An F-Score-Weighted Indoor Positioning Algorithm Integrating WiFi and Magnetic Field Fingerprints
Algorithm 1
: Pseudocode of the proposed method.
Training-testing phase:
Inputs: Radio Map, Magnetic Map.
Outputs: WiFi-RSS-based model , MF-based model .
(1)
Normalize each instance in radio map and magnetic map using min-max normalization procedure.
(2)
Split the radio map and the magnetic map as training data (60%) and test data (40%).
(3)
Use (6) to obtain and for the training data of each signal type.
(4)
Calculate the RP labels for both test data type using (9) separately.
(5)
Apply (10) to calculate the F-score values of each signal type per RP using the calculated RP labels and the actual RP labels. The F-score values are stored as the weight of each signal type as and .
(6)
Construct WiFi-RSS-based model and MF-based model as follows:
Positioning phase:
Inputs: ,, WiFi New Test Data, MF New Test Data.
Outputs: estimated position.
(1)
Apply with (8) using WiFi New Test Data to obtain likelihood values of each RP (,, where is the number of RPs).
(2)
Apply with (8) using MF New Test Data to obtain likelihood values of each RP (,, where is the number of RPs).
(3)
Normalize likelihood values using max-min normalization method to obtain and .
(4)
Use the following equation to calculate the final position: