Flexible RFID location system based on artificial neural networks for medical care facilities

Abstract

RFID location systems are often used in real-time location systems that come up with the problems like multipath phenomenon and layout changing. These make locating difficult because most of the location systems are based on fixed mathematical calculation that cannot take these situations into account. Using artificial neural network, our location scheme can learn the geography features to adapt to the real world. It could avoid multipath phenomenon effect and be flexibly applied to any environment. The experimental processes and result are shown in the end of the paper.

Enhancing Cluster-based RFID Tag Localization using artificial neural networks and virtual reference tags

“…The problem is more complicated when the localization system is based on empirical or theoretical formulas, which cannot be adapted to the environmental features of the sensing area. ANN overcomes this limitation by learning the relationship between the signal strength and the location of transmitters for each sensing environment [32]. An ANN contains three main types of layers: input layer, hidden layer(s), and output layer.…”

“…Wu et al [32] applied a Back-Propagation (BP) network, which backpropagates the error from the output layer to the hidden layers [28], to find the most probable location of the target node. They used reference tags as landmarks and the RSSI values recorded from each of the references are the input for training the network.…”

“…Martínez Sala et al [18] proposed an ANN similar to that of Wu et al [32] but used the exact coordinates of the reference tags as the input of the ANN for the training phase instead of using zone's numbers. As a result, the ANN provides the coordinates of the target tag in the localization phase.…”

“…However, achieving the desired high accuracy with CMTL in large areas can be costly, and in some cases impossible. In order to improve the previous research, artificial neural networks (ANNs) [32] are applied to overcome the limitations of an empirical positioning formula used in the previous research. Additionally, using virtual reference tags (VRTs) [34] is proposed to improve the accuracy while reducing the cost of the solution.…”

Intelligent RFID Indoor Localization System Using a Gaussian Filtering Based Extreme Learning Machine

“…Currently, an extensive body of research for the IPS has focused on the machine learning approaches such as Extreme Learning Machine (ELM) [11], Artificial Neural Network (ANN) or Support Vector Machine (SVM) [12] and so on, in order to overcome the shortcomings faced by the traditional positioning methods. Wu et al [13] applied the ANN to overcome the limitations of the empirical positioning formula, which was used in the previous research. The ANN can learn the geography features to adapt to the real world, which can avoid the impact of the multipath phenomenon and be flexibly applied to any environment.…”