METHOD AND SYSTEM FOR RECOGNIZING DAILY ACTIVITIES USING SENSORS

• US 20090051524A1
• Filed: 04/08/2008
• Published: 02/26/2009
• Est. Priority Date: 08/20/2007
• Status: Active Grant

• Current Assignee: Electronics and Telecommunications Research Institute
• Original Assignee: Electronics and Telecommunications Research Institute
• Inventors: Park, Seon Hee, Park, Soo Jun, Jang, Jae Won, Lim, Joon Ho, Song, Sa Kwang, Jang, Hyun Chul
• Granted Patent: US 7,843,323 B2
• Time in Patent Office: Days
• US Class Current: 340/501
• CPC Class Codes: A61B 5/00 Measuring for diagnostic purposes radiation diagnosis A61B6/00; diagnosis by ultrasonic, sonic or infrasonic waves A61B8/00; Identification of persons
• CPC Class Codes: A61B 5/0002 Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network A61B5/07 takes precedence; transmission systems for measured values G08C; transmission H04B; transmission of digital information H04L; wireless communication networks H04W
• CPC Class Codes: A61B 5/6887 mounted on external non-worn devices, e.g. non-medical devices
• CPC Class Codes: G08B 21/0423 detecting deviation from an expected pattern of behaviour or schedule

Abstract

There is provided a daily activity recognition system using sensors installed in required positions in a home to recognize daily activities of an old person, the system including: a radio frequency (RF) management unit receiving data measured by a plurality of sensors installed in required positions in a home, recognizing a corresponding sensor transmitting the received data, and converting the received data into a basic activity corresponding to the recognized sensor; a buffer management unit storing the basic activity received from the wireless processing manager in an internal buffer; and a daily activity recognition unit recognizing daily activities of an old person at each point in time previously set, based on the basic activity stored in the buffer. The daily activities of the old person are recognized and stored in a database, thereby providing various services related to the health of the old person.

Claims

1. A daily activity recognition system using sensors, the system comprising:

a radio frequency (RF) management unit receiving data measured by a plurality of sensors installed in required positions in a home, recognizing a corresponding sensor transmitting the received data, and converting the received data into a basic activity corresponding to the recognized sensor;

a buffer management unit storing the basic activity received from the wireless processing manager in an internal buffer; and

a daily activity recognition unit recognizing daily activities of an old person at each point in time previously set, based on the basic activity stored in the buffer.

2. The system of claim 1, further comprising a daily activity recording unit receiving the daily activities recognized by the daily activity recognizer and recoding the received daily activity in a database.

3. The system of claim 1, wherein the RF management unit compares the converted basic activity with a previous basic activity and transmits the converted basic activity together with a present time when the converted basic activity is different from the previous basic activity.

4. The system of claim 3, wherein the converted basic activity comprises one or more of a table-based activity, a bed-based activity, a sofa-based activity, and a first toilet-based activity, a second lever-based activity, a first go-out-based activity, and a second come-in-based activity.

5. The system of claim 1, wherein the daily activity recognition unit comprises:

a candidate daily activity recognizer checking contents of the basic activities stored in the buffer management unit for each point in time previously set and extracting candidate daily activities by using the checked contents; and

a plurality of daily activity recognizers recognizing the daily activities of the old person, corresponding to the basic activities included in the extracted candidate daily activities.

6. The system of claim 5, wherein the plurality of daily activity recognizers comprise:

a meal recognizer recognizing a meal activity based on the table-based activity when the table-based activity is present in the extracted candidate daily activities;

a sleep recognizer recognizing a sleep activity based on the bed-based activity when the bed-based activity is present in the extracted candidate daily activities;

a rest recognizer recognizing a rest activity based on the sofa-based activity when the sofa-based activity is present in the extracted candidate daily activities;

an excretion recognizer recognizing an excretion activity based on the first toilet-based activity and the second lever-based activity when the first toilet-based activity and the second lever-based activity are present in the extracted candidate daily activities; and

a go-out recognizer recognizing a go-out activity based on the first go-out-based activity and the second come-in-based activity when the first go-out-based activity and the second come-in-based activity are present in the extracted candidate daily activities.

7. The system of claim 6, wherein the meal recognizer estimates a probability value based on a reference meal time and a meal-maintenance time and recognizes as the meal activity when the estimated probability value is greater than a preset threshold value.

8. The system of claim 6, wherein the sleep recognizer estimates a probability value based on a reference sleep time and a sleep-maintenance time and recognizes as the sleep activity when the estimated probability value is greater than a preset threshold value.

9. The system of claim 6, wherein the rest recognizer calculates a maintenance time comprising a break for a short time within the sofa-based activity and recognizes a start point in time and an end point in time as the rest activity when the calculated maintenance time is greater than a preset threshold time.

10. The system of claim 6, wherein the excretion recognizer recognizes an amount of time from a point in time when the first toilet-based activity occurs to a point in time when the second lever-based activity starts, as the excretion activity.

11. The system of claim 10, wherein the excretion recognizer does not recognizes as the excretion activity when the first toilet-based activity occurs and the second lever-based activity does not occur.

12. The system of claim 6, wherein the go-out recognizer, when a time interval between the first go-out-based activity and the second come-in-based activity is greater than a preset threshold time, recognizes an amount of time from a point in time when the first go-out activity to a point in time when the second come-in activity starts, as the go-out activity.

13. A method of recognizing daily activities of an old person in a daily activity recognition system, the method comprising:

receiving data measured by a plurality of sensors installed in required positions in a home in real time;

recognizing a corresponding sensor transmitting the received data and converting the received data into a basic activity corresponding to the recognized sensor;

storing the received basic activity received from a radio frequency (RF) management unit, in an internal buffer;

recognizing the daily activities of the old person based on the basic activity stored in the buffer for each present point in time; and

storing the recognized daily activities in a database.

14. The method of claim 13, wherein the recognizing the daily activities of the old person for each preset point in time comprises:

checking contents of the basic activity stored in the buffer, for the each preset point in time;

extracting candidate daily activities by using the checked contents; and

recognizing each of the daily activities of the old person, corresponding to a basic activity included in the extracted candidate daily activities.

15. The method of claim 14, wherein the recognizing each of the daily activities of the old person comprises:

recognizing a meal activity based on a table-based activity when the table-based activity is present in the extracted candidate daily activities;

recognizing a sleep activity based on a bed-based activity when the bed-based activity is present in the extracted candidate daily activities;

recognizing a rest activity based on a sofa-based activity when the sofa-based activity is present in the extracted candidate daily activities;

recognizing an excretion activity based on a first toilet-based activity and a second lever-based activity when the first toilet-based activity and the second lever-based activity are present in the extracted candidate daily activities; and

recognizing a go-out activity based on a first go-out-based activity and a second come-in-based activity when the first go-out-based activity and the second come-in-based activity are present in the extracted candidate daily activities.

16. The method of claim 15, wherein the recognizing a meal activity comprises:

estimating a probability value based on a reference time and a maintenance time with respect to a meal;

comparing the estimated probability value with a preset threshold value; and

recognizing as the meal activity when the estimated probability value is greater than the threshold value.

17. The method of claim 15, wherein the recognizing a sleep activity comprises:

estimating a probability value based on a reference time and a maintenance time with respect to a sleep;

comparing the estimated probability value with a preset threshold value; and

recognizing as the sleep activity when the probability value is greater than the threshold value.

18. The method of claim 15, wherein the recognizing a rest activity comprises:

calculating a maintenance time including a break for a short time within the sofa-based activity;

comparing the calculated maintenance time with a preset threshold time; and

recognizing an amount of time from a point in time when the maintenance time starts and a point in time when the maintenance time is finished, when the maintenance time is greater than the threshold time.

19. The method of claim 15, wherein the recognizing an excretion activity comprises:

checking whether the second lever-based activity occurs;

recognizing an amount of time from a point in time when the first toilet-based activity starts to a point in time when the second lever-based activity starts, when the second lever-based activity occurs; and

recognizing as the excretion activity does not occur, when the second lever-based activity does not occur.

20. The method of claim 15, wherein the recognizing a go-out activity comprises:

obtaining a time interval between the first go-out-based activity and the second come-in-based activity;

comparing the obtained time interval with a preset threshold time; and

recognizing an amount of time from a point in time when the first go-out-based activity starts to a point in time when the second come-in-based activity starts, as the go-out activity, when the time interval is greater than the threshold time.