Apparatus, system, and method for automatic identification of sensor placement

Patent metadata

Field	Value
Publication number	US-9891701-B2
Application number	US-201214002665-A
Country	US
Kind code	B2
Filing date	Mar 2, 2012
Priority date	Mar 2, 2011
Publication date	Feb 13, 2018
Grant date	Feb 13, 2018

Abstract

A location of a sensor is determined by: (1) receiving time series data including components in a plurality of dimensions, wherein the time series data correspond to measurements of the sensor that is applied to a subject; (2) determining a plurality of subsequences associated with the time series data, wherein each of the plurality of subsequences represents a characteristic pattern projected along one of the plurality of dimensions; (3) identifying a correlated subset of the plurality of subsequences as at least one instance of an activity of the subject; and (4) based on features of the correlated subset, determining the location of the sensor as applied to the subject.

First claim

What is claimed is:

1. A non-transitory computer-readable storage medium, comprising executable instructions to:
receive time series data including components in a plurality of dimensions, wherein the time series data correspond to measurements of a sensor that has been applied to a subject;
determine a plurality of subsequences associated with the time series data, wherein each of the plurality of subsequences represents a characteristic pattern projected along one of the plurality of dimensions;
identify a correlated subset of the plurality of subsequences as at least one instance of an activity of the subject; and
based on features of the correlated subset, determine a location of where the sensor has been applied to the subject,
wherein the executable instructions to determine the plurality of subsequences include executable instructions to:
determine at least one subsequence as disposed between two consecutive stable regions in the time series data.

2. The non-transitory computer-readable storage medium of claim 1 , wherein the executable instructions to identify the correlated subset include executable instructions to:
perform graph clustering on vertices corresponding to the plurality of subsequences.

3. The non-transitory computer-readable storage medium of claim 2 , wherein the executable instructions to perform the graph clustering include executable instructions to:
assign weights to the vertices based on a degree of temporal overlap of respective pairs of the vertices.

4. The non-transitory computer-readable storage medium of claim 1 , wherein the activity corresponds to walking, and the correlated subset corresponds to walking subsequences.

5. The non-transitory computer-readable storage medium of claim 1 , wherein the executable instructions to determine the location of the sensor include executable instructions to:
derive at least one feature based on a frequency domain representation of the correlated sub set.

6. The non-transitory computer-readable storage medium of claim 1 , wherein the executable instructions to determine the location of the sensor include executable instructions to:
derive at least one feature based on a time domain representation of the correlated subset.

7. The non-transitory computer-readable storage medium of claim 1 , wherein the features of the correlated subset are indicative of at least one of a stride impact, a motion range, or a degree of freedom.

8. The non-transitory computer-readable storage medium of claim 1 , wherein the executable instructions to determine the location of the sensor include executable instructions to:
identify a body part of the subject to which the sensor is applied.

9. The non-transitory computer-readable storage medium of claim 1 , further comprising executable instructions to:
calibrate the measurements of the sensor based on the location of the sensor.

10. The non-transitory computer-readable storage medium of claim 1 , further comprising executable instructions to:
control operation of the sensor based on the location of the sensor.

11. A system for sensor localization, comprising:
a processing unit; and
a memory connected to the processing unit and including executable instructions to:
identify a portion of a multi-dimensional time series as at least one instance of physical movement of a subject, wherein the multi-dimensional time series correspond to measurements of a sensor that has been applied to the subject;
selectively process the portion of the multi-dimensional time series to derive a set of features associated with the physical movement; and
based on the set features, determine a location of where the sensor has been applied to the subject,

wherein the executable instructions to identify the portion of the multi-dimensional time series include executable instructions to:
determine, within the portion of the multi-dimensional time series, at least one subsequence as disposed between two consecutive stable regions in the multi-dimensional time series.

12. The system of claim 11 , wherein the executable instructions to identify the portion of the multi-dimensional time series include executable instructions to:
identify, within the portion of the multi-dimensional time series, a set of subsequences that are correlated in time.

13. The system of claim 11 , wherein the executable instructions to selectively process the portion of the multi-dimensional time series include executable instructions to derive at least one of:
an accumulated value associated with the portion of the multi-dimensional time series; and
a maximum value associated with the portion of the multi-dimensional time series.

14. The system of claim 11 , wherein the executable instructions to determine the location of the sensor include executable instructions to:
perform a supervised classification to assign a region of the subject as corresponding to the set of features.

15. The system of claim 11 , wherein the sensor corresponds to an accelerometer, and the multi-dimensional time series correspond to acceleration data in a plurality of dimensions.

16. The system of claim 11 , wherein the memory further includes executable instructions to:
control operation of the sensor based on the location of the sensor.

17. The system of claim 11 , wherein the memory further includes executable instructions to:
calibrate the measurements of the sensor based on the location of the sensor.

Assignees

• Sarrafzadeh Majid
• Nahapetian Ani
• Vahdatpour Alireza
• Rofouei Mahsan
• Univ California

Inventors

• Sarrafzadeh Majid
• Nahapetian Ani
• Vahdatpour Alireza
• Rofouei Mahsan

Classifications

• G06F3/011 Primary

  Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00) · CPC title

• A61B5/1112 Primary

  Global tracking of patients, e.g. by using GPS · CPC title

• G01C22/006

  Pedometers · CPC title