Method and system for lightweight calibration of magnetic fingerprint dataset
A method and system of instantiating a recalibration of a magnetic fingerprint dataset of indoor facilities or infrastructure for mobile device navigation. The method comprises, based on magnetic parameters acquired from a plurality of mobile devices acquired at a set of positions within an indoor area, accumulating the magnetic parameters in accordance with a trained neural network-based magnetic fingerprint dataset in a fingerprint database of the indoor area, identifying respective positions of a subset of the set of positions having a variance that exceeds a threshold variance between observed magnetic parameters and magnetic parameters determined in accordance with the trained neural network, and when contiguous positions of the subset are encompassed by a boundary representing a portion of the indoor area, instantiating a re-calibration of the magnetic fingerprint dataset for mobile device navigation within the portion of the indoor area.
1. A method, executed in a processor of a server computing device, of instantiating a re-calibration of a magnetic fingerprint dataset for mobile device indoor navigation, the method comprising:
based on magnetic parameters acquired from a plurality of mobile devices acquired at a set of positions within an indoor area, accumulating the magnetic parameters in accordance with a trained neural network-based magnetic fingerprint dataset in a fingerprint database of the indoor area;
identifying respective positions of a subset of the set of positions having a variance that exceeds a threshold variance between observed magnetic parameters and magnetic parameters determined in accordance with the trained neural network, the threshold variance persisting for at least a predetermined duration of time; and
when contiguous positions of the subset are encompassed by a boundary representing a portion of the indoor area, instantiating a re-calibration of the magnetic fingerprint dataset for mobile device navigation within the portion of the indoor area, the re-calibration including gathering the magnetic fingerprint dataset for the portion of the indoor area.
2. The method of claim 1 wherein the portion of the indoor area comprises at least 10 percent of an area measurement of the indoor area.
3. The method of claim 1 wherein the indoor area is segmented into a plurality of functional areas, and the portion of the indoor area comprises at least 50 percent of an area measurement of at least one of the plurality of functional areas.
4. The method of claim 3 wherein the plurality of areas comprises one of a highly traversed area and a lesser traversed area.
5. The method of claim 4 wherein the threshold variance is a first threshold variance and further comprising a second threshold variance that is higher than the first threshold variance.
6. The method of claim 5 wherein the re-calibration is instantiated for the highly traversed area based on the first threshold variance, and instantiated for the lesser traversed area based on the second threshold variance.
7. The method of claim 5 wherein the more traveled and less traveled portions are determined based on accumulated historical data of mobile device traversals within the indoor area.
8. The method of claim 1 wherein the threshold variance between the observed magnetic parameters and the magnetic parameters determined in accordance the trained neural network is at least 30%.
9. The method of claim 1 wherein the trained neural network comprises a convolution neural network trained in accordance with:
computing, at an output layer of the convolution neural network implemented by the processor, an error matrix based on comparing an initial matrix of weights associated with the at least a first neural network layer representing a set of magnetic input features to a magnetic output feature in accordance with the magnetic acquired parameters of the mobile device at the first location; and
recursively adjusting the initial weights matrix by backpropogation to diminish the error matrix until the magnetic output feature matches the magnetic acquired parameters;
wherein the backpropagation comprises a backward propagation of errors in accordance with the error matrix as computed at the output layer, the errors being distributed backwards throughout the weights of the at least one neural network layer.
10. A server computing system for instantiating a lightweight re-calibration of a magnetic fingerprint dataset for mobile device indoor navigation, the server computing system comprising:
a processor; and
a memory including instructions executable in the processor to:
based on magnetic parameters acquired from a plurality of mobile devices acquired at a set of positions within an indoor area, accumulate the magnetic parameters in accordance with a trained neural network-based magnetic fingerprint dataset in a fingerprint database of the indoor area;
identify respective positions of a subset of the set of positions having a variance that exceeds a threshold variance between observed magnetic parameters and magnetic parameters determined in accordance with the trained neural network, the threshold variance persisting for at least a predetermined duration of time; and
when contiguous positions of the subset are encompassed by a boundary representing a portion of the indoor area, instantiate a re-calibration of the magnetic fingerprint dataset for mobile device navigation within the portion of the indoor area, the re-calibration including gathering the magnetic fingerprint dataset for the portion of the indoor area.
11. The server computing system of claim 10 wherein the portion of the indoor area comprises at least 10 percent of an area measurement of the indoor area.
12. The server computing system of claim 10 wherein the indoor area is segmented into a plurality of functional areas, and the portion of the indoor area comprises at least 50 percent of an area measurement of at least one of the plurality of functional areas.
13. The server computing system of claim 12 wherein the plurality of areas comprises one of a highly traversed area and a lesser traversed area.
14. The server computing system of claim 13 wherein the threshold variance is a first threshold variance and further comprising a second threshold variance that is higher than the first threshold variance.
15. The server computing system of claim 14 wherein the re-calibration is instantiated for the highly traversed area based on the first threshold variance, and instantiated for the lesser traversed area based on the second threshold variance.
16. The server computing system of claim 14 wherein the more traveled and less traveled portions are determined based on accumulated historical data of mobile device traversals within the indoor area.
17. The server computing system of claim 10 wherein the threshold variance between the observed magnetic parameters and the magnetic parameters determined in accordance the trained neural network is at least 30%.
18. The server computing system of claim 10 wherein the trained neural network comprises a convolution neural network trained in accordance with:
computing, at an output layer of the convolution neural network implemented by the processor, an error matrix based on comparing an initial matrix of weights associated with the at least a first neural network layer representing a set of magnetic input features to a magnetic output feature in accordance with the magnetic acquired parameters of the mobile device at the first location; and
recursively adjusting the initial weights matrix by backpropogation to diminish the error matrix until the magnetic output feature matches the magnetic acquired parameters;
wherein the backpropagation comprises a backward propagation of errors in accordance with the error matrix as computed at the output layer, the errors being distributed backwards throughout the weights of the at least one neural network layer.