Positioning Technology Research Based On FM

With the rapid development of Internet technology and wireless communication technology and the popularity of smart mobile devices,a wide variety of applications for mobile devices and services appeared,including the application of location based service is gradually into people’s life and play an important role. Wireless location technology as the core technology of location services,is the hotspot and difficulty of attention. This article mainly aims at the existing positioning technology signal coverage is not wide or require expensive hardware faults,FM Radio(FM Radio) is proposed for indoor target positioning,and fused FM and Wi-Fi,play the advantages of different kinds of signals,in order to obtain the best location performance.This article through to the FM and Wi-Fi FM fusion positioning technology research,to obtain the following results and innovations.First of all,In view of the characteristics of the FM radio signal, puts forward a method of positioning based on FM broadcast signal, using the algorithm of Bayesian probability calculation of maximum a posteriori probability method to get the corresponding locating results. With the location fingerprints measured in a practical environment,analyses the basic characteristic of the FM signal from the Angle of positioning. Including device can receive the radio station, FM signal probability distribution,the number of signal intensity and position of the mapping relationship,the influence of the antenna to the signal intensity,the activity of people indoors,the influence of signal intensity, sample size effect on the signal strength. These early preparations for the back of the real scene indoor positioning laid a certain theoretical basis.Secondly,through the research of the problem of FM positioning error found that FM signal is signal strength can cause migration time,training model and location data is not in the same time,the positioning performance falling obviously.In view of the fast that dynamic changes of Frequency Modulation radio signal have great influence on the positioning,a localization method based on dynamic radio map was proposed. During offline phase,the relationship between radio signal strength of a few calibration points and each reference point was established by multiple linear regression and neural network,and then during online phase,the real-time radio signal strength values at all reference points were predicted based on the radio signal strength collected at calibration points in real-time. Dynamic map of radio frequencywith adaptive ability was established using these two methods, and Bayesian estimation method was used to locate the target. The experimental results show that,compared with static radio map,the multiple linear regression model would reduce the deviation by 9.1%,and the neural network model would reduce the deviation by36.3%,which restrains the negative impact of radio signal’s time-dependent nature to the position performance.Finally,The article combined with the advantages of FM and Wi-Fi,multimode fusion method of positioning were used,puts forward a method of FM and Wi-Fi fusion positioning. This method is better than single FM or Wi-Fi location accuracy,to a certain extent,make up the defects of the Wi-Fi location system.