# US 11,026,600 B2 · Activity classification in a multi-axis activity monitor device > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,026,600 B2 - Document ID: US11026600B2 - Status: Granted - Kind: B2 - Application number: 13/648,963 - Filed: 2012-10-10 - Published: 2013-07-11 - Granted: 2021-06-08 - Earliest claimed: 2012-01-09 - Assignees: InvenSense, Inc. - Applicants: InvenSense, Inc. - Inventors: Jonathan E. Lee - Web page: https://patentgrep.com/patent/US11026600B2 ## CPC - A61B 5/1118: {Determining activity level} - A61B 5/1123: {Discriminating type of movement, e.g. walking or running (A61B5/1116, A61B5/112 take precedence)} - G01R 33/028: Electrodynamic magnetometers - A61B 5/0002: {Remote monitoring of patients using telemetry, e.g. transmission of vital signals via a communication network (endoradiosondes A61B5/07)} - A61B 5/1116: {Determining posture transitions} - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12) ## Abstract An activity classification device is disclosed. The activity classification device comprises one or more motion sensors and a memory configured to receive signals from the one or more motion sensors. The device further includes a processor in communication with the memory. Finally, the device includes a classification algorithm executed by the processor, the classification algorithm for identifying activities that a user is engaged in. The memory may also record a user's activity log, calorie count and an RF module, which transmits the recorded data to a host either upon request or continuously. ## Claims ### Claim 1 A device comprising: motion sensors including a gyroscope and an accelerometer; a memory configured to receive signals from the motion sensors; a processor in communication with the memory; a classification algorithm executed by the processor; the classification algorithm for identifying activities that a user is engaged in using the gyroscope and the accelerometer and for assigning a confidence value to an identified activity; and a power management algorithm that (i) stores data from the accelerometer associated with the identified activity and disables the gyroscope when the confidence value exceeds a threshold and (ii) compares subsequent data from the accelerometer to the stored data and enables the gyroscope when variance between the subsequent data and the stored data is sufficiently large. ### Claim 2 (depends on 1) The device of claim 1, wherein the motion sensors comprise any or any combination of one or more accelerometers, one or more gyroscopes, one or more magnetometers, one or more pressure sensors, one or more temperature sensors, one or more microphones, and one or more heart rate monitors. ### Claim 3 (depends on 1) The device of claim 1, wherein each of the motion sensors is an integrated module on a single substrate. ### Claim 4 (depends on 1) The device of claim 1, further comprising a step counter based on any combination of the identified activity or identified activity transitions, and reporting a number of steps. ### Claim 5 (depends on 1) The device of claim 1, wherein the memory is configured to store an activity data. ### Claim 6 (depends on 5) The device of claim 5, further comprising a circuit which wirelessly transmits the activity data to a second device. ### Claim 7 (depends on 1) The device of claim 1, wherein the classification algorithm includes estimating a calorie burn rate based on the identified activities. ### Claim 8 (depends on 1) The device of claim 1, wherein the identified activities include any of sleeping, driving a car, bicycling, jogging, playing tennis, golfing, sitting, standing, walking, running, swim strokes, waving motions and moving hand in circles. ### Claim 9 (depends on 8) The device of claim 8, wherein the swim strokes comprise any of a breaststroke, a backstroke, and freestyle and the waving motions include any of a handshake, dribbling. ### Claim 10 A computer-implemented method for identifying activities of a device, the method comprising: utilizing motion sensors on the device including a gyroscope and an accelerometer to identify activities; utilizing a classification algorithm executed by a processor; the classification algorithm for identifying the activities and for assigning a confidence value to an identified activity; and utilizing a power management algorithm executed by the processor that (i) stores data from the accelerometer associated with the identified activity and disables the gyroscope when the confidence value exceeds a threshold and (ii) compares subsequent data from the accelerometer to the stored data and enables the gyroscope when variance between the subsequent data and the stored data is sufficiently large. ### Claim 11 (depends on 10) The computer-implemented method of claim 10, wherein the utilizing motion sensors comprises executing a classification algorithm to identify activities. ### Claim 12 (depends on 11) The computer implemented method of claim 11, which includes estimating a calorie burn rate based on the identified activities by the classification algorithm. ### Claim 13 (depends on 10) The computer-implemented method of claim 10, wherein the identified activities include any of sitting, standing, walking, running, swim strokes, waving motions and moving hand in circles. ### Claim 14 (depends on 13) The computer-implemented method of claim 13, wherein the swim strokes comprise any of a breaststroke, a backstroke, and freestyle and the waving motions include any of a handshake, dribbling. ### Claim 15 A computer program product containing program instructions for identifying activities of a device on a non-transitory computer-readable medium, the program instructions to be executed by a processor, the program instructions when executed comprising: utilizing motion sensors on the device including a gyroscope and an accelerometer to identify activities of the device; utilizing a classification algorithm executed by the processor; the classification algorithm for identifying the activities and for assigning a confidence value to an identified activity; and utilizing a power management algorithm executed by the processor that (i) stores data from the accelerometer associated with the identified activity and disables the gyroscope when the confidence value exceeds a threshold and (ii) compares subsequent data from the accelerometer to the stored data and enables the gyroscope when variance between the subsequent data and the stored data is sufficiently large. ### Claim 16 (depends on 15) The computer program product of claim 15, further comprising repeating the utilizing motion sensors step to improve confidence level, accuracy, and performance of the device. ### Claim 17 A system comprising: at least one host device comprising a first processor; a first memory; a first wireless communication module; and a classification algorithm executed by the first processor; the classification algorithm for identifying activities that a user is engaged in and for assigning a confidence value to an identified activity; and at least one sensor device, each of the sensor devices comprising one or more motion sensors selected from a gyroscope and a gyroscope, such that the system comprises at least one gyroscope and at least one accelerometer; a second memory configured to receive signals from the one or more motion sensors; a second processor in communication with the second memory; and a second wireless communication module to communicate with the at least one host device via the first wireless communication module, wherein the second processor executes a power management algorithm to (i) store data from the accelerometer associated with the identified activity and disable the gyroscope when the confidence value exceeds a threshold and (ii) compare subsequent data from the accelerometer to the stored data and enable the gyroscope when variance between the subsequent data and the stored data is sufficiently large.