2022
DOI: 10.1007/978-3-031-16452-1_13
|View full text |Cite
|
Sign up to set email alerts
|

GaitForeMer: Self-supervised Pre-training of Transformers via Human Motion Forecasting for Few-Shot Gait Impairment Severity Estimation

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
3
3
1

Relationship

0
7

Authors

Journals

citations
Cited by 15 publications
(3 citation statements)
references
References 20 publications
0
3
0
Order By: Relevance
“…There are few recent developments that have shown the potential of the SSL paradigm in engineering fields (Yengera et al, 2018;Endo et al, 2022;Yu et al, 2022;Shurrab and Duwairi, 2022), and several PHM researchers considered this approach to address the data scarcity in fault diagnostics problems, showing promising results (Hahn and Mechefske, 2021;Ding et al, 2022). However, to date, there is, to the best of the authors' knowledge, only a limited amount of existing research that focuses on the application of SSL to prognostic problems in PHM, for example for RUL estimation on the NASA C-MAPSS 1 dataset (Yoon et al, 2017;Ellefsen et al, 2019;Krokotsch et al, 2022;Guo et al, 2022).…”
Section: Self-supervised Learningmentioning
confidence: 99%
“…There are few recent developments that have shown the potential of the SSL paradigm in engineering fields (Yengera et al, 2018;Endo et al, 2022;Yu et al, 2022;Shurrab and Duwairi, 2022), and several PHM researchers considered this approach to address the data scarcity in fault diagnostics problems, showing promising results (Hahn and Mechefske, 2021;Ding et al, 2022). However, to date, there is, to the best of the authors' knowledge, only a limited amount of existing research that focuses on the application of SSL to prognostic problems in PHM, for example for RUL estimation on the NASA C-MAPSS 1 dataset (Yoon et al, 2017;Ellefsen et al, 2019;Krokotsch et al, 2022;Guo et al, 2022).…”
Section: Self-supervised Learningmentioning
confidence: 99%
“…There are few recent developments that have shown the potential of the SSL paradigm in engineering fields [32][33][34][35], and several PHM researchers considered this approach to address the data scarcity in fault diagnostics problems, showing promising results [36,37]. However, to date, there is, to the best of the authors' knowledge, only a limited amount of existing research that focuses on the application of SSL to prognostic problems in PHM, for example for RUL estimation on the NASA C-MAPSS 1 dataset [39,40,21,22].…”
Section: Self-supervised Learningmentioning
confidence: 99%
“…This study also presents an approach to generate adaptive target/reference trajectories for children with CP, that vary from cycle-to-cycle, and take into account the asymmetry of the left and right joints, since a separate trajectory will be generated for each joint of the left and right sides. A similar approach has been done by Endo et al [37], which train the GaitForMer network based on healthy gait patterns for human motion forecasting, and then retrain the model that learned gait mappings to predict the severity of gait impairment of patients with Parkinson's disease, based on the Movement Disorder Society Unified Parkinson's Disease Rating Scale (MDS-UPDRS).…”
Section: Introductionmentioning
confidence: 99%