Matches in SemOpenAlex for { <https://semopenalex.org/work/W2793183797> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W2793183797 abstract "Electrophysiological muscle classification (EMC) is a crucial step in the diagnosis of neuromuscular disorders. Existing quantitative techniques are not sufficiently robust and accurate to be reliably clinically used. Here, EMC is modeled as a multiple instance learning (MIL) problem and a system to infer unsupervised motor unit potential (MUP) labels and create supervised muscle classifications is presented.The system has five main steps: MUP representation using morphological, stability, and near fiber parameters as well as spectral features extracted from wavelet coefficients; MUP feature selection using unsupervised Laplacian scores; MUP clustering using neighborhood distance entropy consistency to find representations of MUP normality and abnormality; muscle representation by embedding its MUP cluster associations in a feature vector; and muscle classification using support vector machines or random forests.The evaluation data consist of 63, 83, 93, and 84 sets of MUPs recorded in deltoid, vastus medialis, first dorsal interosseous, and tibialis anterior muscles, respectively. The proposed system discovered representations of normal, myopathic, and neurogenic MUPs for each specific muscle type and resulted in an average classification accuracy of 98%, which is higher than in previous works.Modeling EMC as an instance of the MIL solves the traditional problem of characterizing MUPs without full supervision. Furthermore, finding representations of MUP normality and abnormality using morphological, stability, near fiber, and spectral features improve muscle classification.The proposed method is able to characterize MUPs with respect to disease categories, with no a priori information." @default.
- W2793183797 created "2018-03-29" @default.
- W2793183797 creator A5008341202 @default.
- W2793183797 creator A5050275034 @default.
- W2793183797 date "2018-11-01" @default.
- W2793183797 modified "2023-09-25" @default.
- W2793183797 title "Electrophysiological Muscle Classification Using Multiple Instance Learning and Unsupervised Time and Spectral Domain Analysis" @default.
- W2793183797 cites W135654278 @default.
- W2793183797 cites W142173424 @default.
- W2793183797 cites W1590386482 @default.
- W2793183797 cites W1969935486 @default.
- W2793183797 cites W1970050892 @default.
- W2793183797 cites W1984822541 @default.
- W2793183797 cites W1995875735 @default.
- W2793183797 cites W1996021349 @default.
- W2793183797 cites W2001061109 @default.
- W2793183797 cites W2003168003 @default.
- W2793183797 cites W2006990966 @default.
- W2793183797 cites W2010792435 @default.
- W2793183797 cites W2016388634 @default.
- W2793183797 cites W2022319257 @default.
- W2793183797 cites W2022547468 @default.
- W2793183797 cites W2025974650 @default.
- W2793183797 cites W2056933353 @default.
- W2793183797 cites W2060915658 @default.
- W2793183797 cites W2061849496 @default.
- W2793183797 cites W2075165811 @default.
- W2793183797 cites W2103215269 @default.
- W2793183797 cites W2108745803 @default.
- W2793183797 cites W2110119381 @default.
- W2793183797 cites W2121394390 @default.
- W2793183797 cites W2131347386 @default.
- W2793183797 cites W2148603752 @default.
- W2793183797 cites W2149620660 @default.
- W2793183797 cites W2526355407 @default.
- W2793183797 cites W2526371976 @default.
- W2793183797 cites W2528967587 @default.
- W2793183797 cites W2590786131 @default.
- W2793183797 cites W273955616 @default.
- W2793183797 cites W2962771908 @default.
- W2793183797 cites W1865936406 @default.
- W2793183797 cites W2135587405 @default.
- W2793183797 cites W2549809952 @default.
- W2793183797 doi "https://doi.org/10.1109/tbme.2018.2802200" @default.
- W2793183797 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/29993485" @default.
- W2793183797 hasPublicationYear "2018" @default.
- W2793183797 type Work @default.
- W2793183797 sameAs 2793183797 @default.
- W2793183797 citedByCount "3" @default.
- W2793183797 countsByYear W27931837972020 @default.
- W2793183797 crossrefType "journal-article" @default.
- W2793183797 hasAuthorship W2793183797A5008341202 @default.
- W2793183797 hasAuthorship W2793183797A5050275034 @default.
- W2793183797 hasConcept C105702510 @default.
- W2793183797 hasConcept C12267149 @default.
- W2793183797 hasConcept C137711082 @default.
- W2793183797 hasConcept C153180895 @default.
- W2793183797 hasConcept C154945302 @default.
- W2793183797 hasConcept C2524010 @default.
- W2793183797 hasConcept C2779329155 @default.
- W2793183797 hasConcept C2781425072 @default.
- W2793183797 hasConcept C33923547 @default.
- W2793183797 hasConcept C41008148 @default.
- W2793183797 hasConcept C73555534 @default.
- W2793183797 hasConcept C86803240 @default.
- W2793183797 hasConceptScore W2793183797C105702510 @default.
- W2793183797 hasConceptScore W2793183797C12267149 @default.
- W2793183797 hasConceptScore W2793183797C137711082 @default.
- W2793183797 hasConceptScore W2793183797C153180895 @default.
- W2793183797 hasConceptScore W2793183797C154945302 @default.
- W2793183797 hasConceptScore W2793183797C2524010 @default.
- W2793183797 hasConceptScore W2793183797C2779329155 @default.
- W2793183797 hasConceptScore W2793183797C2781425072 @default.
- W2793183797 hasConceptScore W2793183797C33923547 @default.
- W2793183797 hasConceptScore W2793183797C41008148 @default.
- W2793183797 hasConceptScore W2793183797C73555534 @default.
- W2793183797 hasConceptScore W2793183797C86803240 @default.
- W2793183797 hasLocation W27931837971 @default.
- W2793183797 hasLocation W27931837972 @default.
- W2793183797 hasOpenAccess W2793183797 @default.
- W2793183797 hasPrimaryLocation W27931837971 @default.
- W2793183797 hasRelatedWork W2041399278 @default.
- W2793183797 hasRelatedWork W2056016498 @default.
- W2793183797 hasRelatedWork W2099369243 @default.
- W2793183797 hasRelatedWork W2129011754 @default.
- W2793183797 hasRelatedWork W2136184105 @default.
- W2793183797 hasRelatedWork W2141705618 @default.
- W2793183797 hasRelatedWork W2153189372 @default.
- W2793183797 hasRelatedWork W4223656335 @default.
- W2793183797 hasRelatedWork W2187500075 @default.
- W2793183797 hasRelatedWork W2345184372 @default.
- W2793183797 isParatext "false" @default.
- W2793183797 isRetracted "false" @default.
- W2793183797 magId "2793183797" @default.
- W2793183797 workType "article" @default.