Method, device and system for fitness tracking

1. A method of fitness tracking, performed on a computer having a processor, a memory, and one or more code sets stored in the memory and executing by the processor, the method comprising:

receiving, as inputs, data collected from a plurality of sensors embedded in one or more insoles;

filtering the data;

executing an evolutionary algorithm on the data, wherein the evolutionary algorithm converges the data from the plurality of sensors;

determining, based on the converged data, a total weight applied to the one or more insoles;

generating a test data set based on one or more samples of the data from a first set of the plurality of sensors, wherein the first set of the plurality of sensors are embedded in a first insole of the one or more insoles;

associating a known weight quantity with a second set of the plurality of sensors; wherein the second set of the plurality of sensors are embedded in a second insole of the one or more insoles;

applying a fitness function to the test data and the known weight quantity; and

determining, based on the fitness function, whether or not the evolutionary algorithm has optimally converged, such that a predicted weight can be applied to a new data sample outside the test data set.

2. The method as in claim 1 , wherein the first insole and the second insole constitute a pair of insoles adapted to be worn by a single user.

3. The method as in claim 1 , wherein the filtering comprises at least one of: low-pass filtering, Gaussian filtering, moving average filtering, smoothing, rejection of outlier data points, interpolation, frequency, domain transformation, and dimension reduction.

4. The method as in claim 1 , wherein the evolutionary algorithm is one of: a genetic algorithm, a particle swarm optimization algorithm, and a differential evolution algorithm.

5. The method as in claim 1 , wherein the plurality of sensors comprise at least one of force sensors and pressure sensors.

6. The method as in claim 1 , wherein the plurality of sensors are embedded in one or more regions of the one or more insoles, and wherein each region of the one or more insoles in adapted to contact a region of a foot of a user.

7. The method as in claim 1 , wherein the data collected from the plurality of sensors embedded in the one or more insoles is transmitted wirelessly to the processor.

8. A system for fitness tracking, comprising:

one or more insoles, the one or more insoles having embedded therein a plurality of sensors;

a computer having a processor and memory; and

one or more code sets stored in the memory and executing by the processor, which, when executed, configure the processor to:

receive, as inputs, data collected from the plurality of sensors embedded in the one or more insoles;

filter the data;

execute an evolutionary algorithm on the data, wherein the evolutionary algorithm converges the data from the plurality of sensors;

determine, based on the converged data, a total weight applied to the one or more insoles;

generate a test data set based on one or more samples of the data from a first set of the plurality of sensors, wherein the first set of the plurality of sensors are embedded in a first insole of the one or more insoles;

associate a known weight quantity to a second set of the plurality of sensors;

wherein the second set of the plurality of sensors are embedded in a second insole of the one or more insoles;

apply a fitness function to the test data and the known weight quantity; and

determine, based on the fitness function, whether or not the evolutionary algorithm has optimally converged, such that a predicted weight can be applied to a new data sample outside the test data set.

9. The system as in claim 8 , wherein the first insole and the second insole constitute a pair of insoles adapted to be worn by a single user.

10. The system as in claim 8 , wherein the filtering comprises at least one of: low-pass filtering, Gaussian filtering, moving average filtering, smoothing, rejection of outlier data points, interpolation, frequency, domain transformation, and dimension reduction.

11. The system as in claim 8 , wherein the evolutionary algorithm is one of: a genetic algorithm, a particle swarm optimization algorithm, and a differential evolution algorithm.

12. The system as in claim 8 , wherein the plurality of sensors comprises at least one of force sensors and pressure sensors.

13. The system as in claim 8 , wherein the plurality of sensors is embedded in one or more regions of the one or more insoles, and wherein each region of the one or more insoles in adapted to contact a region of a foot of a user.

14. The system as in claim 8 , wherein the data collected from the plurality of sensors embedded in the one or more insoles is transmitted wirelessly to the processor.

15. A device for fitness tracking, comprising:

one or more insoles, the one or more insoles having embedded therein a plurality of sensors and wireless data transmitter, the one or more insoles configured to collect data and wireless transmit the data to a computer having a processor, memory, and one or more code sets stored in the memory and executing by the processor, which, when executed, configure the processor to:

receive, as inputs, the data collected from the plurality of sensors embedded in the one or more insoles;

filter the data;

execute an evolutionary algorithm on the data, wherein the evolutionary algorithm converges the data from the plurality of sensors;

determine, based on the converged data, a total weight applied to the one or more insoles;

generate a test data set based on one or more samples of the data from a first set of the plurality of sensors, wherein the first set of the plurality of sensors are embedded in a first insole of the one or more insoles;

associate a known weight quantity to a second set of the plurality of sensors; wherein the second set of the plurality of sensors are embedded in a second insole of the one or more insoles;

apply a fitness function to the test data and the known weight quantity; and

determine, based on the fitness function, whether or not the evolutionary algorithm has optimally converged, such that a predicted weight can be applied to a new data sample outside the test data set.

16. The device as in claim 15 , wherein the first insole and the second insole constitute a pair of insoles adapted to be worn by a single user.

17. The device as in claim 15 , wherein the evolutionary algorithm is one of: a genetic algorithm, a particle swarm optimization algorithm, and a differential evolution algorithm.