Mostra el registre d'ítem simple

dc.contributor.authorRaboshchuk, Ganna
dc.contributor.authorNadeu Camprubí, Climent
dc.contributor.authorJancovic, Peter
dc.contributor.authorPeiró Lilja, Alexandre Cristian
dc.contributor.authorKokuer, Munevver
dc.contributor.authorMuñoz Mahamud, Blanca
dc.contributor.authorRiverola de Veciana, Ana
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2018-01-15T14:12:36Z
dc.date.available2018-01-15T14:12:36Z
dc.date.issued2017-12-21
dc.identifier.citationRaboshchuk, G., Nadeu, C., Jancovic, P., Peiro, A., Kokuer, M., Muñoz, B., Riverola , A. A knowledge-based approach to automatic detection of equipment alarm sounds in a neonatal intensive care unit environment. "IEEE Journal of Translational Engineering in Health and Medicine", 21 Desembre 2017, vol. 6, p. 4400110-1 / 4400110-10
dc.identifier.issn2168-2372
dc.identifier.urihttp://hdl.handle.net/2117/112805
dc.description.abstractA large number of alarm sounds triggered by biomedical equipment occur frequently in the noisy environment of a neonatal intensive care unit (NICU) and play a key role in providing healthcare. In this paper, our work on the development of an automatic system for detection of acoustic alarms in that difficult environment is presented. Such automatic detection system is needed for the investigation of how a preterm infant reacts to auditory stimuli of the NICU environment and for an improved real-time patient monitoring. The approach presented in this paper consists of using the available knowledge about each alarm class in the design of the detection system. The information about the frequency structure is used in the feature extraction stage and the time structure knowledge is incorporated at the post-processing stage. Several alternative methods are compared for feature extraction, modelling and post-processing. The detection performance is evaluated with real data recorded in the NICU of the hospital, and by using both frame-level and period-level metrics. The experimental results show that the inclusion of both spectral and temporal information allows to improve the baseline detection performance by more than 60%
dc.language.isoeng
dc.subjectÀrees temàtiques de la UPC::Física::Acústica
dc.subject.lcshAcoustical engineering
dc.subject.lcshNeonatal intensive care unit
dc.subject.otherAcoustic event detection
dc.subject.otherAcoustics
dc.subject.otherAlarm detection
dc.subject.otherBiomedical equipment
dc.subject.otherDetectors
dc.subject.otherFeature extraction
dc.subject.otherMonitoring
dc.subject.otherNeonatal intensive Care unit
dc.subject.otherNeural networks
dc.subject.otherNon-negative matrix factorization
dc.subject.otherPediatrics
dc.subject.otherSinusoid detection
dc.subject.otherTime-frequency analysis
dc.titleA knowledge-based approach to automatic detection of equipment alarm sounds in a neonatal intensive care unit environment
dc.typeArticle
dc.subject.lemacEnginyeria acústica
dc.subject.lemacMedicina intensiva neonatal
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.identifier.doi10.1109/JTEHM.2017.2781224
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttp://ieeexplore.ieee.org/document/8234562/
dc.rights.accessOpen Access
local.identifier.drac21711201
dc.description.versionPostprint (published version)
local.citation.authorRaboshchuk, G.; Nadeu, C.; Jancovic, P.; Peiro, A.; Kokuer, M.; Muñoz, B.; Riverola, A.
local.citation.publicationNameIEEE Journal of Translational Engineering in Health and Medicine


Fitxers d'aquest items

Thumbnail

Aquest ítem apareix a les col·leccions següents

Mostra el registre d'ítem simple