Abstract
This paper, taking the applying data of financial subsidy for agriculture development as an example, makes use of cluster analysis to set anomalous points detection data stream on the basis of data source and finds the most possible fields which may cause abnormal records; then uses neural network and cluster analysis method respectively to analyze and compare the abnormal records for finding out the data likely carrying the humbug, which could be consulted by management department when making decisions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Li, H.: The Application of One Improved Cluster Method in Abnormal Detection. Microelectronics and Computer (08), 66–69 (2010)
Zhoujunlin: Distributed No-supervising Anomaly Detection Based on Models Sharing. The Transaction in Zhengzhou University (01), 89–92 (2010)
Zhaoliangdong: One Abnormal Detection Method Based on Improved BP Neural Network. Micro-computer Information (28), 216–218 (2010)
Chenbin, Chensongcan: Anomaly Detection Overview. Transaction in Shandong University (06), 13–22 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wu, X., Liu, B., Li, Y. (2012). Application of Neural Network and Cluster Analysis in Anomaly Detection. In: Lei, J., Wang, F.L., Li, M., Luo, Y. (eds) Network Computing and Information Security. NCIS 2012. Communications in Computer and Information Science, vol 345. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35211-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-35211-9_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35210-2
Online ISBN: 978-3-642-35211-9
eBook Packages: Computer ScienceComputer Science (R0)