A Method of Data Flow Anomaly Detection and Multiple Verification Based on Enhanced Angle Anomaly Factor

Abstract

The invention discloses a data flow abnormality detection and multiple verification method based on an enhancement-type angle abnormality factor, and the method comprises the following steps: 1), carrying out the processing of a real-time data flow; 2), setting a data set S in a sliding window; 3), initializing parameters k, r, and zeta; 4), obtaining a distance matrix dist; 5), obtaining an r neighborhood point set; 6), obtaining an angle factor (shown in the description) and local density (shown in the description) of the r neighborhood point set, and obtaining a dissimilarity degree; 8), obtaining a cluster center factor of each data point; 9), obtaining an ownership matrix; 10), determining cluster centers, and carrying out the clustering; 11), carrying out the abnormal detection of all clusters after clustering; 12), carrying out multiple verification. The method employs the sliding window technology and the basic window technology, achieves the construction of a high-efficiency data flow processing model, reduces the occupying rate of the memory, is good in real-time performance, is high in abnormality detection accuracy, and is low in time complexity.

Description

technical field [0001] The invention relates to data flow abnormality detection and data clustering, in particular to a method for data flow abnormality detection and multiple verification based on enhanced angle anomaly factors. Background technique [0002] The rapid development of network technology and the continuous improvement of social informatization have triggered an explosive growth in the amount of information, causing various industries to generate massive, high-speed, dynamic streaming data, such as network intrusion monitoring, business transaction management and analysis, video surveillance , sensor network monitoring, etc. Due to the real-time and unlimited characteristics of dynamic data streams, traditional static data anomaly detection methods can no longer accurately and effectively analyze and process such large-scale and dynamically growing stream data. Therefore, building a real-time and effective anomaly detection method suitable for data streams beco...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the problems of traditional methods such as high time complexity, large memory usage, low efficiency, too much human parameter intervention, and low effectiveness in a multi-dimensional data environment, the present invention provides a data flow anomaly detection based on enhanced angle anomaly factors and multiple authentication methods

Images