Calculation of minimum ground clearance using body worn sensors
Inventors
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-9524424-B2
Publication Date
2016-12-20
Expiration Date
Abstract
Methods, systems, and apparatus for deriving a relationship between minimum ground clearance (MGC) and inertial sensor data. A regression model may be generated by collecting tri-axial angular velocity and acceleration data from inertial sensors and MGC data from optical motion capture systems during a walking trial. A linear, quadratic, interaction, stepwise interaction, or another regression model may be generated. The regression model may estimate the MGC as a function of one or more parameters measured by or derived from the inertial sensor data. The regression model may be used to calculate an estimate of the MGC based on inertial sensor data collected from one or more individuals.
Core Innovation
The invention assesses falls risk in one or more persons by using one or more inertial sensors and at least one processor. A regression model is generated by collecting reference data during a walking trial in which inertial sensor trial data are measured and reference minimum ground clearance measurements are measured using an optical motion capture system having at least one camera. The generated regression model represents minimum ground clearance parameters as a function of one or more parameters of the motion data from the one or more inertial sensors.
After generating the regression model, subsequent motion data are measured using one or more inertial sensors on a first person while walking. A minimum ground clearance parameter of the first person is calculated using the generated regression model with an input selected from the measured subsequent motion data, and the calculation is performed without use of the optical motion capture system. A value indicative of a risk of fall, or risk of falling, for the first person is then generated based on the calculated minimum ground clearance parameter.
The approach is implemented as a method, a system, and a non-transitory computer-readable medium configured to perform the same regression-model-based falls-risk assessment. The system includes one or more inertial sensors mounted on a body of a first person and a processor configured to collect reference data, generate the regression model, perform subsequent inertial-only calculation, and generate the value indicative of a risk of falling.
Claims Coverage
The document provides three independent claims, covering a method, a non-transitory computer-readable medium, and a system for assessing falls risk. Across the independent claims, the core inventive structure is the regression model that maps inertial motion parameters to minimum ground clearance parameters and is used to generate a value indicative of falls risk without optical motion capture for subsequent measurements.
Regression model for minimum ground clearance from inertial motion
Generating a regression model using measured inertial sensor trial data and measured reference minimum ground clearance measurements, wherein the regression model represents minimum ground clearance parameters as a function of one or more parameters of the motion data from the one or more inertial sensors.
Inertial-only calculation of minimum ground clearance for subsequent walking
After generating the regression model, measuring subsequent motion data using one or more inertial sensors on a first person while walking and calculating, using the generated regression model, a minimum ground clearance parameter of the first person, wherein an input to the generated regression model comprises parameters selected from the measured subsequent motion data of the first person and wherein the calculation is performed without use of the optical motion capture system.
Risk value generated from calculated minimum ground clearance
Generating, using the processor, a value indicative of a risk of fall or risk of falling for the first person based on the calculated minimum ground clearance parameter.
Non-transitory computer-readable medium performing the regression-model falls-risk assessment
A non-transitory computer-readable medium comprising one or more instructions that, when executed, cause one or more processors to collect reference data, generate the regression model, measure subsequent motion data with inertial sensors, calculate a minimum ground clearance parameter without use of the optical motion capture system, and generate a value indicative of a risk of fall.
System with inertial sensors and processor for regression-model falls-risk assessment
A system comprising one or more inertial sensors mounted on a body of a first person configured to measure motion data, and a processor configured to collect reference data, generate the regression model, measure subsequent motion data, calculate a minimum ground clearance parameter without use of the optical motion capture system, and generate a value indicative of a risk of falling.
Overall, claim coverage centers on training a regression model from paired inertial sensor trial data and optical minimum ground clearance reference measurements, then using the trained regression model with subsequent inertial-only motion data to compute a minimum ground clearance parameter and generate a value indicative of falls risk. The independent claims extend this structure to a non-transitory computer-readable medium and a system architecture with mounted inertial sensors and a processor.
Stated Advantages
Allows calculation of minimum ground clearance parameters and a value indicative of falls risk without use of the optical motion capture system after the regression model is generated.
Generates a falls-risk indicator based on a calculated minimum ground clearance parameter derived from inertial sensor motion data.
Documented Applications
Falls risk assessment for one or more persons during walking by using an inertial-sensor-based regression model tied to minimum ground clearance measurements measured during reference collection with an optical motion capture system.
Interested in licensing this patent?