Detecting novelties in time series through neural networks forecasting with robust confidence intervals

Abstract Novelty detection in time series is an important problem with application in a number of different domains such as machine failure detection and fraud detection in financial systems. One of the methods for detecting novelties in time series consists of building a forecasting model that is later used to predict future values. Novelties are assumed to take place if the difference between predicted and observed values is above a certain threshold. The problem with this method concerns the definition of a suitable value for the threshold. This paper proposes a method based on forecasting with robust confidence intervals for defining the thresholds for detecting novelties. Experiments with six real-world time series are reported and the results show that the method is able to correctly define the thresholds for novelty detection.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Sameer Singh,et al.  Novelty detection: a review - part 1: statistical approaches , 2003, Signal Process..

[3]  Jingtao Yao,et al.  A case study on using neural networks to perform technical forecasting of forex , 2000, Neurocomputing.

[4]  Germano C. Vasconcelos,et al.  An investigation of feedforward neural networks with respect to the detection of spurious patterns , 1995 .

[5]  Eamonn J. Keogh,et al.  HOT SAX: efficiently finding the most unusual time series subsequence , 2005, Fifth IEEE International Conference on Data Mining (ICDM'05).

[6]  Jukka Saarinen,et al.  Time Series Prediction with Multilayer Perception, FIR and Elman Neural Networks , 1996 .

[7]  Lutz Prechelt,et al.  PROBEN 1 - a set of benchmarks and benchmarking rules for neural network training algorithms , 1994 .

[8]  Kyoung-jae Kim,et al.  Financial time series forecasting using support vector machines , 2003, Neurocomputing.

[9]  Bernhard Schölkopf,et al.  Support Vector Method for Novelty Detection , 1999, NIPS.

[10]  Lijuan Cao,et al.  Support vector machines experts for time series forecasting , 2003, Neurocomputing.

[11]  Risto Miikkulainen,et al.  Intrusion Detection with Neural Networks , 1997, NIPS.

[12]  Chris Chatfield,et al.  The Analysis of Time Series: An Introduction , 1990 .

[13]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[14]  Stephen R. Marsland,et al.  On-line novelty detection for autonomous mobile robots , 2005, Robotics Auton. Syst..

[15]  Eija Koskivaara.  Artificial neural network models for predicting patterns in auditing monthly balances , 1997, ECIS.

[16]  Mats Jackson,et al.  Application of infrared technology for quality control of diesel engine glow plugs , 2005 .

[17]  Timothy Masters,et al.  Neural, Novel & Hybrid Algorithms for Time Series Prediction , 1995 .

[18]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2004 .

[19]  Eija Koskivaara.  Artificial Neural Networks in Auditing : State of the Art , 2003 .

[20]  Cyrus Shahabi,et al.  TSA-tree: a wavelet-based approach to improve the efficiency of multi-level surprise and trend queries on time-series data , 2000, Proceedings. 12th International Conference on Scientific and Statistica Database Management.

[21]  Sameer Singh,et al.  An approach to novelty detection applied to the classification of image regions , 2004, IEEE Transactions on Knowledge and Data Engineering.

[22]  D. Dasgupta,et al.  Combining negative selection and classification techniques for anomaly detection , 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600).

[23]  Germano C. Vasconcelos,et al.  Investigating feedforward neural networks with respect to the rejection of spurious patterns , 1995, Pattern Recognit. Lett..

[24]  J. Ma,et al.  Time-series novelty detection using one-class support vector machines , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[25]  Sameer Singh,et al.  Novelty detection: a review - part 2: : neural network based approaches , 2003, Signal Process..

[26]  Eamonn J. Keogh,et al.  Finding surprising patterns in a time series database in linear time and space , 2002, KDD.

[27]  Dipankar Dasgupta,et al.  Neuro-Immune and Self-Organizing Map Approaches to Anomaly Detection: A Comparison , 2002 .

[28]  Heow Pueh Lee,et al.  Modified support vector novelty detector using training data with outliers , 2003, Pattern Recognit. Lett..

[29]  A.L.I. Oliveira,et al.  Improving novelty detection in short time series through RBF-DDA parameter adjustment , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[30]  Michael Y. Hu,et al.  Forecasting with artificial neural networks: The state of the art , 1997 .

[31]  Silvio Romero de Lemos Meira,et al.  A Method Based on RBF-DDA Neural Networks for Improving Novelty Detection in Time Series , 2004, FLAIRS Conference.

[32]  Silvio Romero de Lemos Meira,et al.  Novelty Detection for Short Time Series with Neural Networks , 2003, HIS.

[33]  Silvio Romero de Lemos Meira,et al.  Combining MLP and RBF Neural Networks for Novelty Detection in Short Time Series , 2004, MICAI.

[34]  S. Marsland.  Novelty Detection in Learning Systems , 2008 .

[35]  Dipankar Dasgupta,et al.  Novelty detection in time series data using ideas from immunology , 1996 .