US 12,493,666 B2
Wireless sensing using classifier probing and refinement
Sai Deepika Regani, Campbell, CA (US); Beibei Wang, Clarksville, MD (US); K. J. Ray Liu, Potomac, MD (US); and Oscar Chi-Lim Au, Rockville, MD (US)
Assigned to ORIGIN RESEARCH WIRELESS, INC., Rockville, MD (US)
Filed by Sai Deepika Regani, Campbell, CA (US); Beibei Wang, Clarksville, MD (US); K. J. Ray Liu, Potomac, MD (US); and Oscar Chi-Lim Au, Rockville, MD (US)
Filed on Dec. 22, 2024, as Appl. No. 18/991,632.
Application 18/991,632 is a continuation in part of application No. PCT/US2022/045708, filed on Oct. 4, 2022.
Application 18/991,632 is a continuation in part of application No. 18/401,681, filed on Jan. 1, 2024.
Application 18/991,632 is a continuation in part of application No. 18/401,684, filed on Jan. 1, 2024.
Application 18/991,632 is a continuation in part of application No. 18/395,544, filed on Dec. 23, 2023.
Application 18/991,632 is a continuation in part of application No. 18/395,537, filed on Dec. 23, 2023.
Application 18/991,632 is a continuation in part of application No. 18/395,543, filed on Dec. 23, 2023.
Application 18/991,632 is a continuation in part of application No. 18/395,539, filed on Dec. 23, 2023.
Application 18/991,632 is a continuation in part of application No. 18/395,533, filed on Dec. 23, 2023.
Application 18/991,632 is a continuation in part of application No. 18/379,622, filed on Oct. 12, 2023.
Application 18/991,632 is a continuation in part of application No. 18/199,963, filed on May 21, 2023.
Application 18/991,632 is a continuation in part of application No. 18/108,563, filed on Feb. 10, 2023.
Application 18/991,632 is a continuation in part of application No. 17/960,080, filed on Oct. 4, 2022.
Application 18/991,632 is a continuation in part of application No. 17/959,487, filed on Oct. 4, 2022.
Application 18/991,632 is a continuation in part of application No. 17/537,432, filed on Nov. 29, 2021.
Application 18/991,632 is a continuation in part of application No. 17/149,625, filed on Jan. 14, 2021.
Application 18/991,632 is a continuation in part of application No. 17/838,244, filed on Jun. 12, 2022.
Application 18/991,632 is a continuation in part of application No. 17/838,231, filed on Jun. 12, 2022.
Application 18/991,632 is a continuation in part of application No. 17/838,228, filed on Jun. 12, 2022.
Application 18/991,632 is a continuation in part of application No. 17/827,902, filed on May 30, 2022.
Claims priority of provisional application 63/614,621, filed on Dec. 24, 2023.
Claims priority of provisional application 63/721,406, filed on Nov. 15, 2024.
Claims priority of provisional application 63/651,921, filed on May 24, 2024.
Prior Publication US 2025/0124110 A1, Apr. 17, 2025
Int. Cl. G06F 18/241 (2023.01)
CPC G06F 18/241 (2023.01) 30 Claims
OG exemplary drawing
 
1. A method performed by a system for wireless sensing with classifier probing and refinement, comprising:
in a probing phase of the system:
obtaining a plurality of raw measurement data by a sensing device of the system,
processing the plurality of raw measurement data by a processor of the system to construct a plurality of input data for a classifier,
performing a classification by the processor using the classifier by inputting each of the plurality of input data to the classifier,
computing a plurality of output analytics by the classifier based on the plurality of input data, each output analytics computed by the classifier based on a respective input data,
mapping the plurality of output analytics to a plurality of mapped outcome, each output analytics mapped to a respective mapped outcome,
identifying at least one reference input data each associated with a reference output analytics and a reference mapped outcome, each reference input data being one of the plurality of input data for the classifier for which a respective reference outcome is available and is different from the reference mapped outcome, and
for each reference input data for the classifier:
constructing a respective plurality of perturbed input data for the classifier by perturbing the reference input data, each perturbed input data constructed based on a respective perturbation of the reference input data,
performing the classification using the classifier by inputting each of the plurality of perturbed input data to the classifier,
computing a respective plurality of perturbed output analytics by the classifier based on the plurality of perturbed input data, each perturbed output analytics computed by the classifier based on a respective perturbed input data,
mapping the plurality of perturbed output analytics to a plurality of perturbed mapped outcome, each perturbed output analytics mapped to a respective perturbed mapped outcome,
comparing each perturbed mapped outcome with the reference outcome associated with the reference input data which is different from the reference mapped outcome, and
when at least one perturbed mapped outcome deviates from the reference mapped outcome such that it is the same as the reference outcome, selecting at least one selected perturbed input data each being one of the respective plurality of perturbed input data associated with one of the at least one perturbed mapped outcome as selected perturbed input data for re-training the classifier; and
in a re-training phase of the system:
re-training the classifier based on each of the at least one selected perturbed input data and the associated reference outcome,
wherein for each input data being the reference input data or any perturbed input data:
the input data is a k-dimensional (k-D) matrix,
each component of the input data is a matrix element of the k-D matrix,
a first matrix element of the k-D matrix is a neighboring component near a second matrix element of the k-D matrix if a distance between coordinates of the first matrix element and the second matrix element is less than a threshold.