Processing channel state information (CSI) to determine characteristics of a space between wireless access points
A computing system includes a memory and one or more processors coupled to the memory and configured to obtain a sequence of channel state information (CSI) samples, wherein the sequence of CSI samples corresponds to a communication channel between a first computing device and a second computing device, and calculate, based on the sequence of CSI samples, frequency domain information. The one or more processors are further configured to determine one or more similarity values for the frequency domain information, wherein the one or more similarity values are indicative of one or more characteristics of a space between the first computing device and the second computing device.
1 . A computing system comprising:
a memory; and
one or more processors coupled to the memory and configured to:
obtain a sequence of channel state information (CSI) samples, wherein the sequence of CSI samples corresponds to a communication channel between a first computing device and a second computing device;
calculate, based on the sequence of CSI samples, frequency domain information; and
determine one or more similarity values for the frequency domain information, wherein the one or more similarity values are indicative of one or more characteristics of a space between the first computing device and the second computing device.
2 . The computing system of claim 1 , wherein the first computing device comprises a first Wi-Fi access point, and wherein the second computing device comprises a second Wi-fi Access Point.
3 . The computing system of claim 2 , wherein the sequence of CSI samples is obtained based on Wi-Fi signals exchanged between the first computing device and the second computing device.
4 . The computing system of claim 1 , wherein the frequency domain information includes a set of frequency domain values for each frequency band of a plurality of frequency bands.
5 . The computing system of claim 1 ,
wherein to obtain the sequence of CSI samples, the one or more processors are configured to receive a sequence of sets of CSI values, wherein each set of CSI values of the sequence of sets of CSI values corresponds to a respective CSI sample of the sequence of CSI samples, wherein the sequence of sets of CSI values correspond to a set of CSI value sequences,
wherein to calculate the frequency domain information, the one or more processors are configured to compute a set of discrete Fourier transforms (DFTs) each corresponding to a respective CSI value sequence of the set of CSI value sequences, wherein each DFT of the set of DFTs includes a plurality of DFT values each indicating a parameter of a respective frequency band of a plurality of frequency bands, and
wherein to determine the one or more similarity values for the frequency domain information, the one or more processors are configured to determine the one or more similarity values based on a set of DFT values for each frequency band of the plurality of frequency bands.
6 . The computing system of claim 5 , wherein if frequencies within a first frequency band of the plurality of frequency bands are more prevalent in the CSI value sequence than frequencies within a second frequency band of the plurality of frequency bands, then a first DFT value corresponding to the first frequency band is greater than a second DFT value corresponding to the second frequency band.
7 . The computing system of claim 1 , wherein the one or more processors are further configured to:
perform an action based on the one or more similarity values.
8 . The computing system of claim 7 , wherein the action comprises a security action.
9 . The computing system of claim 1 , wherein the sequence of CSI samples is generated according to a predefined time interval.
10 . The computing system of claim 1 , wherein to determine the one or more similarity values for the frequency domain information, the one or more processors are configured to:
execute a trained machine learning model, wherein the one or more similarity values represent inputs to the machine learning model; and
receive, as an output from the machine learning model, the one or more characteristics of the space between the first computing device and the second computing device.
11 . A method comprising:
obtaining, by one or more processors coupled to a memory, a sequence of channel state information (CSI) samples, wherein the sequence of CSI samples correspond to a communication channel between a first computing device and a second computing device;
calculating, by the one or more processors based on the sequence of CSI samples, frequency domain information; and
determining, by the one or more processors, one or more similarity values for the frequency domain information, wherein the one or more similarity values are indicative of one or more characteristics of a space between the first computing device and the second computing device.
12 . The method of claim 11 , wherein the first computing device comprises a first Wi-Fi access point, and wherein the second computing device comprises a second Wi-fi Access Point.
13 . The method of claim 12 , wherein the sequence of CSI samples is obtained based on Wi-Fi signals exchanged between the first computing device and the second computing device.
14 . The method of claim 11 , wherein the frequency domain information includes a set of frequency domain values for each frequency band of a plurality of frequency bands.
15 . The method of claim 11 ,
wherein obtaining the sequence of CSI samples comprises receiving a sequence of sets of CSI values, wherein each set of CSI values of the sequence of sets of CSI values corresponds to a respective CSI sample of the sequence of CSI samples, wherein the sequence of sets of CSI values correspond to a set of CSI value sequences,
wherein calculating the frequency domain information comprises computing a set of discrete Fourier transforms (DFTs) each corresponding to a respective CSI value sequence of the set of CSI value sequences, wherein each DFT of the set of DFTs includes a plurality of DFT values each indicating a parameter of a respective frequency band of a plurality of frequency bands, and
wherein determining the one or more similarity values comprises determining the one or more similarity values based on a set of DFT values for each frequency band of the plurality of frequency bands.
16 . The method of claim 15 , wherein if frequencies within a first frequency band of the plurality of frequency bands are more prevalent in the CSI value sequence than frequencies within a second frequency band of the plurality of frequency bands, then a first DFT value corresponding to the first frequency band is greater than a second DFT value corresponding to the second frequency band.
17 . The method of claim 11 , further comprising:
performing an action based on the one or more similarity values.
18 . The method of claim 17 , wherein the action comprises a security action.
19 . The method of claim 11 , wherein the sequence of CSI samples is generated according to a predefined time interval.
20 . Non-transitory computer-readable media comprising instructions that, when executed by one or more processors, causes the one or more processors to:
obtain a sequence of channel state information (CSI) samples, wherein the sequence of CSI samples corresponds to a communication channel between a first computing device and a second computing device;
calculate, based on the sequence of CSI samples, frequency domain information; and
determine one or more similarity values for the frequency domain information, wherein the one or more similarity values are indicative of one or more characteristics of a space between the first computing device and the second computing device.