PERSONAL EMERGENCY RESPONSE (PER) SYSTEM
A system includes one or more sensors mounted on a mobile patient; a wireless transceiver to communicate with a remote station; and a processor coupled to the sensor and the wireless transceiver to request assistance if the processor detects a fall by the mobile patient.
1 . A system, comprising:
one or more sensors mounted on a mobile patient;
a wireless transceiver to communicate with a remote station; and
a processor coupled to the sensor and the wireless transceiver to classify sequences of human motions into groups of similar postures each represented by a model and to request assistance if the processor detects a fall by the mobile patient.
2 . The system of claim 1 , wherein the processor determines current position of patient using a global positioning system and a wireless geolocation database.
3 . The system of claim 1 , wherein the processor automatically notifies a third party for assistance upon detecting the fall without a user pressing a button to call for help.
4 . The system of claim 1 , wherein the processor captures movement activities and comparing the movement activities to fall patterns.
5 . The system of claim 1 , wherein the processor determines an in-door position of the patient using signals between the wireless transceiver and the remote station.
6 . The system of claim 1 , wherein the processor determines a fall based on detected motions including one or more changes in height or one or more accelerations associated with movements by the patient.
7 . The system of claim 1 , wherein the processor waits for a predetermined period to detect if the patient can recover from the fall and automatically requests assistance if the patient is unable to recover from the fall.
8 . The system of claim 1 , comprising a call center coupled to the processor to provide a human response.
9 . The system of claim 1 , wherein the processor off-loads processing of accelerometer outputs to a remote computer to conserve battery power.
10 . The system of claim 1 , wherein the processor includes code to generate an acceleration signature based on sensed acceleration; code to match the acceleration signature with at least one of a plurality of stored acceleration signatures, wherein each stored acceleration signatures corresponds with a type of motion; and code to identify the type of motion based on the matching of the acceleration signature with the stored acceleration signature.
11 . A method to monitor a person, comprising:
capturing motions from the person using a mobile device attached to the person;
classifying sequences of human motions into groups of similar postures each represented by a model;
determining a sequence associated with a dangerous condition; and
requesting assistance if a dangerous condition is detected.
13 . The method of claim 11 , comprising determining current position of patient using a global positioning system and a wireless geolocation database.
14 . The method of claim 11 , determining current position of patient using a global positioning system and geolocation data.
15 . The method of claim 11 , further comprising refining identification of the activity, comprising analyzing one of: timing of the identified activity, at least one identified location of the identified activity, a rate of change of a location of the patient, or patterns of a plurality of identified activities.
16 . A method of automatically requesting assistance for a mobile patient, comprising:
attaching a mobile device with one or more accelerometers on the patient to detect patient motion;
classifying sequences of human motions into groups of similar postures each represented by a model;
determining a fall based on detected patient motion; and
automatically requesting assistance from the mobile device on behalf of the patient if help is needed.
17 . The method of claim 16 , comprising detecting if the patient has fallen based on a plurality of accelerometer signals and indicating the fall if the accelerometer signals indicate that the patient is unable to get up.
18 . The method of claim 16 , comprising notifying an emergency service for assistance automatically without a user pressing a button to call for help.
19 . The method of claim 16 , comprising determining current position of patient using a global positioning system and a wireless geolocation database.
20 . The method of claim 16 , further comprising
determining if the patient has fallen based on a plurality of sensor signals indicating changes in height or accelerations associated with the changes in height;
waiting for a predetermined period to detect if the patient can independently recover from the fall; and
requesting assistance if the sensor signals indicate that the patient is unable to independently recover from the fall.