The Entropy and PCA Based Anomaly Prediction in Data Streams

With the increase of data and information, anomaly management has been attracting much more attention and become an important research topic gradually. Previous literatures have advocated anomaly discovery and identification ignoring the fact that practice needs anomaly detection in advance (anomaly prediction) but anomaly detection with post-hoc analysis. Given this apparent gap, this research proposes a new approach for anomaly prediction based on PCA (principle component analysis) and information entropy theory, and support vector regression. The main idea of anomaly prediction is to train the historical data and to identify and recognize outlier data according to previous streams patterns and trends. The explorative results of SO2 concentration of exhaust gas in WFGD (Wet Flue Gas Desulfurization) demonstrate a good performance (efficient and accurate) of the target data prediction approach. This robust and novel method can be used to detect and predict the anomaly in data streams, and applied to fault prediction, credit card fraud prediction, intrusion prediction in cyber-security, malignant diagnosis, etc.