RSSI and Feed Forward Neural Network (FFNN) Based Indoor Localization in WSN

TreeLoc: An Ensemble Learning-based Approach for Range Based Indoor Localization

“…We used the same testbed in [8] and [9]. This experimental testbed has been set up in an electronic lab with an 8.02 square meter area spanning an open space surrounded by walls.…”

“…The ESP8266 has been used to design and develop the mobile and reference nodes in the testbed. ESP8266 is a Wi-Fi module popular for Internet of Things applications [9]. This module has a wireless Wi-Fi transceiver that operates in the IEEE 802.11 b/g/n standard in an unlicensed frequency range of 2400-2484 MHz, supporting the TCP/IP communication protocol stack and Wi-Fi security supporting WAP3.…”

“…Many of them are based on supervised learning, and also there are some novel algorithms as well [6][7][8]. And compare deterministic methods and machine learning methods in [9][10]. The main objective of this work is to develop a novel algorithm with improved accuracy that can be used for indoor localization applications in IoT.…”

“…Results in [8][9][10][11][12] show the performance of using tree-based supervised algorithms in localization. Further, Decision Tree Regression (DTR), Extra Tree Regressor (ETR), and Random Forest Regressor (RFR) have been identified as the highly accurate supervised learning algorithms for indoor localization.…”

“…In this work, it has been modified the experimental testbed used in [9]. The testbed consists of three reference nodes and one target node.…”