Anomaly Detection for Symbolic Time Series Representations of Reduced Dimensionality

Abstract—The systematic collection of data has become an
intrinsic process of all aspects in modern life. From industrial
to healthcare machines and wearable sensors, an unprecedented
amount of data is becoming available for mining and information
retrieval. In particular, anomaly detection plays a key role in a
wide range of applications, and has been studied extensively.
However, many anomaly detection methods are unsuitable in
practical scenarios, where streaming data of large volume arrive

in nearly real-time at devices with limited resources. Dimension-
ality reduction has been excessively used to enable efficient pro-
cessing for numerous high-level tasks. In this paper, we propose

a computationally efficient, yet highly accurate, framework for
anomaly detection of streaming data in lower-dimensional spaces,
utilizing a modification of the symbolic aggregate approximation
for dimensionality reduction and a statistical hypothesis testing
based on the Kullback-Leibler divergence.