# US 2017/0281079 A1 · Tracking caloric expenditure using sensor driven fingerprints > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2017/0281079 A1 - Document ID: US20170281079A1 - Status: Published application - Kind: A1 - Application number: 15/084,670 - Filed: 2016-03-30 - Published: 2017-10-05 - Earliest claimed: 2016-03-30 - Assignees: Intel Corporation - Inventors: Lama Nachman; Hong Lu; Jennifer Healey; Rahul C. Shah; Jonathan J. Huang; Rita H. Wouhaybi; Giuseppe Raffa - Web page: https://patentgrep.com/patent/US20170281079A1 ## CPC - A61B 5/4866: {Evaluating metabolism (using breath test A61B5/083)} - A61B 5/1118: {Determining activity level} - A61B 5/117: Identification of persons (methods or arrangements for recognising patterns, e.g. fingerprints, G06F18/00, G06V40/00; identification of persons by analysing their voice or speech G10L17/00) - A61B 5/222: {combined with detection or measurement of physiological parameters, e.g. heart rate} - A63B 22/02: with movable endless bands {, e.g. treadmills (other training appliances for running on the spot A63B69/0028)} - H04L 67/306: User profiles - H04W 4/02: Services making use of location information - A63B 71/0622: {Visual, audio or audio-visual systems for entertaining, instructing or motivating the user} - A63B 2071/0625: {Emitting sound, noise or music} - A63B 2071/0658: {Position or arrangement of display} - A63B 2220/12: Absolute positions, e.g. by using GPS - A63B 2220/20: Distances or displacements - A63B 2220/40: Acceleration - A63B 2220/805: Optical or opto-electronic sensors - A63B 2220/806: Video cameras - A63B 2225/50: Wireless data transmission, e.g. by radio transmitters or telemetry - A63B 2230/75: calorie expenditure - H04W 4/029: Location-based management or tracking services - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - A63B: APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT (apparatus for passive exercising, massage A61H) - H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M) - H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72) ## Abstract System and techniques for tracking caloric expenditure using sensor driven fingerprints are described herein. A set of outputs may be obtained from a plurality of sensors. A fingerprint may be generated using the set of outputs. The fingerprint may correspond to an activity observed by the plurality of sensors. The generated fingerprint may be compared to a set of fingerprints stored in a database. Each fingerprint of the set of fingerprints may correspond to a respective caloric expenditure. A caloric expenditure may be calculated for the activity based on the comparison. An exercise profile of a user may be updated using the caloric expenditure ## Claims ### Claim 1 A system for tracking caloric expenditure using sensor driven fingerprints, the system comprising: a sensor capture processor to obtain a set of outputs from a plurality of sensors; a fingerprint generator to generate a fingerprint using the set of outputs, the fingerprint corresponding to an activity observed by the plurality of sensors; and an inference comparator to: compare the generated fingerprint to a set of fingerprints stored in a database, each fingerprint of the set of fingerprints corresponding to a respective caloric expenditure; calculate a caloric expenditure for the activity based on the comparison; and update an exercise profile of a user using the caloric expenditure. ### Claim 2 (depends on 1) The system of claim 1, the inference comparator further to: identify that the generated fingerprint does not match a fingerprint of the set of fingerprints; determine a caloric expenditure corresponding to the generated finger print; and store, in the database, the generated fingerprint and the corresponding calculated caloric expenditure. ### Claim 3 (depends on 1) The system of claim 1, fingerprint generator further to: extract features from each sensor of the plurality of sensors included in the set of outputs to generate a fingerprint vector for each sensor of the plurality of sensors over a time period; and merge the fingerprint vector for each sensor to form an aggregate fingerprint vector for the time period; and generate the fingerprint using the aggregate fingerprint vector. ### Claim 4 (depends on 3) The system of claim 3, the fingerprint generator further to use pattern matching to find a similarity between a first feature extracted from a first sensor of the plurality of sensors and a second feature extracted from a second sensor of the plurality of sensors. ### Claim 5 (depends on 1) The system of claim 1, the inference comparator further to: receive a context associated with the activity; and adjust the caloric expenditure based on the context. ### Claim 6 (depends on 1) The system of claim 1, the inference comparator further to: obtain user attributes from the exercise profile of the user; and adjust the caloric expenditure using the user attributes. ### Claim 7 (depends on 1) The system of claim 1, the inference comparator further to: receive a set of data from a smart exercise device; and adjust the caloric expenditure using the set of data. ### Claim 8 (depends on 1) The system of claim 1, further comprising: an activity processing engine to: provide a training mode graphical user interface on a mobile device; obtain an indication, via the training mode graphical user interface, that an activity has commenced; and wherein the sensor capture processor is further to receive a set of outputs from at least one sensor in a wearable device, and wherein the fingerprint generator is further to generate a training fingerprint for the set of outputs and store the training fingerprint in the database. ### Claim 9 At least one machine readable medium including instructions for tracking caloric expenditure using sensor driven fingerprints that, when executed by at least one processor, cause the machine to: obtain a set of outputs from a plurality of sensors; generate a fingerprint using the set of outputs, the fingerprint corresponding to an activity observed by the plurality of sensors; compare the generated fingerprint to a set of fingerprints stored in a database, each fingerprint of the set of fingerprints corresponding to a respective caloric expenditure; calculate a caloric expenditure for the activity based on the comparison; and update an exercise profile of a user using the caloric expenditure. ### Claim 10 (depends on 9) The at least one machine readable medium of claim 9, wherein the instructions to compare the generated fingerprint to the set of fingerprints and calculate the caloric expenditure includes instructions to: identify that the generated fingerprint does not match a fingerprint of the set of fingerprints; determine a caloric expenditure corresponding to the generated finger print; and store, in the database, the generated fingerprint and the corresponding calculated caloric expenditure. ### Claim 11 (depends on 9) The at least one machine readable medium of claim 9, wherein the instructions to generate the fingerprint includes instructions to: extract features from each sensor of the plurality of sensors included in the set of outputs to generate a fingerprint vector for each sensor of the plurality of sensors over a time period; and merge the fingerprint vector for each sensor to form an aggregate fingerprint vector for the time period; and generate the fingerprint using the aggregate fingerprint vector. ### Claim 12 (depends on 11) The at least one machine readable medium of claim 11, wherein the instructions to merge the fingerprint vector for each sensor includes instructions to use pattern matching to find a similarity between a first feature extracted from a first sensor of the plurality of sensors and a second feature extracted from a second sensor of the plurality of sensors. ### Claim 13 (depends on 9) The at least one machine readable medium of claim 9, further comprising instructions to: receive a context associated with the activity; and adjust the caloric expenditure based on the context. ### Claim 14 (depends on 9) The at least one machine readable medium of claim 9, further comprising instructions to: obtain user attributes from the exercise profile of the user; and adjust the caloric expenditure using the user attributes. ### Claim 15 (depends on 9) The at least one machine readable medium of claim 9, further comprising instructions to: receive a set of data from a smart exercise device; and adjust the caloric expenditure using the set of data. ### Claim 16 (depends on 9) The at least one machine readable medium of claim 9, further comprising instructions to: provide a training mode graphical user interface on a mobile device; receive a set of outputs from at least one sensor in a wearable device; obtain an indication, via the training mode graphical user interface, that an activity has commenced; generate a training fingerprint for the set of outputs; and store the training fingerprint in the database. ### Claim 17 A method for tracking caloric expenditure using sensor driven fingerprints, the method comprising: obtaining a set of outputs from a plurality of sensors; generating, using at least one processor, a fingerprint using the set of outputs, the fingerprint corresponding to an activity observed by the plurality of sensors; comparing, using at least one processor, the generated fingerprint to a set of fingerprints stored in a database, each fingerprint of the set of fingerprints corresponding to a respective caloric expenditure; calculating, using at least one processor, a caloric expenditure for the activity based on the comparing; and updating an exercise profile of a user using the caloric expenditure. ### Claim 18 (depends on 17) The method of claim 17, wherein comparing the generated fingerprint to the set of fingerprints includes: identifying that the generated fingerprint does not match a fingerprint of the set of fingerprints; determining a caloric expenditure corresponding to the generated finger print; and storing, in the database, the generated fingerprint and the corresponding calculated caloric expenditure. ### Claim 19 (depends on 17) The method of claim 17, wherein generating the fingerprint includes: extracting features from each sensor of the plurality of sensors included in the set of outputs to generate a fingerprint vector for each sensor of the plurality of sensors over a time period; and merging the fingerprint vector for each sensor to form an aggregate fingerprint vector for the time period; and generating the fingerprint using the aggregate fingerprint vector. ### Claim 20 (depends on 19) The method of claim 19, wherein merging the fingerprint vector for each sensor includes using pattern matching to find a similarity between a first feature extracted from a first sensor of the plurality of sensors and a second feature extracted from a second sensor of the plurality of sensors. ### Claim 21 (depends on 17) The method of claim 17, further comprising: receiving a context associated with the activity; and adjusting the caloric expenditure based on the context. ### Claim 22 (depends on 17) The method of claim 17, further comprising: obtaining user attributes from the exercise profile of the user; and adjusting the caloric expenditure using the user attributes. ### Claim 23 (depends on 17) The method of claim 17, further comprising: receiving a set of data from a smart exercise device; and adjusting the caloric expenditure using the set of data. ### Claim 24 (depends on 17) The method of claim 17, further comprising: providing a training mode graphical user interface on a mobile device; receiving a set of outputs from at least one sensor in a wearable device; obtaining an indication, via the training mode graphical user interface, that an activity has commenced; generating a training fingerprint for the set of outputs; and storing the training fingerprint in the database.