Research On Identification And Localization Technology Of IoT Terminals

With the continuous development of information and communication technology,Internet of Things technology has been widely used in both military and civil fields.Because of the massive connection characteristic of the Internet of Things,the security problems caused by Io T terminals become more and more serious.It brings great challenges to the cyberspace security of the country and the military.Therefore,it is of great military significance and value to carry out research on Io T countermeasure.Focusing on the cyberspace security of Io T,this dissertation mainly studies on the identification and localization technology of Io T terminals in the field of Io T countermeasure.Firstly,the dissertation introduces the research background and significance of the subject,as well as the research status at home and abroad.And the main research object of the subject is defined.Then,the basic knowledge of NB-Io T,active terminal detection and identification technology and Io T terminal localization algorithms are elaborated in the dissertation.And the performance evaluation indexes of localization algorithms are given.Finally,the dissertation achieves in-depth research on the contents of Io T terminal detection and identification,static and dynamic Io T terminal localization respectively.Firstly,according to the problems of the traditional active terminal detection and identification technology such as poor concealment and low terminal handover success rate,as well as low detection efficiency of passive terminal detection and identification technology,the dissertation proposes a detection and identification technical way of Io T terminals based on Man-in-the-Middle technology.The disguised access point of Io T terminals is firstly established by parameter optimization configuring and network camouflaging.Then,the Tracking Area Code is updated to make Io T terminals in coverage area carry out updating their locations.In the signaling interaction process,the identity information of terminals is acquired from the wireless link in real time.The experiments verify that the technology has higher successful rate of detection and identification.drosophila optimization algorithm in the static Internet of things terminal positioning.Secondly,in view of low accuracy and slow convergence speed of the current mainstream fruit fly optimization algorithm of static Io T terminal localization algorithms,the dissertation proposes a localization algorithm based on improved fruit fly optimization algorithm.In this algorithm,the problem of terminal localization is transformed into a constrained optimization problem.At first,the Bounding-Box algorithm is adopted to limit the initial searching range of fruit fly population.Then,the taste concentration function of the algorithm is reconstructed to improve localization accuracy.At last,the performance of the algorithm is verified by simulation.The results show that compared to previous algorithms,the improved algorithm has faster convergence speed,better localization accuracy and higher stability,the algorithm can meet the localization requirements of static Io T terminals.Finally,aiming at the disadvantage that classical least square support vector regression(LSSVR)algorithm is difficult to determine the optimal parameters in dynamic Io T terminal localization algorithms,the dissertation proposes a localization algorithm based on improved particle swarm optimization algorithm to optimize least square support vector regression machine.Firstly,LSSVR is adopted to build localization model.Then,inertia weight and learning factors are adaptively adjusted to improve optimization performance of particle swarm optimization algorithm.And it is applied to optimize the parameters of LSSVR for avoiding the blindness.Finally,according to RSSD ranging technology,distance vectors are obtained in the process of terminal movement,which are input into LSSVR localization model to estimate the location information of target terminals.The simulation results show that the algorithm proposed has relatively better localization accuracy,higher stability and real-time performance.