Design And Implementation Of Information Security Configuration Verification System

With the increasing number of vehicles,the traffic congestion of most cities and highways at home and abroad is becoming more and more serious,this phenomenon seriously affected people's daily work and life.In order to solve the problem of traffic congestion,Intelligent Transportation Systems is widely used to alleviate the congestion.With the improvement of traffic data collection technology,it is possible to make a large number of historical data be a prediction sample of traffic state.Traffic state prediction is a very important part of traffic management in Intelligent Transportation Systems,which is the prerequisite of traffic guidance.Therefore,the study of traffic state prediction plays a very important role in traffic planning and traffic control optimization.In this paper,the parameter "velocity" which reflects the most direct traffic condition is chosen as the parameter of state prediction.Aiming at the shortcomings of the existing velocity prediction methods,a velocity prediction model based on the fusion of KNN-HA and KNN-RBF is proposed.First,the KNN-HA method and KNN-RBF method are used to predict the speed of the predicted road sections,and the results of the workday and the weekend are obtained respectively.According to the morning and evening peak,the day is divided into five time periods,comparing the prediction accuracy of the two methods in each time period,we get the speed prediction algorithm based on the two algorithms;Secondly,the method is compared with the neural network algorithm(NN)and the support vector regression algorithm(SVR).The prediction model proposed in this paper is superior to other prediction models,and its accuracy is 11% higher than that of the support vector regression algorithm,6% higher than the KNN-RBF algorithm;Finally,the traffic state is divided into five states according to the speed threshold,and the traffic state of the road is judged by the forecasting speed.The consistency between the predicted value and the actual traffic state is compared,and the prediction accuracy reached 91.7%.