Design And Implement Of Indoor Positioning System Based On BLE Technology

Nowadays,with the rapid development of technology,almost every one of us has his/her own mobile phone,and hopes that the mobile phones will bring them more convenience.Location based service(LBS)is becoming popular in recent years.This holds out a great prospect for further expansion of LBS in such areas as hospital telenursing,plant asset management and information push technology.So the study of LBS has been an important flied.Tradition Bluetooth technology has not been widely used in the field of indoor location because of its high power consumption,poor penetration and signal transmission distance.However,after the release of 4.0 Bluetooth communication standard,the power consumption,transmission distance,signal strength and other aspects have been significantly improved,and positioning technology has been widely used.This paper studies the design and implementation of indoor positioning on the base of the low-energy Bluetooth technology,the main work and contribution are as follows:(1)This paper proposes a BLE indoor positioning algorithm based on RSSI?BP neural network and fingerprint algorithm.This algorithm modified faults of traditional BP neural network.During collecting fingerprint date in the offline,the paper uses some outlier detection algorithms and the calculating method of RSSI average to ensure the accuracy of fingerprint data.During online location,the distance of space geometry method is proposed to improve tracking accuracy.(2)This paper designs the inverted-F antenna of BLE module and software and hardware of iBeacons.(3)Android mobile client and iBeacons collaborate with each other for data collection and processing.The new algorithm presented in this paper can be used in positioning.Considering the pressure of android mobile client,the server accomplish most work of calculating positioning result.The mobile client is only responsible for the collection and the results display.In this way,it reduces system maintenance costs and improves user experience.The test results of this system show that the average positioning error is about 1.87 m.Compared with other methods reported in some literatures,the average positioning error fells 28%,which meets the basic need of the indoor positioning accuracy.