Device and method for detecting eating activities

• US 9,685,097 B2
• Filed: 06/25/2014
• Issued: 06/20/2017
• Est. Priority Date: 06/25/2013
• Status: Expired due to Fees

• Current Assignee: Clemson University
• Original Assignee: Clemson University
• Inventors: Scisco, Jenna, Hoover, Adam, Muth, Eric, Dong, Yujie
• Primary Examiner(s): Thai, Xuan
• Assistant Examiner(s): SHIRLEY, KRISTEN NICOLE
• Application Number:
  US14/314,160
• Publication Number:
  US 20140377724A1
• Time in Patent Office: 1,091 Days
• Field of Search: 434127, 434236
• CPC Class Codes: G06F 2218/00 Aspects of pattern recognition specially adapted for signal processing
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113
• CPC Class Codes: G09B 19/0092 Nutrition

Abstract

Devices and methods for detecting an eating activity occurrence are provided. A device includes a sensor for monitoring movement of a portion of an arm of a subject, and a processor in communication with the sensor for collecting raw data associated with movement of the portion of the arm. The processor is configured to process the raw data and form processed data. The processed data includes a determination of whether an eating activity has occurred. A method includes sensing movement of a portion of an arm of a subject, and processing raw data associated with the movement of the portion of the arm of the subject to form processed data. The processed data includes a determination of whether an eating activity has occurred.

Claims

1. A device for detecting an eating activity, the device comprising:

one or more sensors for monitoring movement of a portion of a lower arm of a subject; and

a processor in communication with the one or more sensors for collecting raw data associated with the movement of the portion of the lower arm, the processor being configured to process the raw data and thereby determine that an eating activity preparation event has occurred, an eating activity cleanup event has occurred, and an eating activity has occurred between the eating activity preparation event and the eating activity cleanup event and form processed data.

2. The device of claim 1, wherein the one or more sensors comprise an accelerometer, the accelerometer monitoring movement along at least one of an x-, y-, or z-axis.

3. The device of claim 1, wherein the one or more sensors comprise a gyroscope, the gyroscope monitoring movement about at least one of an x-, y-, or z-axis.

4. The device of claim 1, wherein the movement of the portion of the lower arm comprises roll motion of the portion of the lower arm.

5. The device of claim 1, wherein the processor further collects raw data associated with a time at which the movement of the portion of the lower arm occurs.

6. The device of claim 1, wherein the portion of the lower arm is a wrist.

7. The device of claim 1, further comprising a memory for storing the processed data.

8. The device of claim 1, the processor being configured to recognize in the raw data a movement pattern that includes a first period of high motion activity that is associated with the eating activity preparation event, a second period of low motion activity that is associated with the eating event, and a third period of high motion activity that is associated with the eating activity cleanup event.

9. The device of claim 8, the processor being configured to recognize and analyze one or more features during the second period of low motion activity.

10. The device of claim 9, the one or more features comprising one or more of manipulation, linear acceleration, amount of wrist roll motion, and regularity of wrist roll motion.

11. The device of claim 9, the one or more features comprising all of manipulation, linear acceleration, amount of wrist roll motion, and regularity of wrist roll motion.

12. A method for detecting an eating activity occurrence, the method comprising:

mounting one or more sensors on a wearable device, the one or more sensors being configured to sense movement of a portion of a lower arm of a subject wearing the wearable device; and

configuring a processor to process raw data obtained by the sensors and thereby form processed data, the processing comprising determination that an eating activity preparation event has occurred, determination that an eating activity cleanup event has occurred, and determination that an eating activity has occurred between the eating activity preparation event and the eating activity cleanup event.

13. The method of claim 12, the step of processing the raw data comprising pre-processing the raw data to obtain pre-processed data.

14. The method of claim 13, the step of processing the raw data further comprising segmentation of the pre-processed data.

15. The method of claim 14, the segmentation of the pre-processed data comprising:

determining that a motion activity meets a threshold value K at a first time a and that the motion activity is increasing as the threshold value K is passed at time a;

determining that the motion activity meets the threshold value K at a second time b that follows the first time a and that the motion activity is decreasing as the threshold value K is passed at time b;

determining that the motion activity meets the threshold value K at a third time c that follows the second time b and that the motion activity is increasing as the threshold value K is passed at time c; and

determining that the motion activity meets the threshold value K at a fourth time d that follows the third time c and that the motion activity is decreasing as the threshold value K is passed at time d.

16. The method of claim 14, the segmentation of the pre-processed data comprising:

determining a segmented motion energy of the subject by use of the following equation;

17. The method of claim 14, the step of processing the raw data further comprising classification of the pre-processed and segmented data to recognize one or more features of the eating activity.

18. The method of claim 17, the one or more features comprising one or more of manipulation, linear acceleration, amount of wrist roll motion, regularity of wrist roll motion, cumulative time spent eating in a day, cumulative time spent eating during the eating activity, and time since last eating activity.

19. The method of claim 18, the one or more features comprising all of manipulation, linear acceleration, amount of wrist roll motion, and regularity of wrist roll motion.