Using Multi-Layer Perceptrons to Enhance the Performance of Indoor RTLS

Abstract

Accuracy in indoor Real-Time Locating Systems (RTLS) is still a problem requiring novel solutions. Wireless Sensor Networks are an alternative to develop RTLS aimed at indoor environments. However, there are some effects associated to the propagation of radio frequency waves, such as attenuation, diffraction, reflection and scattering that depends on the materials and the objects in the environment, especially indoors. These effects can lead to other undesired problems, such as multipath. When the ground is the main responsible for waves reflections, multipath can be modeled as the ground reflection effect. This paper presents a model for improving the accuracy of RTLS, focusing on the mitigation of the ground reflection effect and the estimation of the final position by using Neural Networks.