Indoor Positioning System Using Wifi Fingerprint

Indoor Positioning System aims at locating objects inside buildings wirelessly, and have huge benefit for indoor location-aware mobile application. To explore this immature system design, we choose UJIndoorLoc database as our data set, use PCA for feature selection, and build prediction models based on decision tree, gradient boosting, kNN and SVM, respectively. Our experiment results indicate that combination of kNN and Gradient Boosting provides high prediction accuracy for Indoor Positioning. kNN shows good performance for large volume of data set with sample size greater 1000, and Gradient Boosting has small cross validation error for small data volume and is robust to missing data.