Monitoring velocity and dwell trends from wireless sensor network data
A system and method of processing one or more sensor logs includes receiving a sensor log and identifying a set of entries in the sensor log having a predefined sequence of sensor identifiers. The set of entries may define a velocity event. The method can also provide for calculating an in-home gait velocity for the velocity event. In one example, the method also provides for identifying another set of entries in the sensor log having a sensor identifier that corresponds to a dwell sensor mounted in a doorway, wherein the other set of entries define a dwell event. The method may also provide for calculating an in-home dwell time for the dwell event.
1. A method comprising:
receiving a sensor log, wherein each entry in the sensor log has at least one timestamp;
identifying a first set of entries in the sensor log having a predefined sequence of sensor identifiers, the first set of entries defining a velocity event for a human subject in an in-home environment;
calculating an in-home gait velocity for the velocity event based on an initial timestamp in the velocity event, a final timestamp in the velocity event, and a fixed distance between sensors corresponding to the initial and final timestamps;
identifying a second set of entries in the sensor log having a sensor identifier that corresponds to a dwell sensor mounted in a doorway, a rising edge timestamp comprising a time indicative of an entrance into a vicinity of the dwell sensor, and a falling edge timestamp comprising a time indicative of an exit from the vicinity of the dwell sensor, individual entries of the second set of entries defining a dwell event for the human subject in the in-home environment; and
calculating an in-home dwell time for the dwell event based on the rising and falling edge timestamps.
2. The method of claim 1 , further including disqualifying the velocity event if a velocity disqualification condition is true, the velocity disqualification condition including at least one of:
the in-home gait velocity exceeds a velocity threshold; and
a time difference between the initial timestamp and a final timestamp of a previous velocity event is less than a velocity reset threshold.
3. The method of claim 1 , wherein calculating the in-home gait velocity includes averaging a plurality of velocity value calculations, wherein each velocity value calculation corresponds to a pair of sensors in the predefined sequence.
4. The method of claim 1 , further including disqualifying the dwell event if a dwell disqualification condition is true, the dwell disqualification condition including at least one of:
a time difference between the rising edge timestamp of the second set of entries and a falling edge timestamp of a previous dwell event is less than a dwell reset threshold;
a time difference between the rising and falling edge timestamps of the second set of entries exceeds a dwell duration threshold; and
the time difference between the rising and falling edge timestamps of the second set of entries is a negative value.
5. A method comprising:
receiving sensor data;
identifying a set of entries in the sensor data having a predefined sequence of sensor identifiers, the set of entries defining a velocity event; and
calculating an in-home gait velocity for the velocity event.
6. The method of claim 5 , wherein each entry in the sensor data has a timestamp, the method further including calculating the in-home gait velocity based on an initial timestamp in the velocity event, a final timestamp in the velocity event, and a distance between sensors corresponding to the initial and final timestamps.
7. The method of claim 6 , wherein the distance is fixed.
8. The method of claim 6 , further including disqualifying the velocity event if a velocity disqualification condition is true, the velocity disqualification condition including at least one of:
the in-home gait velocity exceeds a velocity threshold; and
a time difference between the initial timestamp and a final timestamp of a previous velocity event is less than a velocity reset threshold.
9. The method of claim 6 , wherein calculating the in-home gait velocity includes averaging a plurality of velocity value calculations, wherein each velocity value calculation corresponds to a pair of sensors in the predefined sequence.
10. The method of claim 5 , further including:
identifying a second set of entries in the sensor data having a sensor identifier that corresponds to a dwell sensor mounted in a doorway, the second set of entries defining a dwell event; and
calculating an in-home dwell time for the dwell event.
11. The method of claim 10 , wherein the second set of entries has a rising edge timestamp comprising a time indicative of an entrance into a vicinity of the dwell sensor and a falling edge timestamp comprising a time indicative of an exit from a vicinity of the dwell sensor, the method further including calculating the in-home dwell time based on the rising and falling edge timestamps.
12. The method of claim 11 , further including disqualifying the dwell event if a dwell disqualification condition is true, the dwell disqualification condition including at least one of:
a time difference between the rising edge timestamp of the second set of entries and a falling edge timestamp of a previous dwell event is less than a dwell reset threshold;
a time difference between the rising and falling edge timestamps of the second set of entries exceeds a dwell duration threshold; and
the time difference between the rising and falling edge timestamps of the second set of entries is a negative value.