Systems and methods of assessing a plausibility of a ranging measurement
Systems and methods of assessing a plausibility of a ranging measurement are provided. In some embodiments, a method of assessing a plausibility of a ranging measurement includes: obtaining the ranging measurement from a remote device; obtaining one or more measurements associated with the ranging measurement; and based on the one or more measurements associated with the ranging measurement, determining the plausibility of the ranging measurement. The embodiments disclosed herein determine the reliability of the measured range and thus enforce the security level of Ultra-WideBand (UWB) transactions to be secured. Some embodiments are based on existing and standardized metrics. Some embodiments include a capability to auto-assess whether it is reliable to estimate the plausibility of the transaction range. In some embodiments, the computations needed are relatively simple and can be performed by relatively simple devices.
1. A method of assessing a plausibility of a ranging measurement, comprising:
obtaining the ranging measurement from a remote device;
obtaining one or more measurements associated with the ranging measurement; and
based on the one or more measurements associated with the ranging measurement, determining the plausibility of the ranging measurement by comparing the one or more measurements associated with the ranging measurement with a model of expected values for a plausible ranging measurement;
wherein comparing the one or more measurements associated with the ranging measurement with the model of expected values for a plausible ranging measurement comprises:
projecting the one or more measurements associated with the ranging measurement into digital cells of an n-dimensional space;
determining a density of the digital cells and a global state anomaly score;
determining an anomaly score for the one or more measurements associated with the ranging measurement; and
determining the plausibility of the ranging measurement by comparing the anomaly score with the global state anomaly score.
2. The method of claim 1 wherein the ranging measurement is part of an Ultra-WideBand (UWB) transaction.
3. The method of claim 2 wherein the one or more measurements associated with the ranging measurement comprise one or more of the group consisting of:
a received channel power from the remote device;
a Channel Impulse Response (CIR) associated with the ranging measurement;
a Time of Flight (ToF) associated with the ranging measurement;
a received channel power of the remote device; and
an angle of arrival associated with the ranging measurement.
4. The method of claim 1 wherein the model of expected values for a plausible ranging measurement is the result of an unsupervised clustering algorithm of known plausible ranging measurements.
5. The method of claim 4 wherein the unsupervised clustering algorithm comprises a digital grid clustering algorithm.
6. The method of claim 1 further comprising:
determining reliability of the model of expected values for a plausible ranging measurement.
7. The method of claim 6 wherein determining the reliability of the model of expected values for a plausible ranging measurement is based on a number of dense cells of the model of expected values and a number of past measurements out of the cluster of dense cells.
8. The method of claim 4 wherein determining the plausibility of the ranging measurement comprises:
comparing the one or more measurements associated with the ranging measurement with a one-class State Vector Machine (SVM) algorithm which predicts whether the ranging measurement is plausible.
9. The method of claim 8 further comprising:
if the ranging measurement is determined to not be plausible but within a threshold, retraining the model of expected values using the one or more measurements associated with the ranging measurement.
10. The method of claim 9 further comprising:
assessing a reliability of the plausibility determination based on a generalization loss of cross-validation done when the model of expected values is trained or re-trained.
11. A computing device for assessing a plausibility of a ranging measurement, comprising at least one processor, the at least one processor being configured to:
obtain the ranging measurement from a remote device;
obtain one or more measurements associated with the ranging measurement; and
based on the one or more measurements associated with the ranging measurement, determine the plausibility of the ranging measurement by comparing the one or more measurements associated with the ranging measurement with a model of expected values for a plausible ranging measurement;
wherein comparing the one or more measurements associated with the ranging measurement with the model of expected values for a plausible ranging measurement comprises the at least one processor being configured to:
project the one or more measurements associated with the ranging measurement into digital cells of an n-dimensional space;
determine a density of the digital cells and a global state anomaly score;
determine an anomaly score for the one or more measurements associated with the ranging measurement; and
determine the plausibility of the ranging measurement by comparing the anomaly score with the global state anomaly score.
12. The computing device of claim 11 wherein the ranging measurement is part of an Ultra-WideBand (UWB) transaction.
13. The computing device of claim 12 wherein the one or more measurements associated with the ranging measurement comprise one or more of the group consisting of:
a received channel power from the remote device;
a Channel Impulse Response (CIR) associated with the ranging measurement;
a Time of Flight (ToF) associated with the ranging measurement;
a received channel power of the remote device; and
an angle of arrival associated with the ranging measurement.
14. The computing device of claim 11 wherein the model of expected values for a plausible ranging measurement is the result of an unsupervised clustering algorithm of known plausible ranging measurements.
15. The computing device of claim 14 wherein the unsupervised clustering algorithm comprises a digital grid clustering algorithm.
16. The computing device of claim 11 wherein the at least one processor is configured to:
determine reliability of the model of expected values for a plausible ranging measurement.
17. The computing device of claim 16 wherein determining the reliability of the model of expected values for a plausible ranging measurement is based on a number of dense cells of the model of expected values and a number of past measurements out of the cluster of dense cells.
18. The computing device of claim 14 wherein determining the plausibility of the ranging measurement comprises the at least one processor being further configured to:
compare the one or more measurements associated with the ranging measurement with a one-class State Vector Machine (SVM) algorithm which predicts whether the ranging measurement is plausible.
19. The computing device of claim 18 wherein the at least one processor is further configured to:
if the ranging measurement is determined to not be plausible but within a threshold, retrain the model of expected values using the one or more measurements associated with the ranging measurement.
20. The computing device of claim 19 wherein the at least one processor is configured to:
assess a reliability of the plausibility determination, based on a generalization loss of cross-validation done when the model of expected values is trained or re-trained.