MULTI-ON-BODY ACTION DETECTION BASED ON ULTRASOUND

1 . A method comprising:

transmitting, by a device that is worn by a user, an ultrasonic signal, wherein the ultrasonic signal propagates on the user's body;

receiving, by the device, an ultrasound event that includes receipt of the ultrasonic signal that propagated on the user's body and effected by an on-body action, performed by the user on the user's body, in an area in which the ultrasonic signal has propagated;

analyzing, by the device, a characteristic of the ultrasonic signal received;

determining, by the device, one or more sides of the device at which the on-body action is performed relative to the device; and

selecting, by the device, an input based on an analysis of the ultrasound event and the one or more sides of the device.

2 . The method of claim 1 , further comprising:

performing, by the device, an operation specified by the input, wherein the on-body action is a multi-touch action or a multi-gesture action in which each touch or each gesture is performed on different sides of the device simultaneously, and wherein the determining comprises:

determining, by the device, one side of the device that a touch of the multi-touch action or a gesture of the multi-gesture action is performed relative to the device; and

determining, by the device, another side of the device that another touch of the multi-touch action or another gesture of the multi-gesture action is performed relative to the device.

3 . The method of claim 1 , further comprising:

storing a database that maps ultrasound event data to data indicating inputs, wherein the ultrasound event data includes characteristic data of the ultrasonic signal and side data that indicates a side of the device; and

comparing the characteristic data and the side data to data stored in the database; and wherein the selecting comprises:

selecting the input based on the comparing.

4 . The method of claim 1 , wherein determining the one or more sides is based on the receipt of the ultrasonic signal that propagated on the user's body and effected by the on-body action, wherein a frequency of the ultrasonic signal received maps to a side of the device.

5 . The method of claim 1 , wherein the analyzing comprises:

analyzing a frequency and an amplitude of the ultrasonic signal received; and

identifying the on-body action based on the analyzing.

6 . The method of claim 1 , wherein determining the one or more sides is based on an arrival time of the ultrasonic signal received that propagated on the user's body and effected by the on-body action.

7 . The method of claim 1 , wherein the input is application-specific.

8 . A device comprising:

an ultrasonic transmitter, wherein the ultrasonic transmitter is configured to transmit an ultrasonic signal that can propagate on a user's body;

an ultrasonic receiver, wherein the ultrasonic receiver is configured to receive an ultrasonic event that includes receipt of the ultrasonic signal that propagated on the user's body and effected by an on-body action, performed by the user, in an area in which the ultrasonic signal has propagated;

a memory, wherein the memory stores software; and

a processor, wherein the processor is configured to execute the software to:

analyze a characteristic of the ultrasonic signal received;

determine one or more sides of the device at which the on-body action is performed relative to the device; and

select an input based on an analysis of the ultrasonic event and the one or more sides of the device.

9 . The device of claim 8 , further comprising:

a communication interface, wherein the processor is further configured to execute the software to:

transmit, via the communication interface, the input to another device.

10 . The device of claim 8 , wherein the processor is further configured to execute the software to:

store a database that maps ultrasound event data to data indicating inputs, wherein the ultrasound event data includes characteristic data of the ultrasonic signal and side data that indicates a side of the device; and

compare the characteristic data and the side data to data stored in the database; and wherein, when selecting, the processor is further configured to execute the software to:

select the input based on a comparison.

11 . The device of claim 8 , wherein when determining the one or more sides, the processor is further configured to execute the software to:

determine the one or more sides based on the receipt of the ultrasonic signal that propagated on the user's body and effected by the on-body action, wherein a frequency of the ultrasonic signal received maps to a side of the device.

12 . The device of claim 8 , wherein, when analyzing, the processor is further configured to execute the software to:

analyze a frequency and an amplitude of the ultrasonic signal received; and

identify the on-body action based on an analysis of the frequency and the amplitude of the ultrasonic signal received.

13 . The device of claim 8 , further comprising:

a display, and wherein the on-body action is a multi-touch action or a multi-gesture action in which each touch or each gesture is performed on different sides of the device simultaneously, and wherein, when determining, the processor is further configured to execute the software to:

determine one side of the device that a touch of the multi-touch action or a gesture of the multi-gesture action is performed relative to the device, and

determine another side of the device that another touch of the multi-touch action or another gesture of the multi-gesture action is performed relative to the device.

14 . The device of claim 8 , wherein when determining the one or more sides, the processor is further configured to execute the software to:

determine the one or more sides based on an arrival time of the ultrasonic signal that propagated on the user's body and effected by the on-body action.

15 . The device of claim 8 , wherein the software comprises a machine learning module that allows the user to train the device to recognize particular on-body actions performed by the user and select inputs corresponding to the on-body actions.

16 . A non-transitory storage medium that stores instructions executable by a processor of a computational device, which when executed, cause the computational device to:

analyze a characteristic of an ultrasonic signal that propagated on a body of a user of the computational device and effected by an on-body action, performed by the user, in an area in which the ultrasonic signal has propagated;

determine one or more sides of the computational device at which the on-body action is performed relative to the computational device;

select an input based on an analysis of the ultrasonic signal and the one or more sides; and

perform an action specified by the input.

17 . The non-transitory storage medium of claim 16 , wherein the instructions to determine comprise instructions to:

determine the one or more sides based on a receipt of the ultrasonic signal that propagated on the body of the user and effected by the on-body action, wherein a frequency of the ultrasonic signal received maps to a side of the computational device.

18 . The non-transitory storage medium of claim 16 , wherein the instructions comprise instructions to:

store a database that maps ultrasonic signal profiles to inputs; and

use the database to select the input.

19 . The non-transitory storage medium of claim 16 , wherein the instructions to determine comprise instructions to:

determine the one or more sides based on an arrival time of the ultrasonic signal that propagated on the body of the user and effected by the on-body action.

20 . The non-transitory storage medium of claim 16 , wherein the on-body action is a multi-touch action or a multi-gesture action.