An Anomaly Pattern Detection Method for Sensor Data

Abstract

With the development of the Internet of Things (IOT) technology, a large number of sensor data have been produced. Due to the complex acquisition environment and transmission condition, anomalies are prevalent. Sensor data is a kind of typical time series data, its anomaly refers to not only outliers, but also the anomaly of continuous data fragments, namely anomaly patterns. To achieve anomaly pattern detection on sensor data, the characteristics of sensor data are analyzed including temporal correlation, spatial correlation and high dimension. Then based on these characteristics and the real-time processing requirements of sensor data, a sensor data oriented anomaly pattern detection approach is proposed in this paper. In the approach, the frequency domain features of sensor data are obtained by Fast Fourier Transform, the dimension of the feature space is reduced by describing frequency domain features with statistical values, and the high-dimensional sensor data is processed in time on the basis of Isolation Forest algorithm. In order to verify the feasibility and effectiveness of the proposed approach, experiments are carried out on the open dataset IBRL. The experimental results show that the approach can effectively identify the pattern anomalies of sensor data, and has low time cost while ensuring the high accuracy.