Abstract
Kepler satellite data is analyzed to detect anomalies within the short cadence light curve using traditional statistical algorithms and neural networks. Windowed mean division normalization is presented as a method to transform non-linear data to linear data. Modified Z-score, general extreme studentized deviate, and percentile rank algorithms were applied to initially detect anomalies. A refined windowed modified Z-score algorithm was used to determine “true anomalies” that were then used to train both a Pattern Neural Network and Recurrent Neural Network to detect anomalies. For speed in detection, trained neural networks have the clear advantage. However, the additional tuning and complexity of training means that unless speed is the primary concern traditional statistical methods are easier to use and equally effective at detection.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aleksander, I., Morton, H.: An introduction to Neural Computing, 2nd edn. Intl Thomson Computer Pr (T), London (1995)
Botros, A.: Artificial intelligence on the final frontier: using machine learning to find new earths. Technical report, Stanford University (2014)
Guo, H., Murphey, Y., Feldkamp, L.: Neural learning from unbalanced data. In: Applied Intelligence, vol. 21, pp. 117–128. Kluwer Academic Publishers (2004)
Iglewicz, B., Hoaglin, D.: The ASQC basic references in quality control: statistical techniques. In: How to Detect and Handle Outliers, vol. 16 (1993)
Lane, D., Scott, D., Hebl, M., Guerra, R., Osherson, D., Zimmer, H.: Introduction to statistics, pp. 29–33. Rice University, University of Houston, Tufts University (2007)
Leiner, E.: Other Worlds: Analyzing the Light Curves of Transiting Extrasolar Planets. Wesleyan University, Thesis (2010)
Mikulski Archive for Space Telescopes: Space Telescope Science Institute. http://archive.stsci.edu/pub/kepler/lightcurves/tarfiles/
Nanduri, A., Sherry, L.: Anomaly detection in aircraft data using recurrent neural networks. In: Integrated Communications Navigation and Surveillance (ICNS) Conference, pp. 5C2 1–8. IEEE Press (2016)
NASA: Kepler: About the Mission. https://kepler.nasa.gov/Mission
Rosner, B.: Percentage points for a generalized ESD many-outlier procedure. Technometrics 25(2), 165–172 (1983)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Grabaskas, N., Si, D. (2017). Anomaly Detection from Kepler Satellite Time-Series Data. In: Perner, P. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2017. Lecture Notes in Computer Science(), vol 10358. Springer, Cham. https://doi.org/10.1007/978-3-319-62416-7_16
Download citation
DOI: https://doi.org/10.1007/978-3-319-62416-7_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-62415-0
Online ISBN: 978-3-319-62416-7
eBook Packages: Computer ScienceComputer Science (R0)