Personalized Gait Trajectory Prediction of Hemiplegic Patients Based on Transfer Learning

Exoskeleton robots serve as crucial tools for active rehabilitation training among patients with lower limb motor dysfunction. Accurately recognizing human motion intention poses a significant challenge for exoskeleton robots, which can be addressed by continuously estimating human joint angles. Nev...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE sensors journal Ročník 25; číslo 16; s. 30970 - 30983
Hlavní autoři: Zhao, Yan, Li, Jiayi, Zhang, Jianhua, Li, Kexiang, Wang, Dan, Li, Hui, Zhang, Jianjun
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York IEEE 15.08.2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Data models
Deep learning (DL)
Electromyography
Exoskeletons
Feature extraction
Gait
gait trajectory prediction
Human motion
Limbs
Machine learning
Muscles
Prediction models
Predictive models
Principal components analysis
Robot dynamics
Sensors
surface electromyography (sEMG)
Training
Trajectories
Trajectory
Transfer learning
transfer learning (TL)
ISSN:1530-437X, 1558-1748
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Exoskeleton robots serve as crucial tools for active rehabilitation training among patients with lower limb motor dysfunction. Accurately recognizing human motion intention poses a significant challenge for exoskeleton robots, which can be addressed by continuously estimating human joint angles. Nevertheless, most existing studies primarily focus on healthy subjects, neglecting the target audience of lower limb exoskeletons, namely, patients with lower limb hemiplegia. This article proposed a general model utilizing a transfer learning (TL) strategy to predict the gait trajectory of hemiplegic patients. First, a gait dataset is established featuring hemiplegic patients walking on level ground. The original surface electromyography (sEMG) signal sequence is then decomposed using the empirical mode decomposition (EMD) algorithm to mitigate noise and nonstationarity inherent in the data signals. Second, kernel principal component analysis (KPCA) is employed to extract key features from the sEMG signal sequence, eliminating redundant information from the original sequence. Third, considering the impact of spatio-temporal correlation in gait data on prediction accuracy, a prediction model based on CNN-BiLSTM is devised. Finally, TL technology is applied between the healthy and affected sides of the subject to transfer knowledge learned from the source domain data to the target domain. This method enhanced the accuracy of gait trajectory prediction for hemiplegic patients, alleviated the training burden, and bolstered the model's generalization. The findings indicated that this TL strategy holds significant application value for advancing the development of lower limb exoskeleton control systems.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2025.3576709