The Research Of Real Time Tracking And Arrival Time Prediction Of Subway Based On Smartphone Inertial Sensors

Real-time tracking of subway riding and arrival time prediction will provide great convenience to millions of commuters in metropolitan areas.Traditional approaches using timetables need continuous attentions from the subway riders and are limited to the poor accuracy of estimating the travel time.Recent approaches using mobile devices rely on GSM and WiFi,which are not always available underground.Based on this,we present a system utilizing sensors on mobile devices to provide automatic tracking of subway riding in real time.This system could track multi-status of the user: station entering detection,user position tracking and arrival time prediction.The main contributions of this work are as follows:Firstly,the real-time automatic tracking covers three major aspects of a passenger: detection of entering a station,we analyze the main error source of the inertial navigation system and its propagation deeply.By large amount of experiments,we prove that the error of gyroscope is the main source of error in navigation and the estimated velocity drift linearly.These conclusions if the foundation of our drift elimination algorithm.Secondly,we propose a station entering detection method based on the distribution of cell tower ID inside and around the station.The proposed method uses less energy comparing to the GPS based method.Thirdly,we propose an attitude double align algorithm based on quaternion considering the usage of the smartphone.Which eliminate the unreasonable assumption that used by previous methods.Also,the real motions of the train can be clearly found in the sampled data after the smartphone has been aligned.Lastly,we can estimate the velocity of the train by accumulate the acc on time after the smartphone has been aligned.Since we know that the velocity will drift linearly in time,we design a drift elimination algorithm based on zero velocity reference points and the history data in the same region.All in all,the proposed system could estimate the train's velocity and the corresponding position,and further predict the arrival time in real time.Our extensive experiments in two cities demonstrate that our system can accurately track the position of subway riders,predict the arrival time.