Wearable device

• US 8,021,297 B2
• Filed: 06/24/2005
• Issued: 09/20/2011
• Est. Priority Date: 07/07/2004
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips Electronics N.V. (Koninklijke Philips N.V.)
• Inventors: Aerts, Steven G. E.
• Primary Examiner(s): Yao; Sam
• Assistant Examiner(s): Rajan; Kai
• Application Number:
  US11/571,540
• Publication Number:
  US 20070161874A1
• Time in Patent Office: 2,279 Days
• Field of Search: 600/300, 600/301, 128903-905, 128/920
• US Class Current: 600/300
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/02438 with portable devices, e.g. worn by the patient
• CPC Class Codes: A61B 5/1112 Global tracking of patients, e.g. by using GPS
• CPC Class Codes: A61B 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: A61B 5/222 combined with detection or measurement of physiological parameters, e.g. heart rate
• CPC Class Codes: A61B 5/6801 specially adapted to be attached to or worn on the body surface

Abstract

A wearable device comprising at least two measuring devices (2,3,4,5,6) providing primary data, a processor (1) designed for calculating secondary data from the primary data, for calculating reference data from the primary and/or the secondary data and for comparing the reference data with at least two specific data pattern to automatically recognize an activity, and a memory (7) designed for storing the primary, the secondary data and the at least two specific data pattern each assigned to a certain activity. The activity recognition is performed by loading the primary and/or the secondary data to the processor (1), calculating the reference data, comparing the reference data with the specific data patterns, assigning the primary and/or the secondary data with the recognized activity and storing the assigned primary and/or secondary data in the memory (7).

Claims

1. A wearable device comprising:

at least two measuring devices that provide primary data,

a processor programmed to;

calculate secondary data from the primary data,

calculate reference data from the primary and/or secondary data, and

compare the reference data with at least two specific data patterns, each data pattern corresponding to a predefined activity such that the comparing of the reference data to the data patterns automatically recognizes the corresponding predefined activity, the predefined activities including at least three of;

jogging and the specific data pattern assigned to jogging comprises a heart rate with variations over jogging time intervals, a velocity varying between 7 km/h and 25 km/h, a periodic vertical acceleration and a constant step frequency,

cycling and the specific data pattern assigned to cycling comprises a heart rate unvarying within cycling time intervals, a velocity varying between 10 km/h and 90 km/h, a discrete horizontal acceleration, and no step frequency,

a water sport and the specific data pattern assigned to the water sport comprises a heart rate with variations over a water sport variation range and water sport time intervals, a velocity below 20 km/h, periodic accelerations, above normal skin humidity, and no step frequency,

a ball game and the specific data pattern assigned to the ball game comprises a varying heart rate, a velocity varying between 0 km/h and 30 km/h, a varying horizontal and vertical acceleration during defined ball game time intervals, a strongly varying step frequency, and

a fitness sport and the specific data pattern assigned to the fitness sport comprises a heart rate with first variations within a first fitness sport variation range and first fitness sport time intervals, a velocity below 5 km/h, a periodically varying horizontal and vertical acceleration during a second fitness sport time interval range and a varying step frequency within a second fitness sport variation during the second fitness sport time intervals; and

a memory that stores the primary data, the secondary data and the at least two specific data patterns.

2. The wearable device according to claim 1, in which the primary and/or the secondary data correspond to at least two data classes selected from the group consisting of heart rate, respiration, heat flux, body-temperature, bioelectric impedance, oxygen intake, calorie expenditure, step frequency, GPS signals, environmental temperature, vertical and horizontal acceleration, time, time intervals, velocity, and humidity.

3. The wearable device according to claim 1, in which in response to the reference data not corresponding to one of the predefined activities, the processor is programmed to query a user to request the user to define a new activity.

4. The wearable device according to claim 1, in which the predefined activities include at least

the water sport and the specific data pattern assigned to the water sport comprises a heart rate with variations over a water sport variation range and a water sport time interval range, a velocity below 20 km/h, periodic accelerations, above normal skin humidity, and no step frequency.

5. The wearable device according to claim 1, in which the predefined activities include at least two of:

the water sport and the specific data pattern assigned to the water sport comprises a heart rate with variations over a water sport variation range and a water sport time interval range, a velocity below 20 km/h, periodic accelerations, above normal skin humidity, and no step frequency,

the ball game and the specific data pattern assigned to the ball game comprises a varying heart rate, a velocity varying between 0 km/h and 30 km/h, a varying horizontal and vertical acceleration during defined ball game time intervals, a strongly varying step frequency, and

the fitness sport and the specific data pattern assigned to the fitness, sport comprises a heart rate with first variations within a first fitness sport variation range and a first fitness sport time interval range, a velocity below 5 km/h, a periodically varying horizontal and vertical acceleration during a second fitness sport time interval range and a varying step frequency within a second fitness sport variation range during the second fitness sport time interval range.

6. The wearable device according to claim 1, in which the predefined activities include at least four of:

jogging and the specific data pattern assigned to jogging comprises a heart rate with variations over a jogging time interval range, a velocity varying between 7 km/h and 25 km/h, a periodic vertical acceleration and a constant step frequency,

cycling and the specific data pattern assigned to cycling comprises a heart rate unvarying within a cycling time interval range, a velocity varying between 10 km/h and 90 km/h, a discrete horizontal acceleration, and no step frequency,

a water sport and the specific data pattern assigned to the water sport comprises a heart rate with variations over a water sport variation range and a water sport time interval range, a velocity below 20 km/h, periodic accelerations, above normal skin humidity, and no step frequency,

a ball game and the specific data pattern assigned to the ball game comprises a varying heart rate, a velocity varying between 0 km/h and 30 km/h, a varying horizontal and vertical acceleration during defined ball game time intervals, a strongly varying step frequency, and

a fitness sport and the specific data pattern assigned to the fitness sport comprises a heart rate with first variations within a first fitness sport variation range and a first fitness sport time interval range, a velocity below 5 km/h, a periodically varying horizontal and vertical acceleration during a second fitness sport time interval range and a varying step frequency within a second fitness sport variation range during the second fitness sport time interval range.

7. A wearable device comprising:

at least two measuring devices providing primary data,

a memory which stores the primary data, secondary data and data patterns which identify previously defined activities, wherein the predefined activities include at least a water sport and the specific data pattern assigned to the water sport comprises a heart rate with variations over a water sport variation range and a water sport time interval range, a velocity below 20 km/h, periodic accelerations, above normal skin humidity, and no step frequency;

a processor programmed to;

calculate the secondary data from the primary data,

calculate reference data from the primary and/or secondary data,

compare the reference data with the stored data patterns which identify the previously defined activities to automatically recognize a currently measured activity,

in response to failing to recognize the current activity, generate a request for a definition of the unrecognized current activity,

send the request to a user to define the unrecognized current activity, and

in response to receiving the definition of the unrecognized activity from the user, causing the memory to store the data pattern of the current activity definition;

a user interface which displays the request for the definition of the unidentified current activity and via which the user inputs the definition of the unrecognized current activity.

8. The wearable device according to claim 7, in which the data patterns include upper and lower limits for each defined activity.

9. The wearable device according to claim 8, in which the processor is further programmed to:

analyze the primary data and/or the secondary data stored in the memory in association with at least one of the defined activities;

change at least one of upper and lower limits for the at least one of the defined activities in response to the analysis.

10. The wearable device according to claim 7, in which the processor calculates data patterns corresponding to activities defined by the user.

11. The wearable device according to claim 7, further comprising a computer interface which exchanges or adds data and/or specific data patterns assigned to additional activities.

12. An activity recognition method for a wearable device, wherein a processor performs the steps of

measuring primary data as a function of time,

calculating secondary data from the primary data,

storing the primary and/or the secondary data as a function of time,

loading the primary and/or the secondary data and a plurality of data patterns each corresponding to one of a plurality of predefined activities from a memory in communication with the processor, wherein the data patterns corresponding to at least one of the predefined activities have upper and lower limits and wherein the predefined activities include at least one of:

a water sport and the specific data pattern assigned to the water sport comprises a heart rate with variations over a water sport variation range and a water sport time interval range, a velocity below 20 km/h, periodic accelerations, above normal skin humidity, and no step frequency,

a ball game and the specific data pattern assigned to the ball game comprises a varying heart rate, a velocity varying between 0 km/h and 30 km/h, a varying horizontal and vertical acceleration during defined ball game time intervals, a strongly varying step frequency, and

a fitness sport and the specific data pattern assigned to the fitness sport comprises a heart rate with first variations within a first fitness sport variation range and a first fitness sport time interval range, a velocity below 5 km/h, a periodically varying horizontal and vertical acceleration during a second fitness sport time interval range and a varying step frequency within a second fitness sport variation range during the second fitness sport time interval range,

calculating reference data from the primary and/or secondary data,

comparing the reference data with the data patterns to automatically recognize a corresponding one of the predefined activities,

assigning the primary and/or the secondary data with the recognized predefined activity,

storing the assigned data with the recognized predefined activity in the memory,

analysing the assigned data corresponding to one of the predefined activities,

modifying the data pattern corresponding to the recognized predefined activity according to the analyzed assigned data, and the adapting step includes;

changing at least one of the upper and lower limits,

sending a request to a user to define an activity which is not one of the recognized predefined activities,

receiving a new activity definition from the user,

assigning the corresponding primary and/or secondary data with a new activity definition,

calculating a new data pattern for the new activity definition,

storing the new activity definition and the new data pattern, and

displaying on a display device at least one of the upper limit, the lower limit, the primary data, the secondary data, an identification of one of the predefined activities, and the data patterns.

13. The activity recognition method according to claim 12, in which the automatic recognition is interrupted for a user-defined period comprising the following steps:

starting the user-defined period via a user interface,

inserting a definition of a currently performed activity by a user,

assigning further primary and/or secondary data with the user-inserted definition,

storing the further primary and/or secondary data and the user-inserted definition,

leaving the user-defined period via the user interface,

loading further primary and/or secondary data from the user-defined period,

calculating of a new data pattern from the further primary and/or secondary data, and

storing the new data pattern and the user-inserted definition.

14. The activity recognition method according to claim 12, in which the data patterns corresponding to at least one of the defined activities has upper and lower limits and wherein

the analysis step includes evaluating variations in the primary and/or secondary data assigned to the at least one predefined activities;

and

the adapting step includes modifying at least one of the upper and lower limits.

15. An activity recognition method for a wearable device, wherein a processor is programmed to perform the steps of:

measuring primary data as a function of time,

calculating secondary data from the primary data,

storing the primary and/or the secondary data as a function of time,

loading the primary and/or the secondary data and a plurality of data patterns each indicative of a corresponding one of a plurality of predefined activities from a memory in communication with the processor, wherein the predefined activities include at least three of;

jogging and the specific data pattern assigned to jogging comprises a heart rate with variations over a jogging time interval range, a velocity varying between 7 km/h and 25 km/h, a periodic vertical acceleration and a constant step frequency,

cycling and the specific data pattern assigned to cycling comprises a heart rate unvarying within a cycling time interval range, a velocity varying between 10 km/h and 90 km/h, a discrete horizontal acceleration, and no step frequency,

a water sport and the specific data pattern assigned to the water sport comprises a heart rate with variations over a water sport variation range and a water sport time interval range, a velocity below 20 km/h, periodic accelerations, above normal skin humidity, and no step frequency,

a ball game and the specific data pattern assigned to the ball game comprises a varying heart rate, a velocity varying between 0 km/h and 30 km/h, a varying horizontal and vertical acceleration during defined ball game time intervals, a strongly varying step frequency, and

a fitness sport and the specific data pattern assigned to the fitness sport comprises a heart rate with first variations within a first fitness sport variation range and a first fitness sport time interval range, a velocity below 5 km/h, a periodically varying horizontal and vertical acceleration during a second fitness sport time interval range and a varying step frequency within a second fitness sport variation range during the second fitness sport time interval range,

calculating reference data from the primary and/or secondary data,

comparing the reference data with the data patterns to automatically recognize a corresponding one of the predefined activities,

assigning the primary and/or the secondary data with the recognized predefined activity,

storing the assigned data with the recognized predefined activity in the memory,

analyzing the assigned data corresponding to one of the predefined activities,

modifying the data pattern corresponding to the recognized predefined activity according to the analyzed assigned data,

evaluating training data for patterns corresponding to each of a plurality of activities,

defining data patterns corresponding to each of the plurality of predefined activities, and

displaying on a display device at least one of the primary data, the secondary data, one of the data patterns, and an identification of one of the predefined activity.

16. The method according to claim 15, in which the predefined activities include at least two of:

the water sport and the specific data pattern assigned to the water sport comprises a heart rate with variations over a water sport variation range and a water sport time interval range, a velocity below 20 km/h, periodic accelerations, above normal skin humidity, and no step frequency,

the ball game and the specific data pattern assigned to the ball game comprises a varying heart rate, a velocity varying between 0 km/h and 30 km/h, a varying horizontal and vertical acceleration during defined ball game time intervals, a strongly varying step frequency, and

the fitness sport and the specific data pattern assigned to the fitness sport comprises a heart rate with first variations within a first fitness sport variation range and a first fitness sport time interval range, a velocity below 5 km/h, a periodically varying horizontal and vertical acceleration during a second fitness sport time interval range and a varying step frequency within a second fitness sport variation range during the second fitness sport time interval range.

17. An activity recognition method for a wearable device, wherein a processor performs the steps of:

measuring primary data as a function of time,

calculating secondary data from the primary data,

storing the primary and/or the secondary data as a function of time,

loading the primary and/or the secondary data and a plurality of data patterns each indicative of a corresponding to one of a plurality of predefined activities from a memory, wherein the predefined activities include at least three of;

jogging and the specific data pattern assigned to jogging comprises a heart rate with variations over a jogging time interval range, a velocity varying between 7 km/h and 25 km/h, a periodic vertical acceleration and a constant step frequency,

cycling and the specific data pattern assigned to cycling comprises a heart rate unvarying within a cycling time interval range, a velocity varying between 10 km/h and 90 km/h, a discrete horizontal acceleration, and no step frequency,

a water sport and the specific data pattern assigned to the water snort comprises a heart rate with variations over a water sport variation range and a water sport time interval range, a velocity below 20 km/h, periodic accelerations, above normal skin humidity, and no step frequency,

a ball game and the specific data pattern assigned to the ball game comprises a varying heart rate, a velocity varying between 0 km/h and 30 km/h, a varying horizontal and vertical acceleration during defined ball game time intervals, a strongly varying step frequency, and

a fitness sport and the specific data pattern assigned to the fitness sport comprises a heart rate with first variations within a first fitness sport variation range and a first fitness sport time interval range, a velocity below 5 km/h, a periodically varying horizontal and vertical acceleration during a second fitness sport time interval range and a varying step frequency within a second fitness sport variation range during the second fitness sport time interval range,

calculating reference data from the primary and/or secondary data,

comparing the reference data with the data patterns to automatically recognize a corresponding one of the predefined activities,

assigning the primary and/or the secondary data with the recognized predefined activity,

storing the assigned data with the recognized predefined activity in the memory,

analyzing the assigned data corresponding to one of the predefined activities,

modifying the data pattern corresponding to the recognized predefined activity according to the analyzed assigned data, and

displaying on a display device at least one of the primary data, the secondary data, one of the data patterns, and an identification of one of the predefined activity,

in which the comparing step includes;

calculating a correlation probability of the reference data and the data patterns of the predefined activities.

18. The method according to claim 17, in which the predefined activities include at least two of:

the water sport and the specific data pattern assigned to the water sport comprises a heart rate with variations over a water sport variation range and a water sport time interval range, a velocity below 20 km/h, periodic accelerations, above normal skin humidity, and no step frequency,

the ball game and the specific data pattern assigned to the ball game comprises a varying heart rate, a velocity varying between 0 km/h and 30 km/h, a varying horizontal and vertical acceleration during defined ball game time intervals, a strongly varying step frequency, and

the fitness sport and the specific data pattern assigned to the fitness sport comprises a heart rate with first variations within a first fitness sport variation range and a first fitness sport time interval range, a velocity below 5 km/h, a periodically varying horizontal and vertical acceleration during a second fitness sport time interval range and a varying step frequency within a second fitness sport variation range during the second fitness sport time interval range.