Increasing accuracy in workout autodetection systems and methods
Devices, systems, and methods can be used including receiving motion data, categorizing the motion data into portions of a minute that indicate activity or a workout, and automatically determining an accurate number of active minutes for an individual. Multiple data streams may be analyzed and de-duplicated, such that an accurate metric may be computed and reported to an individual.
1. A health and fitness monitoring system for calculating active minutes for an individual, comprising:
a portable electronic device configured to be carried by the individual, the portable electronic device comprising:
a motion sensor configured to generate a first motion data stream including time-stamped motion data;
a processor; and
a memory, wherein
the processor is configured to process the first motion data stream into an active segment data stream indicating at least one of an active range or activity classification for a given duration,
the processor is configured to organize the active segment data stream into time-stamped minute buckets of one minute including duration values for a plurality of activity-specific classifications,
the memory is configured to store the time-stamped minute buckets in an array,
the processor is configured to determine that a portion of the array includes one of the time-stamped minute buckets that indicates that the individual engaged in a workout based on the duration values for the plurality of activity-specific classifications, and
the processor is configured to receive a second motion data stream including third party software platform motion data, wherein the system at least one of merges or de-duplicates data within the second motion data stream corresponding to data within the first motion data stream.
2. The system of claim 1 , wherein the first motion data stream comprises an operating system based activity classification, and wherein the second motion data stream comprises an activity classification of the third party software platform.
3. The system of claim 1 , wherein the processor further consolidates the data array into an hourly summary that is transmitted to a back end system.
4. The system of claim 3 , wherein the second motion data stream is sent to the back end system, and is added to the hourly summary.
5. The system of claim 4 , wherein the first motion data stream comprises an operating system based activity classification, and wherein the second motion data stream comprises an activity classification of the third party software platform.
6. The system of claim 1 , wherein the processor defines a candidate start density threshold, which is defined by a percentage of a motion classification one of the time-stamped minute buckets must reach in order for the processor to consider the one of the time-stamped minute buckets to be a candidate for the start of an activity.
7. The system of claim 6 , wherein the processor further defines a minimum time active such that the individual may input, through a user interface on the portable electronic device, a desired threshold for the system to consider a workout after a candidate start density threshold minute.
8. A health and fitness monitoring system for calculating active minutes for an individual, comprising:
a portable electronic device configured to automatically detect an activity, the portable electronic device comprising:
a processor;
a motion sensor configured to transmit a first motion data stream comprising first motion data for the individual to the processor; and
a memory comprising a first software platform and a second software platform, the second software platform comprising a second motion data stream comprising second motion data for the individual, the first software platform having instructions that when executed by the processor cause the processor to:
process the first motion data stream into a motion segment data stream;
organize the motion segment data stream into minute buckets and store the minute buckets in the memory as an array;
compare the array to the second motion data stream to determine that the first motion data stream and second motion data stream overlap, to determine unique data in the second motion data stream corresponding to additional active minutes; and
add the minute buckets from the first motion data stream to the additional active minutes of the second motion data stream.
9. The system of claim 8 , wherein the instructions when executed by the processor cause the processor to:
determine that an entry of the array indicates an inactive density threshold;
determine that a minimum time inactive has elapsed after the entry of the array indicating the inactive density threshold such that an end of the activity is determined; and
confirm whether a minimum time active elapsed between a candidate start density threshold minute and the end of the activity such that the activity is categorized as a workout.
10. The system of claim 8 , wherein the second motion data stream comprises a third party software platform activity classification.
11. The system of claim 8 , wherein the second motion data stream comprises data input by the individual.
12. The system of claim 8 , wherein the second motion data stream comprises geo-tagged data.
13. The system of claim 8 , wherein the instructions when executed by the processor cause the processor to:
account for active minutes of the second motion data that occur at the same time as active minutes of the first motion data while also ambient collecting the active minutes of the first motion data by subtracting the active minutes of the first motion data.
14. A health and fitness monitoring system for calculating active minutes for an individual, comprising:
a portable electronic device configured to automatically detect an activity, the portable electronic device comprising:
a processor;
a motion sensor configured to transmit a first motion data stream comprising first motion data for the individual to the processor; and
a memory comprising a first software platform and a second software platform, the second software platform comprising a second motion data stream comprising second motion data for the individual from a third party software platform, the first software platform having instructions that when executed by the processor cause the processor to:
compare the first motion data and the second motion data;
categorize an overlap of the first motion data with the second motion data;
determine that a minimum time active has elapsed between an indication that the activity has begun and an indication that the activity has ended such that the activity is categorized as a workout based on the overlap of the first motion data with the second motion data; and
add active time within the second motion data that is not also within the first motion data.
15. The system of claim 14 , further comprising a user interface that is configured to receive the minimum time active from an individual and communicate the minimum time active to the memory for use by the processor.
16. The system of claim 14 , wherein categorizing the overlap comprises categorizing the first motion data as inactive when the second motion data comprises the same data.
17. The system of claim 14 , wherein the instructions when executed by the processor cause the processor to:
account for active minutes of the second motion data that occur at the same time as active minutes of the first motion data while also always ambient collecting the active minutes of the first motion data by subtracting the active minutes of the first motion data.