Wireless measurement of human product interaction

1. A method of inferring product activity, the method comprising:

providing a first product having an attached first harmonic tag;

directing, at a first area in which the first product is located, a first transmitted signal of a first frequency;

receiving a first return signal of a first return frequency from the first harmonic tag, wherein the first harmonic tag, upon receiving the first transmitted signal, radiates the first return signal, such that the first return frequency is a harmonic of the first frequency;

based on the first return signal, determining a movement of the first product, wherein the first return signal comprises a doppler shift; and

inferring, by a computer, a first activity in which the first product is being used based on the movement of the first product.

2. The method of claim 1 , comprising:

generating, by the computer, a power spectrogram based on a series of short-time Fourier transforms applied to the first return signal.

3. The method of claim 2 , comprising:

analyzing the power spectrogram, by the computer, with a convolutional neural network to determine an identified activity,

wherein the identified activity comprises the first activity.

4. The method of claim 2 , comprising:

analyzing the power spectrogram, by the computer, with a support vector machine to determine an identified activity,

wherein the identified activity comprises the first activity.

5. The method of claim 2 , wherein inferring the first activity comprises:

comparing the power spectrogram signal to one or more pre-stored activity models.

6. The method of claim 1 , comprising:

directing, at the first area, a second transmitted signal of a second frequency different from the first frequency;

receiving a second return signal of a second return frequency from a second harmonic tag, wherein the second harmonic tag is attached to a second product located in the first area and, the second harmonic tag, upon receiving the second transmitted signal, radiates the second return signal, such that the second return frequency is a harmonic of the second frequency; and

based on the second return signal, inferring, by the computer, a second activity in which the second product is being used.

7. The method of claim 1 , comprising:

receiving a second return signal of the first frequency from a user of the product in the first area reflecting the first transmitted signal.

8. A system for inferring product activity, the system comprising:

a first product having an attached first harmonic tag;

a radar configured to direct, at a first area in which the first product is located, a first transmitted signal of a first frequency;

the radar configured to receive a first return signal of a first return frequency from the first harmonic tag, wherein the first harmonic tag, upon receiving the first transmitted signal, radiates the first return signal, such that the first return frequency is a harmonic of the first frequency;

a memory storing executable instructions; and

a processor in communication with the memory, wherein execution of the executable instructions by the processor causes the processor to:

determine a doppler shift included in the first return signal;

determine movement of the first product to based on the doppler shift; and

infer from the movement of the first product, a first activity in which the first product is being used.

9. The system of claim 8 , wherein execution of the executable instructions by the processor causes the processor to:

generate a power spectrogram based on a series of short-time Fourier transforms applied to the first return signal.

10. The system of claim 9 , wherein execution of the executable instructions by the processor causes the processor to:

analyze the power spectrogram with a convolutional neural network to determine an identified activity,

wherein the identified activity comprises the first activity.

11. The system of claim 9 , wherein execution of the executable instructions by the processor causes the processor to:

analyze the power spectrogram with a support vector machine to determine an identified activity,

wherein the identified activity comprises the first activity.

12. The system of claim 9 , wherein inferring the first activity comprises:

comparing the power spectrogram to one or more pre-stored activity models.

13. The system of claim 8 , further comprising:

the radar configured to direct, at the first area, a second transmitted signal of a second frequency different from the first frequency;

the radar configured to receive a second return signal of a second return frequency from a second harmonic tag, wherein the second harmonic tag is attached to a second product located in the first area and, the second harmonic tag, upon receiving the second transmitted signal, radiates the second return signal, such that the second return frequency is a harmonic of the second frequency; and

wherein execution of the executable instructions by the processor causes the processor to: infer a second activity in which the second product is being used based on the second return signal.

14. The system of claim 8 , further comprising:

the radar configured to receive a second return signal of the first frequency from a user of the product in the first area reflecting the first transmitted signal.

15. A method of inferring product activity, the method comprising:

providing a first product having an attached first harmonic tag;

directing, at a first area in which the first product is located, a first transmitted signal of a first frequency;

receiving a first return signal of a first return frequency from the first harmonic tag, wherein the first harmonic tag, upon receiving the first transmitted signal, radiates the first return signal, such that the first return frequency is a harmonic of the first frequency, wherein the first return signal comprises doppler shift information;

determining a movement of the first product by analyzing the doppler shift information based on the first return signal; and

inferring, by a computer, a first activity in which the first product is being used.