Fingerprinting based positioning is commonly used for indoor positioning. In this method, initially a radio map is created using Received Signal Strength (RSS) values that are measured from predefined reference points. During the positioning, the best match between the observed RSS values and existing RSS values in the radio map is established as the predicted position. In the positioning literature, machine learning algorithms have widespread usage in estimating positions. One of the main problems in indoor positioning systems is to find out appropriate machine learning algorithm. In this paper, selected machine learning algorithms are compared in terms of positioning accuracy and computation time. In the experiments, UJIIndoorLoc indoor positioning database is used. Experimental results reveal that k-Nearest Neighbor (k-NN) algorithm is the most suitable one during the positioning. Additionally, ensemble algorithms such as AdaBoost and Bagging are applied to improve the decision tree classifier performance nearly same as k-NN that is resulted as the best classifier for indoor positioning.
Özetçe-RF tabanlı iç ortam konumlama sistemlerinde, ortamda bulunan erişim noktalarından önceden belirlenen referans noktalarında toplanan alınan sinyal gücü (RSS) değerleri ile RF haritası oluşturulur. Konumlama işleminden önce oluşturulan RF haritasının, konum tahmin işlemi sırasında farklı mobil cihazlarla elde edilen ölçümler ile karşılaştırılabilmesi için kalibrasyon işleminden geçirilmesi ve ortam dinamiklerine adapte olabilmesi için güncellenmesi gerekebilir. Literatürde sırasıyla RF haritası kalibrasyonu ve güncellenmesi olarak tanımlanan bu işlemler, konumlama doğruluğu üzerinde büyük rol oynamaktadır. Bu bildiride, RF haritası oluşturma, kalibrasyon ve güncelleme adına yapılan çalışmalar incelenerek bir derleme oluşturulmuştur.
Anahtar Kelimeler -RF haritası, iç ortam konumlama, RF haritası kalibrasyonu, RF haritası güncelleme.
Abstract-In RF based indoor positioning systems, RF map is constructed by collecting Received Signal Strength (RSS) values from access points at predetermined reference points in the working area. RF map is calibrated in order tocompare with the measurements obtained using heterogeneous mobile devices and is updated to adapt to the environment dynamics before positioning. These processes, which are defined as RF map calibration and update respectively in the literature, play important roles in positioning accuracy. In this paper, a survey is presented by reviewing the workson RF map construction, calibration and update.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.