论文信息 - Indoor localization using K-nearest neighbor and artificial neural network back propagation algorithms

Indoor localization using K-nearest neighbor and artificial neural network back propagation algorithms

Currently, indoor localization plays vigorous role in academia and industries. In the proposed technique, 99.78% of room level classifications are correctly classified using K-nearest Neighbor (KNN). For regression based problem, an Artificial Neural Network in Back Propagation (ANNBP) performs an accuracy of 50% and 100% for errors less than 0.5 m and 0.9 m respectively. The root-mean-square error (RMSE) for regression based localization is 0.56. Thus, the result confirmations that the integration of KNN with ANNBP techniques can give better indoor location based services (LBSs).

[1] Hao Jiang,et al. A Fast and Precise Indoor Localization Algorithm Based on an Online Sequential Extreme Learning Machine † , 2015, Sensors.

[2] José M. Claver,et al. RF-Based Location Using Interpolation Functions to Reduce Fingerprint Mapping , 2015, Sensors.

[3] David Mascharka,et al. Machine Learning for Indoor Localization Using Mobile Phone-Based Sensors , 2015, ArXiv.

[4] Rosdiadee Nordin,et al. Recent Advances in Wireless Indoor Localization Techniques and System , 2013, J. Comput. Networks Commun..

[5] Stavros Stavrou,et al. RSS Based Localization Using a New WKNN Approach , 2015, 2015 7th International Conference on Computational Intelligence, Communication Systems and Networks.

[6] Rongke Liu,et al. Wi-Fi-Based Localization in Dynamic Indoor Environment Using a Dynamic Neural Network , 2013 .

[7] Nesreen I. Ziedan,et al. Effects of Walls and Floors in Indoor Localization Using Tracking Algorithm , 2016 .