Open AccessResearch on train fingerprint positioning based on LTE-R signal strength
Author(s) -
Ming Luo
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/892/1/012044
Subject(s) - fingerprint (computing) , fingerprint recognition , computer science , position (finance) , positioning system , convergence (economics) , signal (programming language) , artificial intelligence , algorithm , mathematics , finance , economics , geometry , point (geometry) , programming language , economic growth
Being aimed at improving the low accuracy when using WKNN location fingerprint based on LTE-R signal strength value, CPSO algorithm, for its advantage, is applied to optimize the weight. CPSO_WKNN location fingerprint positioning algorithm is proposed to solve the train position coordinates.Through verification by cases, WKNN weight optimized by CPSO algorithm and PSO algorithm are separately analyzed and compared, which proves that CPSO optimizes the weight of WKNN algorithm with faster convergence speed. By fingerprint spacing every 25m, 50m, and 100m, the positions of the train in tunnel environment are solved separately by CPSO_WKNN location fingerprint positioning, PSO_WKNN location fingerprint positioning and WKNN location fingerprint positioning. The simulation results show that the positioning accuracy increases with the decrease of the fingerprint spacing for any of the three positioning methods. Under the same fingerprint spacing and the same accuracy demand, the accuracy level of CPSO_WKNN location fingerprint positioning is the highest. When fingerprint spacing is 25m and CPSO_WKNN location fingerprint is applied, the probability of positioning error less than 10m is 87.8%, and the probability of positioning error less than 25m is 96%, which can meet the demand of high-precision positioning in tunnel environment.