Browsing by Author "Cheboli, Deepthi"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Anomaly detection of time series.(2010-05) Cheboli, DeepthiThis thesis deals with the problem of anomaly detection for time series data. Some of the important applications of time series anomaly detection are healthcare, eco-system disturbances, intrusion detection and aircraft system health management. Although there has been extensive work on anomaly detection (1), most of the techniques look for individual objects that are different from normal objects but do not consider the sequence aspect of the data into consideration. In this thesis, we analyze the state of the art of time series anomaly detection techniques and present a survey. We also propose novel anomaly detection techniques and transformation techniques for the time series data. Through extensive experimental evaluation of the proposed techniques on the data sets collected across diverse domains, we conclude that our techniques perform well across many datasets.Item Detecting Anomalies in a Time Series Database(2009-02-05) Chandola, Varun; Cheboli, Deepthi; Kumar, VipinWe present a comprehensive evaluation of a large number of semi-supervised anomaly detection techniques for time series data. Some of these are existing techniques and some are adaptations that have never been tried before. For example, we adapt the window based discord detection technique to solve this problem. We also investigate several techniques that detect anomalies in discrete sequences, by discretizing the time series data. We evaluate these techniques on a large variety of data sets obtained from a broad spectrum of application domains. The data sets have different characteristics in terms of the nature of normal time series and the nature of anomalous time series. We evaluate the techniques on different metrics, such as accuracy in detecting the anomalous time series, sensitivity to parameters, and computational complexity, and provide useful insights regarding the effectiveness of different techniques based on the experimental evaluation.