物联网通信异常数据的检测方法研究

Research on abnormal data detection method of IOT communication

在物联网多设备通信过程中,其差异化的数据在分类种类上存在较大的问题,导致识别过程存在异常数据不收敛或者无穷计算的问题。为了解决这一问题,提出基于多约束标签的异常数据检测方法,在对海量的异常数据进行分类的过程中,引入可以约束标签异常特征的多个约束条件,对物联网通信数据进行降维限制处理,避免扩大化的搜索过程,再运用支持向量机在限制区域内完成检测分类。实验结果表明,利用该算法能对海量的物联网通信异常数据进行自动学习过程的搜索,提高异常数据检测的准确性。

The differentiated data has a great problem of classification variety in the Internet of Things(IOT)multi-device communication process,and causes the abnormal datadivergence or infinite calculation in the identification process.In order to solve these problems,an abnormal data detection method based on multi?constraint label is put forward.The multi-constraint condition which can restrain the label′s abnormal feature is introduced into the classification process of the massive abnormal data.The dimension reduction of the IOT communication data is limited to avoid the expansion of the search process.The support vector machine(SVM)is used to classify and detect the abnormal data in the restricted areas.The experimental results show that the algorithm can search the massive abnormal data in IOT communication by means of automatic learning process,and improve the accaracy of abnormal data detection.