Research On Automatic Construction Algorithm Of Radio Map For Wireless Indoor Localization

According to research data indicate that people spend more than 80%of their time indoors,stimulating the flourishing markets and increasing demand of Location-based Services(LBS).For the latest 15 years,Indoors Positioning System has not only been a heated topic of academic world but also highly favored in the commercial world.With so many years of indoors positioning system's development,the techniques are now various.But under the background of intelligent terminal's rapid development and wide deployment of Wi-Fi and on the premise of the advantages of indoors positioning techniques based on radios,the technique of Wi-Fi and radios indoors positioning technique is now the top choice of indoors positioning service.Site investigation,which is used to make a radio map,is a must in radio positioning.However it'll take enormous labor and time,greatly restricting the development and application range of radio indoors positioning technique.Therefore it's of great significance to improve the efficiency of radio mapping and lower the cost.Leveraging crowdsensed user mobility,we design an automatic method for radio map construction method,which eliminates the efforts of time-consuming and labor-intensive site survey by the participatory sensing of a number of mobile users.The proposed scheme significantly decreases the deployment costs of fingerprint-based localization.Results from real experiments demonstrate that comparable performance can be achieved by automatically built radio maps compared with manually calibrated ones.This thesis emphasizes the client's movement path generation and auto radio mapping.Here are the main research contents:1.The indoors positioning technique is summarized and analyzed.Elaborated the advantages of Wi-Fi and radio indoors positioning and pointed out the significance of lowering mapping cost and further analyzed the deficiencies of this aspect at present.2.The self-adjust FSM-DTW step counting algorithm based on dynamic threshold is puted forward.By acceleration amplitude to distinguish human body's different states of motion,according to which we respectively count steps using self-adjust FSM algorithm based on dynamic threshold,and use DTW algorithm to denoise the result of step counting.Experiments proved the accuracy of this algorithm,which also helps auto radio mapping.3.Leveraging crowdsensed user mobility,by using movement path and radio information collected from client's daily life and work,we put forward a descending dimension algorithm IDR-MDS based on the immeasurable distance reconstruction to generate radio space then project the radio space to physical locational space,making radio point overlap physical location so that we can build a radio map.Results from real experiments demonstrate that comparable performance can be achieved by automatically built radio maps compared with manually calibrated ones.