在此基础上，本文提出了一种响应式数据流异常检测方法。
Based on above analysis, a reactive outlier detection approach over data stream has been introduced.
为了提高数据流中异常数据的预测速度与精度，提出一种基于稀疏表示的数据流异常数据预测方法。
This paper proposed a new prediction method for outliers over data stream based on sparse representation to improve the optimum prediction speed and performance of outliers over data stream.
深度数据包处理在一个数据流当中有多个数据包，在寻找攻击异常行为的同时，保持整个数据流的状态。
Deep packet processing has multiple packets in a data stream, while searching for the behavior of the entire data stream.
现在大多数的程序设计语言提供了异常处理机制，但程序中的异常结构会影响数据流分析。
Recently, most program languages have provided the exception handling, but the exception handling in the program can affect data flow analysis.
异常、变化和突发是三类最典型的数据流事件。
Outlier, change and burst are three typical types of events.
提出了一种k-均值聚类算法和SOM自组织神经网络算法相结合的异常检测模型，使得系统可以更好的分类正常数据流和异常数据流，以此来防范未知的攻击。
Secondly, the anomaly detection model based on K-means algorithm and SOM network is constructed. It can classify the normal and abnormal network data stream so better to detect the unknown attack.
提出了一种k-均值聚类算法和SOM自组织神经网络算法相结合的异常检测模型，使得系统可以更好的分类正常数据流和异常数据流，以此来防范未知的攻击。
Secondly, the anomaly detection model based on K-means algorithm and SOM network is constructed. It can classify the normal and abnormal network data stream so better to detect the unknown attack.
应用推荐