This research aims to purpose the new method, which is called Error Flag Framework (EFF) to enhance accuracy fingerprinting indoor positioning of wireless device by using machine learning algorithms. EFF is compared with well-known machine learning classifiers; i.e. Decision Tree, Naive Bayes, and Artificial Neural Networks, by exploiting the signal strength from limited information. The performance comparison is done in terms of accuracy of classification of positions, precision of distance classified, and effects of classification of positions on results from quantity of learning data. The result of this study can suggest that EFF can increase performance for indoor positioning of every well-known classifier, especially when the quantity of learning data is large enough. Hence, EFF is the alternate way for implementing in positioning software by using the fingerprinting method.
Simultaneous Multi-Information Fusion and Parameter Estimation for Robust 3-D Indoor Positioning Systems
