Localization in a Wireless Sensor Network based on RSSI and a decision tree

In this paper, we propose a new localization technique in a wireless sensor network (wsn) using the Received Signal Strength Indicator (RSSI). This technique is based on a decision tree obtained from a set of empirical experiments on wireless sensors based on XBee modules. The decision tree is used to select the best three neighbour reference nodes that are involved into the estimation of the target sensor node position by applying the Cramer's Rule approach. The tests performed during this study indicate an estimated accuracy of the position around two meters after verifying the validity of our results in an actual environment. This result is acceptable, if we take into consideration the restricted number of nodes used and the application for which the technique will be deployed, this might be the localisation of personnel in high-risk areas in order to enhance their safety in the event of an occurring danger.

---

W artykule zaproponowano nową metodę lokalizacji w sieci bezprzewodowej bazująca na wskaźniku mocy odbieranego sygnału. Metoda została zbadana na przykładzie sieci z modułami XBee. Bazując na drzewie węzłów sieci można określać położenie węzła czujnika stosując metodę prawa Cramera.