Automatic outlier detection for time series: an application to sensor data

Authors:
Sabyasachi Basu;Martin Meckesheimer
Affiliations:
The Boeing Company, The Boeing Math Group, P.O. Box 3707, MS 7L-22, 98124-2207, Seattle, WA, USA;The Boeing Company, The Boeing Math Group, P.O. Box 3707, MS 7L-22, 98124-2207, Seattle, WA, USA
Venue:
Knowledge and Information Systems - Special Issue on Mining Low-Quality Data
Year:
2007

Citing 3
Cited 9

Estimation of time series parameters in the presence of outliers

Technometrics
Time Series Analysis: Forecasting and Control

Time Series Analysis: Forecasting and Control
Guest Editors' Introduction: Information Enhancement for Data Mining

IEEE Intelligent Systems

Anomaly detection: A survey

ACM Computing Surveys (CSUR)
Improving Time Series Forecasting by Discovering Frequent Episodes in Sequences

IDA '09 Proceedings of the 8th International Symposium on Intelligent Data Analysis: Advances in Intelligent Data Analysis VIII
DBOD-DS: distance based outlier detection for data

DEXA'10 Proceedings of the 21st international conference on Database and expert systems applications: Part I
Experimental analysis of IEEE 802.15.4a CSS ranging and its implications

Computer Communications
An adaptive outlier detection technique for data streams

SSDBM'11 Proceedings of the 23rd international conference on Scientific and statistical database management
Online outlier detection for data streams

Proceedings of the 15th Symposium on International Database Engineering & Applications
Efficient estimation of dynamic density functions with an application to outlier detection

Proceedings of the 21st ACM international conference on Information and knowledge management
A framework for nonparametric profile monitoring

Computers and Industrial Engineering
Research issues in outlier detection for data streams

ACM SIGKDD Explorations Newsletter

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this article we consider the problem of detecting unusual values or outliers from time series data where the process by which the data are created is difficult to model. The main consideration is the fact that data closer in time are more correlated to each other than those farther apart. We propose two variations of a method that uses the median from a neighborhood of a data point and a threshold value to compare the difference between the median and the observed data value. Both variations of the method are fast and can be used for data streams that occur in quick succession such as sensor data on an airplane.