Research on Abnormal Detection Method of Network Big Data Flow Based on Track Information
Hao Feng, Rongtao Liao, Wang JingJing, Fen Liu, Zha ZhiYong · 2020
In order to solve this problem, a new anomaly detection method based on trajectory information is proposed. The method of sliding window is used to deal with network big data flow, and the data flow is divided into data blocks. The correlation degree of track information is analyzed to extract data flow features. According to the extracted data flow characteristics, the candidate outliers in the sliding window are verified and the detection method is designed. The experimental results show that the anomaly detection method based on trajectory information has high detection rate and low error detection rate, and its performance is superior.