Anomaly Detection in Wireless Sensor Networks
share
Wireless sensor networks usually comprise a large number of sensors monitoring changes in variables. These changes in variables represent changes in physical quantities. The changes can occur for various reasons; these reasons are highlighted in this work. Outliers are unusual measurements. Outliers are important; they are information-bearing occurrences. This work seeks to identify them based on an approach presented in [1]. A critical review of most previous works in this area has been presented in [2], and few more are considered here just to set the stage. The main work can be described as this; given a set of measurements from sensors that represent a normal situation, [1] proceeds by first estimating the probability density function (pdf) of the set using a data-split approach, then estimate the entropy of the set using the arithmetic mean as an approximation for the expectation. The increase in entropy that occurs when strange data is recorded is used to detect unusual measurements in the test set depending on the desired confidence interval or false alarm rate. The results presented in [1] have been confirmed for different test signals such as the Gaussian, Beta, in one dimension and beta in two dimensions, and a beta and uniform mixture distribution in two dimensions. Finally, the method was confirmed on real data and the results are presented. The major drawbacks of [1] were identified, and a method that seeks to mitigate this using the Bhattacharyya distance is presented. This method detects more subtle anomalies, especially the type that would pass as normal in [1]. Finally, recommendations for future research are presented: the subject of interpretability, especially for subtle measurements, being the most elusive as of today.
READ FULL TEXT
