File(s) under permanent embargo
Classification of Implantable Rotary Blood Pump States with Class Noise
journal contribution
posted on 2016-05-01, 00:00 authored by H L Ooi, M Seera, S C Ng, Chee Peng LimChee Peng Lim, C K Loo, N H Lovell, S J Redmond, E LimA medical case study related to implantable rotary blood pumps is examined. Five classifiers and two ensemble classifiers are applied to process the signals collected from the pumps for the identification of the aortic valve nonopening pump state. In addition to the noise-free datasets, up to 40% class noise has been added to the signals to evaluate the classification performance when mislabeling is present in the classifier training set. In order to ensure a reliable diagnostic model for the identification of the pump states, classifications performed with and without class noise are evaluated. The multilayer perceptron emerged as the best performing classifier for pump state detection due to its high accuracy as well as robustness against class noise.
History
Journal
IEEE Journal of Biomedical and Health InformaticsVolume
20Issue
3Pagination
829 - 837Publisher DOI
ISSN
2168-2194eISSN
2168-2208Publication classification
C Journal article; C1 Refereed article in a scholarly journalCopyright notice
2015, IEEEUsage metrics
Categories
No categories selectedKeywords
Science & TechnologyTechnologyLife Sciences & BiomedicineComputer Science, Information SystemsComputer Science, Interdisciplinary ApplicationsMathematical & Computational BiologyMedical InformaticsComputer ScienceClassificationclassifierclass noiseensemble classifierimplantable rotary blood pump (IRBP)left ventricular assist device (VAD)mislabelingpump state classificationSUCTION DETECTIONCONTROL-SYSTEMHEART-FAILURESUPPORTSELECTIONEVENTSOPTIMIZATIONALGORITHMCURVEMODELnoisebloodvalvesheartinformaticstrainingrobustness
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC