Underwater Biopotential Sensing
Project Description
Swimming and other water-based activities are widely used in sports training, rehabilitation, and personal health. However, understanding how the human body moves and how muscles are activated in aquatic environments remains challenging. Water can affect physiological measurements, introduce substantial motion-related interference, and limit the use of conventional sensing systems. Existing devices may also be intrusive or difficult to deploy without affecting natural movement.
This project will explore sensing and computational methods for analyzing human muscle activity and movement during swimming and other aquatic activities. Possible research components include developing experimental prototypes, collecting synchronized physiological and motion-related data, assessing signal quality, designing signal-processing methods, and applying machine learning to identify meaningful activity patterns.
Depending on the progress of the project and the applicant’s interests, the work may focus on muscle activity analysis, motion and activity recognition, the relationship between movement context and physiological signals, or the integration of multiple sensing modalities. The exact sensing configuration, target activities, experimental scope, and computational methods will be refined during the project.
The long-term objective is to develop practical and low-burden sensing technologies that can support aquatic exercise monitoring, sports performance analysis, and rehabilitation research.
This project will explore sensing and computational methods for analyzing human muscle activity and movement during swimming and other aquatic activities. Possible research components include developing experimental prototypes, collecting synchronized physiological and motion-related data, assessing signal quality, designing signal-processing methods, and applying machine learning to identify meaningful activity patterns.
Depending on the progress of the project and the applicant’s interests, the work may focus on muscle activity analysis, motion and activity recognition, the relationship between movement context and physiological signals, or the integration of multiple sensing modalities. The exact sensing configuration, target activities, experimental scope, and computational methods will be refined during the project.
The long-term objective is to develop practical and low-burden sensing technologies that can support aquatic exercise monitoring, sports performance analysis, and rehabilitation research.
Supervisor
SHAO, Qijia
Quota
2
Course type
UROP1000
UROP1100
UROP2100
UROP3100
UROP3200
UROP4100
Applicant's Roles
The applicant will participate in different stages of the research project. Possible responsibilities include:
Reviewing related work in physiological sensing, electromyography, human movement analysis, and aquatic sensing.
Supporting the design and development of experimental sensing prototypes.
Assisting with pilot studies and controlled data collection in laboratory or aquatic environments.
Organizing, synchronizing, annotating, and assessing the quality of collected sensor data.
Implementing signal-processing methods for noise reduction, segmentation, feature extraction, and pattern analysis.
Developing and evaluating machine-learning models for recognizing muscle activity or movement patterns.
Investigating the robustness of sensing and computational methods across users, activities, and experimental conditions.
Contributing to system evaluation, research documentation, presentations, and potential paper preparation.
The applicant’s specific responsibilities may be adjusted according to their technical background, research interests, and the progress of the project. Students may place greater emphasis on hardware prototyping, signal processing, machine learning, or experimental evaluation.
Reviewing related work in physiological sensing, electromyography, human movement analysis, and aquatic sensing.
Supporting the design and development of experimental sensing prototypes.
Assisting with pilot studies and controlled data collection in laboratory or aquatic environments.
Organizing, synchronizing, annotating, and assessing the quality of collected sensor data.
Implementing signal-processing methods for noise reduction, segmentation, feature extraction, and pattern analysis.
Developing and evaluating machine-learning models for recognizing muscle activity or movement patterns.
Investigating the robustness of sensing and computational methods across users, activities, and experimental conditions.
Contributing to system evaluation, research documentation, presentations, and potential paper preparation.
The applicant’s specific responsibilities may be adjusted according to their technical background, research interests, and the progress of the project. Students may place greater emphasis on hardware prototyping, signal processing, machine learning, or experimental evaluation.
Applicant's Learning Objectives
Develop an understanding of physiological sensing and human movement analysis in aquatic environments.
Gain hands-on experience in designing and evaluating sensing systems.
Learn fundamental methods for physiological and motion-signal processing.
Apply machine-learning techniques to real-world, multimodal sensor data.
Understand how environmental conditions, movement, and sensor placement can influence data quality.
Gain experience in experimental design, human-participant research, data management, and research ethics.
Develop practical skills in hardware–software integration and system evaluation.
Improve scientific communication, technical documentation, teamwork, and presentation skills.
Gain hands-on experience in designing and evaluating sensing systems.
Learn fundamental methods for physiological and motion-signal processing.
Apply machine-learning techniques to real-world, multimodal sensor data.
Understand how environmental conditions, movement, and sensor placement can influence data quality.
Gain experience in experimental design, human-participant research, data management, and research ethics.
Develop practical skills in hardware–software integration and system evaluation.
Improve scientific communication, technical documentation, teamwork, and presentation skills.
Complexity of the project
Moderate