Enhancing Stroke Rehabilitation through a Deep Learning-Enabled Wearable Sensor and a User-Friendly GUI
Session Number
Project ID: CMPS 20
Advisor(s)
Dr. Hongchul Son
Discipline
Computer Science
Start Date
17-4-2024 9:20 AM
End Date
17-4-2024 9:35 AM
Abstract
Stroke rehabilitation faces significant hurdles in providing continuous, real-time care, particularly outside clinical settings. Traditional approaches, while beneficial, are hampered by their intermittent nature and lack of personalized, real-time monitoring. Addressing this gap, this research is the introduction of a wearable sensor technology, designed as a user-friendly bracelet. This device leverages advanced cross-modal deep learning techniques, including variational auto-encoders and training-data augmentation, to offer precise, real-time estimations of joint kinematics, thereby facilitating continuous monitoring and personalized care for stroke survivors.
The sensor's integration with a custom Graphical User Interface (GUI) enables patients and healthcare providers to effortlessly interact with the device, monitor progress, and adjust rehabilitation strategies accordingly. This novel approach not only promises to enhance the accuracy and reliability of patient monitoring outside clinical environments but also aims to significantly improve the quality of life for stroke survivors by ensuring ongoing support and care. The potential societal and economic benefits derived from reducing the impact of stroke-related disabilities further underscore the value of this research. By bridging the existing gaps in stroke rehabilitation, this project paves the way for a new era of patient-centered care, marked by enhanced recovery outcomes and greater accessibility to effective rehabilitation methods.
Enhancing Stroke Rehabilitation through a Deep Learning-Enabled Wearable Sensor and a User-Friendly GUI
Stroke rehabilitation faces significant hurdles in providing continuous, real-time care, particularly outside clinical settings. Traditional approaches, while beneficial, are hampered by their intermittent nature and lack of personalized, real-time monitoring. Addressing this gap, this research is the introduction of a wearable sensor technology, designed as a user-friendly bracelet. This device leverages advanced cross-modal deep learning techniques, including variational auto-encoders and training-data augmentation, to offer precise, real-time estimations of joint kinematics, thereby facilitating continuous monitoring and personalized care for stroke survivors.
The sensor's integration with a custom Graphical User Interface (GUI) enables patients and healthcare providers to effortlessly interact with the device, monitor progress, and adjust rehabilitation strategies accordingly. This novel approach not only promises to enhance the accuracy and reliability of patient monitoring outside clinical environments but also aims to significantly improve the quality of life for stroke survivors by ensuring ongoing support and care. The potential societal and economic benefits derived from reducing the impact of stroke-related disabilities further underscore the value of this research. By bridging the existing gaps in stroke rehabilitation, this project paves the way for a new era of patient-centered care, marked by enhanced recovery outcomes and greater accessibility to effective rehabilitation methods.