Our Center has created resources for the rehabilitation research community
Video-Analysis Technology to Analyze your Gait
In our recent publication, we demonstrated that a deep neural network could predict common quantitative gait metrics, such as cadence, walking speed, and the gait deviation index (GDI). Scripts for training machine-learning models and results analysis, and the code used for generating all figures, are available here, and dataset of trajectories of landmarks extracted from videos is available here. You can also demo the software through our web app.
OpenSense for Analyzing Movement with Inertial Measurement Unit Data
OpenSense is an open-source software tool for analyzing movement with inertial measurement unit (IMU) data. It enables users to (i) read and convert IMU sensors data into a single orientation format, (ii) associate and register IMU sensors with body segments of a musculoskeletal model, and (iii) perform inverse kinematics studies to compute joint angles. The OpenSense capabilities are currently available through a graphical user interface (GUI), as well as the command line and through Matlab and Python scripting. Download Software | Example Workflow
Activity Inequality Study Data
In our recent publication, we demonstrated that a deep neural network could predict common quantitative gait metrics, such as Smartphone data from over 68 million days of activity by 717,527 individuals across 111 countries reveal variability in physical activity across the world. The study website provides more details about the research, along with our code and the anonymized, aggregated data used to generate the published figures.
SimTK Repository for Data and Software Sharing
SimTK is a free project-hosting platform for the biomedical computation community with an emphasis on biomechanical and movement-related resources. Example projects related to rehabilitation include:
- Accelerometry data from neurologically-intact, community-dwelling adults and adults with stroke. Data is from Actigraph accelerometers acquired during 1 hour in the lab and 24 hours in the real world
- Wearable IMU sensor data from subjects with Parkinson’s disease. Data is from APDM IMUs for 20 subjects with Parkinson’s disease (some of who experience freezing of gait) and 9 age-matched healthy control subjects as they navigate a turning and barrier course designed to elicit freezing of gait.
Explore other resources on SimTK.