Hui Chen, Xiangyang Wang, Yang Xiao, Beixian Wu, Zhuo Wang, Yao Liu, Peiyi Wang, Chunjie Chen, Xinyu Wu
{"title":"iP3T: an interpretable multimodal time-series model for enhanced gait phase prediction in wearable exoskeletons","authors":"Hui Chen, Xiangyang Wang, Yang Xiao, Beixian Wu, Zhuo Wang, Yao Liu, Peiyi Wang, Chunjie Chen, Xinyu Wu","doi":"10.3389/fnins.2024.1457623","DOIUrl":null,"url":null,"abstract":"IntroductionWearable exoskeletons assist individuals with mobility impairments, enhancing their gait and quality of life. This study presents the iP3T model, designed to optimize gait phase prediction through the fusion of multimodal time-series data.MethodsThe iP3T model integrates data from stretch sensors, inertial measurement units (IMUs), and surface electromyography (sEMG) to capture comprehensive biomechanical and neuromuscular signals. The model's architecture leverages transformer-based attention mechanisms to prioritize crucial data points. A series of experiments were conducted on a treadmill with five participants to validate the model's performance.ResultsThe iP3T model consistently outperformed traditional single-modality approaches. In the post-stance phase, the model achieved an RMSE of 1.073 and an R<jats:sup>2</jats:sup> of 0.985. The integration of multimodal data enhanced prediction accuracy and reduced metabolic cost during assisted treadmill walking.DiscussionThe study highlights the critical role of each sensor type in providing a holistic understanding of the gait cycle. The attention mechanisms within the iP3T model contribute to its interpretability, allowing for effective optimization of sensor configurations and ultimately improving mobility and quality of life for individuals with gait impairments.","PeriodicalId":12639,"journal":{"name":"Frontiers in Neuroscience","volume":"58 1","pages":""},"PeriodicalIF":3.2000,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Neuroscience","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3389/fnins.2024.1457623","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"NEUROSCIENCES","Score":null,"Total":0}
引用次数: 0
Abstract
IntroductionWearable exoskeletons assist individuals with mobility impairments, enhancing their gait and quality of life. This study presents the iP3T model, designed to optimize gait phase prediction through the fusion of multimodal time-series data.MethodsThe iP3T model integrates data from stretch sensors, inertial measurement units (IMUs), and surface electromyography (sEMG) to capture comprehensive biomechanical and neuromuscular signals. The model's architecture leverages transformer-based attention mechanisms to prioritize crucial data points. A series of experiments were conducted on a treadmill with five participants to validate the model's performance.ResultsThe iP3T model consistently outperformed traditional single-modality approaches. In the post-stance phase, the model achieved an RMSE of 1.073 and an R2 of 0.985. The integration of multimodal data enhanced prediction accuracy and reduced metabolic cost during assisted treadmill walking.DiscussionThe study highlights the critical role of each sensor type in providing a holistic understanding of the gait cycle. The attention mechanisms within the iP3T model contribute to its interpretability, allowing for effective optimization of sensor configurations and ultimately improving mobility and quality of life for individuals with gait impairments.
期刊介绍:
Neural Technology is devoted to the convergence between neurobiology and quantum-, nano- and micro-sciences. In our vision, this interdisciplinary approach should go beyond the technological development of sophisticated methods and should contribute in generating a genuine change in our discipline.