Utilize este identificador para referenciar este registo:
https://hdl.handle.net/1822/67258
Registo completo
Campo DC | Valor | Idioma |
---|---|---|
dc.contributor.author | Fernandes, Carlos | por |
dc.contributor.author | Fonseca, Luis | por |
dc.contributor.author | Ferreira, Flora | por |
dc.contributor.author | Gago, Miguel | por |
dc.contributor.author | Costa, Luís | por |
dc.contributor.author | Sousa, Nuno | por |
dc.contributor.author | Ferreira, Carlos | por |
dc.contributor.author | Gama, João | por |
dc.contributor.author | Erlhagen, Wolfram | por |
dc.contributor.author | Bicho, Estela | por |
dc.date.accessioned | 2020-10-02T14:15:10Z | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Fernandes, C., Fonseca, L., Ferreira, F., Gago, M., Costa, L., Sousa, N., ... & Bicho, E. (2018, December). Artificial neural networks classification of patients with parkinsonism based on gait. In 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 2024-2030). IEEE | por |
dc.identifier.isbn | 978-1-5386-5487-3 | por |
dc.identifier.issn | 2156-1125 | por |
dc.identifier.uri | https://hdl.handle.net/1822/67258 | - |
dc.description.abstract | Differential diagnosis between Idiopathic Parkin-son's disease (IPD) and Vascular Parkinsonism (VaP) is a difficult task, especially early in the disease. There is growing evidence to support the use of gait assessment in diagnosis and management of movement disorder diseases. The aim of this study is to evaluate the effectiveness of some machine learning strategies in distinguishing IPD and VaP gait. Wearable sensors positioned on both feet were used to acquire the gait data from 15 IPD, 15 VaP, and 15 healthy subjects. A comparative classification analysis was performed by applying two supervised machine learning algorithms: Multiple Layer Perceptrons (MLPs) and Deep Belief Networks (DBNs). The decisional space was composed of the gait variables, with or without neuropsychological evaluation (Montreal cognitive assessment (MoCA) score), top-ranked in an error incremental analysis. In the classification task of characterizing parkinsonian gait by distinguishing between patients (IPD+VaP) and healthy control, from the all strides classification of the gait performed by the person, high accuracy (93% with or without MoCA) was obtained for both algorithms. In the classification task of the two groups of patients (VaP vs. IPD), DBN classifier achieved higher performance (73% with MoCA). To the best of our knowledge, this is the first study on gait classification that includes a VaP group. DBN classifiers are not frequently applied in literature to similar studies, but the results here obtained demonstrate that the use of DBN classifiers based on gait analysis is promising to be a good support to the neurologist in distinguishing VaP and IPD. | por |
dc.description.sponsorship | This work was partially supported by the projects NORTE-01-0145-FEDER-000026 (DeM) and NORTE-01- 0145-FEDER-000016 (NanoSTIMA financed by the Regional Operational Program of the North (NORTE2020), under PORTUGAL2020 and FEDER. | por |
dc.language.iso | eng | por |
dc.publisher | IEEE | por |
dc.rights | restrictedAccess | por |
dc.subject | Multiple Layer Perceptrons | por |
dc.subject | Multiple Layer Perceptrons | por |
dc.subject | Belief Net-works | por |
dc.subject | Idiopathic Parkinson's disease | por |
dc.subject | Vascular Parkinsonism | por |
dc.subject | Walking | por |
dc.subject | Deep Belief Networks | por |
dc.title | Artificial neural networks classification of patients with parkinsonism based on gait | por |
dc.type | conferencePaper | por |
dc.peerreviewed | yes | por |
dc.relation.publisherversion | https://ieeexplore.ieee.org/abstract/document/8621466 | por |
oaire.citationStartPage | 2024 | por |
oaire.citationEndPage | 2030 | por |
oaire.citationConferencePlace | Madrid, Spain | por |
dc.identifier.doi | 10.1109/BIBM.2018.8621466 | por |
dc.date.embargo | 10000-01-01 | - |
dc.identifier.eisbn | 978-1-5386-5488-0 | - |
dc.subject.fos | Ciências Médicas::Outras Ciências Médicas | por |
dc.subject.fos | Ciências Naturais::Ciências da Computação e da Informação | por |
dc.subject.wos | Science & Technology | por |
sdum.journal | IEEE International Conference on Bioinformatics and Biomedicine - BIBM | por |
sdum.conferencePublication | PROCEEDINGS 2018 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM) | por |
Aparece nas coleções: |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
10.1109_bibm.2018.8621466.pdf Acesso restrito! | 170,74 kB | Adobe PDF | Ver/Abrir |