大型数据库中异常信息检测仿真研究

Simulation Research on Anomaly Detection in Large Databases

对大型数据库中异常信息的检测,可以确保数据库的安全访问和网络运行稳定性。对大型数据库中异常数据的检测,需要获取滤波前的异常信息相位特征,分析数据偏移程度,并对检测滤波模型进行修正,完成异常信息的检测。传统方法通过获取异常信息的线性调频信号幅频特性,建立异常信息传输模型,但忽略了对传输模型进行修正,导致异常信息检测精度偏低。提出基于大数据与决策树分类特征滤波检测的大型数据库中异常信息的检测方法。通过建立大型数据库中异常信息的决策树信息传输模型,采用基于决策树异常分类特征滤波算法,根据局部特征时间尺度参数获取滤波前的异常信息相位特征,分析数据偏移程度,并对检测滤波模型进行修正,最终实现了大型数据库中异常信息的检测。仿真结果表明,提出方法能有效提高大型数据库中异常信息的检测精度和检测效率,具有良好的实用性。

This article proposes a detection method for abnormal information in large database based on filtering detection of classification feature of large data and decision tree. Firstly, the research built information transmission model of decision tree of abnormal information in large database and used filtering algorithm based on abnormal classi- fication feature of decision tree to acquire phase feature of the abnormal information before filtering according to time scale parameter of local feature, then analyzed degree of data deviation. Moreover, the research amended detection fil- tering model. Simulation results show that the method can improve the detection precision and detection efficiency ef- fectively and has better practicability.