| Current IDS estimates just whether the intrusion happened or not.Those IDSes can not guarantee that the key services work in gear.Aim at the above problems, Cloud theory proposed by academician Lide is integrated into intrusion detection system in this paper to construct the map from qualitative concept knowledge to quantitative data.This study describes the states of Performance Index qualitatively using Cloud Theory and the Weighted Mean Method for Multi-Sensor.In this way, the mathematical transform between qualitative description to quantitative description and the qualitative description intrusion detection system based on Cloud theory is proposed.Partition of discrete numerical interval is the foundation of Qualitative evaluation cloud generator.A new method- Local Outlier Coefficient Wave(LOCW)is proposed to make off partition of discrete numerical interval based on intrusion detecsion,Cloud theory and data mining in order to pretreat the original samples and calculat the local outlier coefficient of each data.LOCW keeps original distribution of data.The partitioned intervals have advantages of data aggregation in an interval and data sparse in different intervals.The experiment result shows the validity of the proposed method.In this paper,a new decision method to estimate the grade of system intrusion possibility is proposed,which is based on PC-LINMAP and cloud theory.Firstly,the index of system performance will be given weighted values by using PC-LINMAP Theory,and these computed weighted values will be compared and fused with the values out from index of system performance in ideal condition.Then this result of comprehensive assessment in ideal conditions could be obtained.Following next,the variation could be obtained by the comparison of real time's weighted fusion values with comprehensive assessment in ideal condition at each specific moment.Finally, the Cloud Generator which is based on Cloud Theory combined with the above variation can achieve the qualitative description about the damage degree of current system intrusion possibility.The result of experimentation shows that this method is effective. |