TY - JOUR
TI - Determination of positioning accuracies by using fingerprint localisation and artificial neural networks
AU - Koyuncu Hakan
JN - Thermal Science
PY - 2019
VL - 23
IS - 11
SP - 99
EP - 111
PT - Article
AB - Fingerprint localization technique is an effective positioning technique to  determine the object locations by using radio signal strength (RSSI), values  in indoors. The technique is subject to big positioning errors due to  challenging environmental conditions. In this paper, initially, a  fingerprint localization technique is deployed by using classical k-NN  method to determine the unknown object locations. Additionally, several  artificial neural networks, (ANN), are employed, using fingerprint data,  such as SFFNN, MFFNN, MBPNN, GRNN and DNN to determine the same unknown  object locations. Fingerprint database is built by RSSI measurement  signatures across the grid locations. The construction and the adapted  approach of different neural networks using the fingerprint data are  described. The results of them are compared with the classical k-NN method  and it was found that DNN was the best neural network technique providing  the maximum positioning accuracies.