Presentation
30. Enhancing Privacy Protection for Time-Series Signals in Ergonomics Studies via Data Synthesis
SessionPoster Session 2
DescriptionBackground: Electromyography (EMG) signal analysis is crucial for diagnosing work-related musculoskeletal disorders, providing insights into muscle function and fatigue. However, effective analyses require extensive EMG datasets, which are scarce.
Objectives: This study uses diffusion models to synthesize non-identified EMG signals for manual material handling tasks, enhancing data availability for ergonomic studies while maintaining privacy.
Methods: We employed a conditional diffusion model with a residual U-Net architecture, using a dataset of raw EMG data from manual handling tasks. This model synthesizes EMG signals, maintaining fidelity in both spectral and temporal domains.
Findings: The synthesized EMG signals showed high fidelity to the original data, demonstrating the model's effectiveness in replicating key signal characteristics.
Takeaways: Our approach addresses the challenges of data scarcity and privacy in ergonomic research, potentially enriching EMG datasets for occupational health studies and improving ergonomic assessments.
Objectives: This study uses diffusion models to synthesize non-identified EMG signals for manual material handling tasks, enhancing data availability for ergonomic studies while maintaining privacy.
Methods: We employed a conditional diffusion model with a residual U-Net architecture, using a dataset of raw EMG data from manual handling tasks. This model synthesizes EMG signals, maintaining fidelity in both spectral and temporal domains.
Findings: The synthesized EMG signals showed high fidelity to the original data, demonstrating the model's effectiveness in replicating key signal characteristics.
Takeaways: Our approach addresses the challenges of data scarcity and privacy in ergonomic research, potentially enriching EMG datasets for occupational health studies and improving ergonomic assessments.
Event Type
Poster
TimeThursday, September 12th5:30pm - 6:30pm MST
LocationMcArthur Ballroom
Aging
Augmented Cognition
Children's Issues
Communications
Cybersecurity
Education
Environmental Design
General Sessions
Human AI Robot Teaming (AI)
Macroergonomics
Occupational Ergonomics
Student Forum
Surface Transportation
Sustainability
System Development