An Inception-Based Architecture for Haemodialysis Time Series Classification

Risultato della ricerca: Capitolo in libro/report/atti di convegnoContributo a conferenzapeer review

Abstract

Classifying haemodialysis sessions, on the basis of the evolution of specific clinical variables over time, allows the physician to identify patients that are being treated inefficiently, and that may need additional monitoring or corrective interventions. In this paper, we propose a deep learning approach to clinical time series classification, in the haemodialysis domain. Specifically, grounding on our previous experience in adopting convolutional neural networks on haemodialysis time series, we have defined an inception-based architecture, able to exploit kernels of different sizes in parallel. The proposed architecture has outperformed the results obtained by resorting both to a more standard convolutional neural network, and to the state of the art approach ROCKET, since we reached higher accuracy values, coupled with a good Matthews Correlation Coefficient.

Lingua originaleInglese
Titolo della pubblicazione ospiteArtificial Intelligence Applications and Innovations. AIAI 2021 IFIP WG 12.5 International Workshops - 5G-PINE 2021, AI-BIO 2021, DAAI 2021, DARE 2021, EEAI 2021, and MHDW 2021, Proceedings
EditorIlias Maglogiannis, John Macintyre, Lazaros Iliadis
EditoreSpringer Science and Business Media Deutschland GmbH
Pagine194-203
Numero di pagine10
ISBN (stampa)9783030791568
DOI
Stato di pubblicazionePubblicato - 2021
Evento17th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2021, 6th Workshop on 5G-Putting Intelligence to the Network Edge, 5G-PINE 2021, Artificial Intelligence in Biomedical Engineering and Informatics Workshop, AI-BIO 2021, Workshop on Defense Applications of AI, DAAI 2021, Distributed AI for Resource-Constrained Platforms Workshop, DARE 2021, Energy Efficiency and Artificial Intelligence Workshop, EEAI 2021, and 10th Mining Humanistic Data Workshop, MHDW 2021 - Virtual, Online
Durata: 25 giu 202127 giu 2021

Serie di pubblicazioni

NomeIFIP Advances in Information and Communication Technology
Volume628
ISSN (stampa)1868-4238
ISSN (elettronico)1868-422X

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???17th IFIP WG 12.5 International Conference on Artificial Intelligence Applications and Innovations, AIAI 2021, 6th Workshop on 5G-Putting Intelligence to the Network Edge, 5G-PINE 2021, Artificial Intelligence in Biomedical Engineering and Informatics Workshop, AI-BIO 2021, Workshop on Defense Applications of AI, DAAI 2021, Distributed AI for Resource-Constrained Platforms Workshop, DARE 2021, Energy Efficiency and Artificial Intelligence Workshop, EEAI 2021, and 10th Mining Humanistic Data Workshop, MHDW 2021
CittàVirtual, Online
Periodo25/06/2127/06/21

Fingerprint

Entra nei temi di ricerca di 'An Inception-Based Architecture for Haemodialysis Time Series Classification'. Insieme formano una fingerprint unica.

Cita questo