Répertoire de publications
de recherche en accès libre
de recherche en accès libre
Abid, Mariem; Ouakrim, Youssef; Mitiche, Amar; Venditolli, Pascal-André; Hagemeister, Nicola et Mezghani, Neila (2021). A comparative study of end-to-end discriminative deep learning models for knee joint kinematic time series classification. Dans Biomedical Signal Processing: Innovation and Applications (p. 33-61). Springer. ISBN 978-3-030-67494-6 https://doi.org/10.1007/978-3-030-67494-6_2
Fichier(s) associé(s) à ce document :![[img]](https://r-libre.teluq.ca/style/images/fileicons/pdf.png)
|
PDF
- Abid2021_2.pdf
Contenu du fichier : Version finale (non publiée) |
|
| Catégorie de document : | Chapitres de livres |
|---|---|
| Évaluation par un comité de lecture : | Oui |
| Étape de publication : | Publié |
| Résumé : | One of the main motivations for classifying knee kinematic signals, which measure flexion/extension, abduction/adduction, and internal/external rotation angle variations during locomotion, is to assist diagnosis of knee joint pathologies. These signals are informative but of high dimensionality and high within-subject variability, serious difficulties which are often referred to as the curse of dimensionality. In general, current machine learning studies of knee pathology classification include feature extraction as an essential component, where feature design is time-consuming and generally not applicable to newly acquired data. To overcome such problems, the purpose of this study is to investigate classification of knee kinematic signals through the entire gait using deep neural networks. The signals are first pre-processed to identify representative patterns of a given subject using the within-subject variability evaluation for outliers’ removal and reliable curves’ selection. The patterns are then used for deep learning of discriminative classifiers. The proposed pre-processing method encompasses steps of gait events detection, normalization, outlier detection, and cycles’ selection. In order to measure the reliability of the subjects’ curves before and after pre-processing, we computed the intraclass correlation (ICC) estimates and their 95% confidence intervals for knee kinematics of a multicentric dataset of 239 subjects: 49 asymptomatic (AS) subjects and 190 knee osteoarthrosis (OA) patients. Then, we describe experiments which support the comparison of five deep neural networks, that have been performed on similar data, to distinguish between asymptomatic (AS) subjects and knee osteoarthrosis (OA) patients and justify further investigation in similar applications. |
| Adresse de la version officielle : | https://link.springer.com/chapter/10.1007/978-3-03... |
| Déposant: | Ayena, Johannes |
| Responsable : | Johannes Ayena |
| Dépôt : | 16 janv. 2023 19:34 |
| Dernière modification : | 16 janv. 2023 19:34 |
|
RÉVISER |
