Improved Radio Frequency Identification Indoor Localization Method via Radial Basis Function Neural Network

Indoor localization technique has received much attention in recent years. Many techniques have been developed to solve the problem. Among the recent proposed methods, radio frequency identification (RFID) indoor localization technology has the advantages of low-cost, noncontact, non-line-of-sight, and high precision. This paper proposed two radial basis function (RBF) neural network based indoor localization methods. The RBF neural networks are trained to learn the mapping relationship between received signal strength indication values and position of objects. Traditional method used the received signal strength directly as the input of neural network; we added another input channel by taking the difference of the received signal strength, thus improving the reliability and precision of positioning. Fuzzy clustering is used to determine the center of radial basis function. In order to reduce the impact of signal fading due to non-line-of-sight and multipath transmission in indoor environment, we improved the Gaussian filter to process received signal strength values. The experimental results show that the proposed method outperforms the existing methods as well as improves the reliability and precision of the RFID indoor positioning system.

Download Full-text

Inertial measurement unit–aided dual-frequency radio frequency identification localization in line-of-sight and non-line-of-sight hybrid environment

International Journal of Distributed Sensor Networks ◽

10.1177/1550147718762033 ◽

2018 ◽

Vol 14 (3) ◽

pp. 155014771876203

Author(s):

Jie Wu ◽

Minghua Zhu ◽

Bo Xiao ◽

Wei He

Keyword(s):

Radio Frequency ◽

Radio Frequency Identification ◽

Inertial Measurement Unit ◽

Signal Strength ◽

Received Signal Strength ◽

Measurement Unit ◽

Line Of Sight ◽

Inertial Measurement ◽

Frequency Identification ◽

Non Line Of Sight

The mitigation of non-line-of-sight propagation conditions is one of main challenges in wireless signal–based indoor localization. When radio frequency identification localization technology is applied in applications, the received signal strength fluctuates frequently due to the shade and multipath effect of radio frequency signal, which could result in localization inaccuracy. In particular, when tag carriers are walking in line-of-sight and non-line-of-sight hybrid environment, great attenuation of received signal strength will happen, which would result in great positioning deviation. The article puts forward a dual-frequency radio frequency identification–based indoor localization approach in line-of-sight–non-line-of-sight hybrid environment with the help of inertial measurement unit. Dual-frequency radio frequency identification includes passive radio frequency identification and active radio frequency identification. Passive radio frequency identification is used to assist in determining the tag initial location with passive reader. Active radio frequency identification is used to locate the tag and send the sensor information to active radio frequency identification readers. The proposed method includes three improvements over previous received signal strength–based positioning methods: inertial measurement unit–aided received signal strength filtering, inertial measurement unit–aided line-of-sight/non-line-of-sight distinguishing, and inertial measurement unit–aided line-of-sight/non-line-of-sight environment switching. Also, Cramér–Rao low bound is calculated to prove theoretically that indoor positioning accuracy for the proposed method in line-of-sight and non-line-of-sight mixed environment is higher than position precision using only received signal strength information. Experiments are conducted to show that the proposed method can reduce the mean positioning error to around 3 m without site survey.

Download Full-text

Indoor localization algorithm based on artificial neural network and radio-frequency identification reference tags

Advances in Mechanical Engineering ◽

10.1177/1687814018808682 ◽

2018 ◽

Vol 10 (12) ◽

pp. 168781401880868 ◽

Cited By ~ 1

Author(s):

Quangang Wen ◽

Yanchun Liang ◽

Chunguo Wu ◽

Adriano Tavares ◽

Xiaosong Han

Keyword(s):

Neural Network ◽

Radio Frequency ◽

Radio Frequency Identification ◽

Signal Strength ◽

Received Signal Strength ◽

Cumulative Distribution ◽

Localization Algorithm ◽

Localization Accuracy ◽

Frequency Identification ◽

Internet Of Things Technology

With the development of Internet of Things technology, radio-frequency identification localization methods have been widely applied due to their low cost and ease of deployment. The indoor radio-frequency identification localization algorithm based on received signal strength indication technology is a currently hot topic. Because the received signal strength is highly dependent on environments, the classic algorithms may result in large errors in localization accuracy. This article proposed a new radio-frequency identification localization algorithm, named BP_LANDMARC, by utilizing the back propagation neural network, which is designed to address nonlinear changes in radio-frequency signals. A strategy for selecting different working parameters in variable environments is presented. The evaluation methods of root mean square error and cumulative distribution function are used to compare the proposed algorithm with some existing algorithms. Experimental results show that the proposed algorithm remarkably improves the localization accuracy of both absolute distance and cumulative probability. Moreover, the proposed algorithm performs effectively and efficiently when it is applied to a logistics warehouse management system.

Download Full-text