A prototype deep learning system for the acoustic monitoring of intensive care patients
| dc.contributor.author | Lykartsis, Athanasios | |
| dc.contributor.author | Hädrich, Markus | |
| dc.contributor.author | Weinzierl, Stefan | |
| dc.date.accessioned | 2022-05-11T10:36:05Z | |
| dc.date.available | 2022-05-11T10:36:05Z | |
| dc.date.issued | 2021-12-08 | |
| dc.description.abstract | We present a prototype system for the acoustic monitoring of artificially ventilated patients in intensive care. A device placed in the patient room detects sounds indicating an emergency situation and notifies a pager of the care staff. The staff can react more quickly and take appropriate action, as well as provide feedback on the prediction for continual learning. A microphone array with adaptive beamforming and an integrated microcomputer is employed, autonomously performing recording, audio preprocessing as well as deep learning based inference. The training dataset originates from a variety of patients and spatial and sonic environments, accommodating for different patterns of background noise and distortions. Mel spectrograms of short length are extracted and used for training a convolutional neural network. An initial evaluation of the system shows an accuracy of 80% for a binary, balanced dataset. The system is deployed in several intensive care facilities and can easily be adapted to other types of medically relevant sounds. | en |
| dc.identifier.eissn | 2076-1465 | |
| dc.identifier.isbn | 978-9-0827-9706-0 | |
| dc.identifier.uri | https://depositonce.tu-berlin.de/handle/11303/16869 | |
| dc.identifier.uri | http://dx.doi.org/10.14279/depositonce-15647 | |
| dc.language.iso | en | en |
| dc.rights.uri | http://rightsstatements.org/vocab/InC/1.0/ | en |
| dc.subject.ddc | 534 Schall und verwandte Schwingungen | de |
| dc.subject.other | acoustic monitoring | en |
| dc.subject.other | beamforming | en |
| dc.subject.other | convolutional neural network | en |
| dc.subject.other | mel spectrograms | en |
| dc.title | A prototype deep learning system for the acoustic monitoring of intensive care patients | en |
| dc.type | Conference Object | en |
| dc.type.version | acceptedVersion | en |
| dcterms.bibliographicCitation.articlenumber | 21482376 | en |
| dcterms.bibliographicCitation.doi | 10.23919/EUSIPCO54536.2021.9616347 | en |
| dcterms.bibliographicCitation.originalpublishername | IEEE | en |
| dcterms.bibliographicCitation.originalpublisherplace | London | en |
| dcterms.bibliographicCitation.proceedingstitle | 29th European Signal Processing Conference (EUSIPCO) | en |
| dcterms.bibliographicCitation.volume | 2021 | en |
| tub.accessrights.dnb | domain | * |
| tub.affiliation | Fak. 1 Geistes- und Bildungswissenschaften::Inst. Sprache und Kommunikation::FG Audiokommunikation | de |
| tub.affiliation.faculty | Fak. 1 Geistes- und Bildungswissenschaften | de |
| tub.affiliation.group | FG Audiokommunikation | de |
| tub.affiliation.institute | Inst. Sprache und Kommunikation | de |
| tub.publisher.universityorinstitution | Technische Universität Berlin | en |