Gait analysis device and computer program product

Patent metadata

Field	Value
Publication number	US-10765347-B2
Application number	US-201213665081-A
Country	US
Kind code	B2
Filing date	Oct 31, 2012
Priority date	Oct 31, 2011
Publication date	Sep 8, 2020
Grant date	Sep 8, 2020

Abstract

According to an embodiment, a gait analysis device includes a measuring unit configured to measure a subject's motion; a determining unit configured to determine a walking start point in time at which the subject starts walking based on the subject's motion; a feature quantity calculator configured to, when the walking start point in time is determined, calculate a feature quantity of the subject's motion measured during a predetermined time period starting from the walking start point in time as a time period in which the subject's motion is not stabilized; and an estimating unit configured to estimate a subject's walking condition based on the feature quantity.

First claim

What is claimed is:

1. A gait analysis device for observing a walking condition of a subject and preventing the subject from falling, the device comprising:
a hardware processor;
an acceleration sensor; and
a memory for storing processor-executable instructions that, when executed by the processor, cause the processor to control the gait analysis device to at least:
receive acceleration data from the acceleration sensor indicative of acceleration of the subject at or near a waist of the subject;
calculate a variance of the acceleration data in each first setting time period;
determine sequential variances are continuously equal to or less than a threshold value for a second setting timing period or longer, and thereafter the sequential variances continuously exceed the threshold value for a third setting time period or longer, and determine, as a walking start point, a time at which acceleration data corresponding to a last one of the variances equal to or less than the threshold value is obtained, the second setting time period and the third setting time period being both longer than the first setting time period; and
estimate a walking condition and a fall risk of the subject subsequent to the walking start point by at least:
calculating a feature quantity of the received acceleration data of the subject for a transitional time period that starts from the walking start point and calculating a variation based on the feature quantity, the calculated feature quantity including at least an average value of the acceleration data in a horizontal direction orthogonal to a moving direction of the subject for the transitional time period; and
estimating the risk that the subject will fall based on the calculated feature quantity and the calculated variation, the estimating using a pattern recognition algorithm that is based on a learned relationship between class labels indicative of different risk levels and values of the feature quantity and variation based thereon for test subjects while walking.

2. The device according to claim 1 , wherein
the received acceleration data comprises acceleration data, which changes in response to a motion of the subject, in at least one direction.

3. The device according to claim 2 , wherein
the processor-executable instructions further cause the processor to control the gait analysis device to calculate the feature quantity of the received acceleration data until the third setting time period elapses from the walking start point.

4. The device according to claim 3 , wherein
the processor-executable instructions further cause the processor to control the gait analysis device to calculate the feature quantity of the received acceleration data during time periods obtained by sequentially delaying the third setting time period from the walking start point by a certain time interval.

5. The device according to claim 4 , wherein the processor-executable instructions further cause the processor to control the gait analysis device to:
calculate, as the feature quantity, maximum autocorrelation values in an autocorrelation function of the acceleration in the vertical direction during the time periods and average values of the acceleration in the horizontal direction,
calculate at least one of a first variation value and a second variation value, the first variation value being a variation value of the maximum autocorrelation values, and the second variation value being a variation value of the average values, and
estimate the risk that the subject will fall based on at least one of the first variation value and the second variation value, and the feature quantity.

6. The device according to claim 5 , wherein the processor-executable instructions further cause the processor to control the gait analysis device to output at least one of the first variation value, the second variation value, the feature quantity, and an estimate of the risk that the subject will fall.

7. A computer program product comprising a non-transitory computer readable medium including program instructions embodied therein, wherein the instructions, when executed by a computer of a gait analysis device, cause the computer to control the gait analysis device to execute at least:
receiving acceleration data based on sensing at or near a waist of a subject;
calculating a variance of the acceleration data in each first setting time period;
determining sequential variances are continuously equal to or less than a threshold value for a second setting timing period or longer, and thereafter the sequential variances continuously exceed the threshold value for a third setting time period or longer, and determining, as a walking start point, a time at which acceleration data corresponding to a last one of the variances equal to or less than the threshold value is obtained, the second setting time period and the third setting time period being both longer than the first setting time period; and
estimating a walking condition and a fall risk of the subject subsequent to the walking start point by at least:
calculating a feature quantity of the received acceleration data of the subject for a transitional time period that starts from the walking start point and calculating a variation based on the feature quantity, the calculated feature quantity including at least an average value of the acceleration data in a horizontal direction orthogonal to a moving direction of the subject for the transitional time period; and
estimating the risk that the subject will fall based on the calculated feature quantity and the calculated variation, the estimating using a pattern recognition algorithm that is based on a learned relationship between class labels indicative of different risk levels and values of the feature quantity and variation thereof for test subjects while walking.

Assignees

• Toshiba Kk
• Tdk Corp

Inventors

• Fuke Sawa
• Suzuki Takuji
• Cho Kenta

Classifications

• A61B5/1117

  Fall detection · CPC title

• A61B5/6823

  Trunk, e.g., chest, back, abdomen, hip · CPC title

• A61B2562/0219

  Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches · CPC title

• A61B5/112 Primary

  Gait analysis · CPC title