Statistical Anomaly Detection for Train Fleets

AAAI Conferences

We have developed a method for statistical anomaly detection which has been deployed in a tool for condition monitoring of train fleets. The tool is currently used by several railway operators over the world to inspect and visualize the occurrence of event messages generated on the trains. The anomaly detection component helps the operators to quickly find significant deviations from normal behavior and to detect early indications for possible problems. The savings in maintenance costs comes mainly from avoiding costly breakdowns, and have been estimated to several million Euros per year for the tool. In the long run, it is expected that maintenance costs can be reduced with between 5 and 10 % by using the tool.


Statistical Anomaly Detection for Train Fleets

AI Magazine

The tool is currently used by several railway operators across the world to inspect and visualize the occurrence of "event messages" generated on the trains. The anomaly detection component helps the operators quickly to find significant deviations from normal behavior and to detect early indications for possible problems. The method used is based on Bayesian principal anomaly, which is a framework for parametric anomaly detection using Bayesian statistics. The savings in maintenance costs of using the tool comes mainly from avoiding costly breakdowns and have been estimated to be several million Euros per year for the tool. In the long run, it is expected that maintenance costs can be reduced by between 5 and 10 percent with the help of the tool. It has been used for fraud detection and intrusion detection for a long time, but in later years the usage has exploded to all kind of domains, like surveillance, industrial system monitoring, epidemiology, and so on. For an overview of different anomaly-detection methods and applications, see, for example, Chandola, Banerjee, and Kumar (2009). The approach taken in statistical anomaly detection is to use data from (predominantly normal) previous situations to build a statistical model of what is normal. New situations are compared against that model and are considered anomalous if they are too improbable to occur in that model. The Swedish Institute of Computer Science (SICS) has for several years developed methods for statistical anomaly detection based on a framework called Bayesian principal anomaly (Holst and Ekman 2011).


Statistical Anomaly Detection for Train Fleets

AI Magazine

We have developed a method for statistical anomaly detection which has been deployed in a tool for condition monitoring of train fleets. The tool is currently used by several railway operators over the world to inspect and visualize the occurrence of event messages generated on the trains. The anomaly detection component helps the operators to quickly find significant deviations from normal behavior and to detect early indications for possible problems. The savings in maintenance costs comes mainly from avoiding costly breakdowns, and have been estimated to several million Euros per year for the tool. In the long run, it is expected that maintenance costs can be reduced with between 5 and 10 % by using the tool.


Sequential Feature Explanations for Anomaly Detection

arXiv.org Machine Learning

In many applications, an anomaly detection system presents the most anomalous data instance to a human analyst, who then must determine whether the instance is truly of interest (e.g. a threat in a security setting). Unfortunately, most anomaly detectors provide no explanation about why an instance was considered anomalous, leaving the analyst with no guidance about where to begin the investigation. To address this issue, we study the problems of computing and evaluating sequential feature explanations (SFEs) for anomaly detectors. An SFE of an anomaly is a sequence of features, which are presented to the analyst one at a time (in order) until the information contained in the highlighted features is enough for the analyst to make a confident judgement about the anomaly. Since analyst effort is related to the amount of information that they consider in an investigation, an explanation's quality is related to the number of features that must be revealed to attain confidence. One of our main contributions is to present a novel framework for large scale quantitative evaluations of SFEs, where the quality measure is based on analyst effort. To do this we construct anomaly detection benchmarks from real data sets along with artificial experts that can be simulated for evaluation. Our second contribution is to evaluate several novel explanation approaches within the framework and on traditional anomaly detection benchmarks, offering several insights into the approaches.


Learning Ensembles of Anomaly Detectors on Synthetic Data

arXiv.org Machine Learning

The main aim of this work is to develop and implement an automatic anomaly detection algorithm for meteorological time-series. To achieve this goal we develop an approach to constructing an ensemble of anomaly detectors in combination with adaptive threshold selection based on artificially generated anomalies. We demonstrate the efficiency of the proposed method by integrating the corresponding implementation into ``Minimax-94'' road weather information system.