 cites W3206812283 @default.
• W4311157749 cites W4220753546 @default.
• W4311157749 cites W4283213862 @default.
• W4311157749 cites W7692620 @default.
• W4311157749 doi "https://doi.org/10.1016/j.bspc.2022.104429" @default.
• W4311157749 hasPublicationYear "2023" @default.
• W4311157749 type Work @default.
• W4311157749 citedByCount "7" @default.
• W4311157749 countsByYear W43111577492023 @default.
• W4311157749 crossrefType "journal-article" @default.
• W4311157749 hasAuthorship W4311157749A5003657036 @default.
• W4311157749 hasAuthorship W4311157749A5019986708 @default.
• W4311157749 hasAuthorship W4311157749A5023583322 @default.
• W4311157749 hasAuthorship W4311157749A5025315149 @default.
• W4311157749 hasAuthorship W4311157749A5026901904 @default.
• W4311157749 hasAuthorship W4311157749A5059752990 @default.
• W4311157749 hasAuthorship W4311157749A5086602135 @default.
• W4311157749 hasBestOaLocation W43111577492 @default.
• W4311157749 hasConcept C108583219 @default.
• W4311157749 hasConcept C118552586 @default.
• W4311157749 hasConcept C119857082 @default.
• W4311157749 hasConcept C153083717 @default.
• W4311157749 hasConcept C154945302 @default.
• W4311157749 hasConcept C15744967 @default.
• W4311157749 hasConcept C2778205975 @default.
• W4311157749 hasConcept C2778827112 @default.
• W4311157749 hasConcept C2781067378 @default.
• W4311157749 hasConcept C2781326671 @default.
• W4311157749 hasConcept C2910364982 @default.
• W4311157749 hasConcept C34736171 @default.
• W4311157749 hasConcept C41008148 @default.
• W4311157749 hasConceptScore W4311157749C108583219 @default.
• W4311157749 hasConceptScore W4311157749C118552586 @default.
• W4311157749 hasConceptScore W4311157749C119857082 @default.
• W4311157749 hasConceptScore W4311157749C153083717 @default.
• W4311157749 hasConceptScore W4311157749C154945302 @default.
• W4311157749 hasConceptScore W4311157749C15744967 @default.
• W4311157749 hasConceptScore W4311157749C2778205975 @default.
• W4311157749 hasConceptScore W4311157749C2778827112 @default.
• W4311157749 hasConceptScore W4311157749C2781067378 @default.

• next