LOCATION DETERMINATION USING GENERALIZED FINGERPRINTING
First Claim
1. A method of location determination for a device, the method comprising:
- dividing a plurality of crowd-sourced location observations and a plurality of non-RF related factors into a training dataset and a test dataset, each of the crowd-sourced location observations including a set of base stations observed by one of a plurality of computing devices and an observation location of the device;
assigning the crowd-sourced location observations to one or more geographic areas based on the observation locations associated with each of the crowd-sourced location observations and a location associated with each of the geographic areas;
determining the device location estimate based on the training data set; and
comparing the determined device location estimate to the observation location of the device corresponding to the location observation in the test dataset to calculate an accuracy value.
2 Assignments
0 Petitions
Accused Products
Abstract
An RF fingerprinting methodology is generalized to include non-RF related factors. For each fingerprinted tile, there is an associated distance function between two fingerprints (the training fingerprint and the test fingerprint) from within that tile which may be a linear or non-linear combination of the deltas between multiple factors of the two fingerprints. The distance function for each tile is derived from a training dataset corresponding to that specific tile, and optimized to minimize the total difference between real distances and predicted distances. Upon receipt of an inference request, a result is derived from a combination of the fingerprints from the training dataset having the least distance per application of the distance function. Likely error for the tile is also determined to ascertain whether to rely on other location methods.
43 Citations
20 Claims
-
1. A method of location determination for a device, the method comprising:
-
dividing a plurality of crowd-sourced location observations and a plurality of non-RF related factors into a training dataset and a test dataset, each of the crowd-sourced location observations including a set of base stations observed by one of a plurality of computing devices and an observation location of the device; assigning the crowd-sourced location observations to one or more geographic areas based on the observation locations associated with each of the crowd-sourced location observations and a location associated with each of the geographic areas; determining the device location estimate based on the training data set; and comparing the determined device location estimate to the observation location of the device corresponding to the location observation in the test dataset to calculate an accuracy value. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system for determining the location of a device, the system comprising:
-
a memory area associated with a computing device, said memory area storing location data comprising a plurality of crowd-sourced location observations and a plurality of non-RF related factors, each of the crowd-sourced location observations including a set of base stations observed by one of a plurality of mobile computing devices and an observation location of the mobile computing device, said location data including training data and test data, said memory area further storing a plurality of modeling algorithms and a plurality of location inference algorithms; and a processor programmed to; divide the location data into a training dataset and a test dataset; assign the location data to one or more geographic areas based on the observation locations associated with each of the crowd-sourced location observations and a location associated with each of the geographic areas; determine the device location estimate based on the training data set; compare the determined device location estimate to the observation location of the device corresponding to the location observation in the test dataset to calculate an accuracy value; and calculate an aggregate accuracy value for each of the areas based on the calculated accuracy values of the location observations assigned thereto. - View Dependent Claims (10, 11, 12, 13, 14)
-
-
15. A computer-readable medium comprising computer readable instructions for determining the location of a device, the computer-readable instructions comprising instructions that:
-
construct a training data set and a test data set from location data comprising a plurality of fingerprints and a plurality of non-RF related factors; create a model from the training data set and a distance function; associate a plurality of tiles with the distance function incorporating the plurality of non-RF related factors; and service an inference request corresponding to the plurality of tiles using the distance function. - View Dependent Claims (16, 17, 18, 19, 20)
-
Specification