Activity monitoring device and method

• US 9,521,967 B2
• Filed: 04/06/2012
• Issued: 12/20/2016
• Est. Priority Date: 03/16/2009
• Status: Active Grant

• Current Assignee: Robert Bosch GmbH
• Original Assignee: Robert Bosch GmbH
• Inventors: Srinivasan, Soundararajan, Gacic, Aca, Ganti, Raghu Kiran
• Primary Examiner(s): GANESAN, SUNDHARA M
• Application Number:
  US13/441,624
• Publication Number:
  US 20120245716A1
• Time in Patent Office: 1,719 Days
• Field of Search: 600/587, 600/595, 482/1, 482 8- 9, 128/920, 128/921
• US Class Current: 1/1
• CPC Class Codes: A61B 2560/0242 adapted to measure environmental factors, e.g. temperature, pollution
• CPC Class Codes: A61B 5/1118 Determining activity level
• CPC Class Codes: A61B 5/1123 Discriminating type of movement, e.g. walking or running A61B5/1116, A61B5/112 take precedence
• CPC Class Codes: A63B 2220/64 Frequency, e.g. of vibration oscillation
• CPC Class Codes: A63B 2220/70 Measuring or simulating ambient conditions, e.g. weather, terrain or surface conditions
• CPC Class Codes: A63B 2220/803 Motion sensors
• CPC Class Codes: A63B 2220/808 Microphones
• CPC Class Codes: A63B 2220/836 Sensors arranged on the body of the user
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: G06V 40/23 Recognition of whole body movements, e.g. for sport training
• CPC Class Codes: G06V 40/25 Recognition of walking or running movements, e.g. gait recognition

Abstract

A physical activity monitoring method and system in one embodiment includes a wearable sensor device configured to generate physiologic data associated with a sensed physiologic condition of a wearer, and to generate audio context data associated with a sensed audio context of the wearer, a memory including program instructions stored therein, a computer configured to receive the physiologic data and the audio context data and to execute the program instructions to distinguish between dynamic and static activities of the wearer based upon the physiologic data, and to generate activity data by differentiating between different classes of distinguished dynamic and static activities based upon the audio context data, and a user interface operably connected to the computer for rendering the activity data.

Claims

1. A physical activity monitoring system comprising:

a wearable sensor device configured to generate physiologic data associated with a sensed physiologic condition of a wearer, and to generate audio context data associated with a sensed audio context of the wearer;

a memory including program instructions stored therein;

a computer configured to receive the physiologic data and the audio context data and to execute the program instructions to distinguish between dynamic and static activities of the wearer based upon the physiologic data, and to generate activity data by differentiating between different classes of distinguished dynamic and static activities based upon the audio context data;

a user interface operably connected to the computer for rendering the activity data; and

a microphone sensor, wherein the computer is configured to execute the stored program instructions to differentiate between different classes using a frequency analysis of the audio context data.

2. The system of claim 1, wherein the program instructions include a hidden Markov Model (HMM).

3. The system of claim 2, further comprising:

a Mel-frequency filterbank stored within the memory.

4. The system of claim 3, further comprising:

an accelerometer sensor, wherein the computer is configured to execute the stored program instructions to distinguish between dynamic and static activities of the wearer based upon a determined acceleration of the wearer using data from the accelerometer sensor.

5. The system of claim 4, wherein:

the determined acceleration comprises a three-dimensional vector magnitude of acceleration;

the computer is configured to execute the stored program instructions to determine a skewness of the three-dimensional vector magnitude of acceleration; and

the computer is configured to execute the stored program instructions to determine an entropy in a z-axis of the three-dimensional vector magnitude of acceleration.

6. A method of displaying data associated with physical activities comprising:

generating physiologic data associated with a sensed physiologic condition of a user with a portable device;

generating audio context data associated with a sensed audio context of the user with the portable device;

distinguishing between dynamic and static activities of the user based upon the generated physiologic data using a processor;

generating activity data by differentiating between different classes of distinguished dynamic and static activities based upon the generated audio context data, generating activity data comprises differentiating between different classes using a frequency analysis of the audio context data; and

rendering the activity data.

7. The method of claim 6, wherein distinguishing comprises distinguishing between dynamic and static activities of the user using a hidden Markov Model (HMM).

8. The method of claim 7, wherein generating activity data comprises differentiating between different classes using a Mel-frequency filterbank.

9. The method of claim 8, wherein distinguishing between dynamic and static activities comprises:

determining an acceleration of the wearer using data from an accelerometer sensor.

10. The method of claim 9, wherein distinguishing between dynamic and static activities comprises:

determining a skewness of a three-dimensional vector magnitude of acceleration; and

determining an entropy in a z-axis of the three-dimensional vector magnitude of acceleration.

11. The method of claim 10, wherein distinguishing between dynamic and static activities comprises distinguishing between dynamic and static activities using at least one cepstral coefficient.