Combining Temporal and Frequency based Prediction for EEG Signals

This paper presents a novel approach for electroencephalogram (EEG) signal prediction. It combines temporal and frequency based prediction to achieve a good final prediction result. Artificial neural networks are used as the predictive model for signals both in the temporal and frequency domain. In frequency based prediction, the amplitude and the phase of the frequency response are predicted separately. Experiments were conducted on the prediction of EEG data recorded from 13 subjects. Eight performance measures were used to evaluate the performance of our proposed method. Experiment results show that the proposed combined prediction method gives the overall best performance compared with the temporal based prediction alone and the frequency based prediction alone.

[1]  Katarzyna J. Blinowska,et al.  Non-linear and linear forecasting of the EEG time series , 1991, Biological Cybernetics.

[2]  C.G. Puntonet,et al.  Time series prediction using ICA algorithms , 2003, Second IEEE International Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications, 2003. Proceedings.

[3]  T.M. McGinnity,et al.  Extracting features for a brain-computer interface by self-organising fuzzy neural network-based time series prediction , 2004, The 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Yi-Sheng Zhu,et al.  Detecting the Determinism of EEG Time Series Using a Nonlinear Forecasting Method , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[5]  R. Stepien,et al.  Testing for non-linearity in EEG signal of healthy subjects. , 2002, Acta neurobiologiae experimentalis.

[6]  E. Vaadia,et al.  Midbrain dopamine neurons encode decisions for future action , 2006, Nature Neuroscience.

[7]  Masatoshi Nakamura,et al.  Nonlinear Markov process amplitude EEG model for nonlinear coupling interaction of spontaneous EEG , 2000, IEEE Transactions on Biomedical Engineering.

[8]  H. Poizner,et al.  Probabilistic reversal learning is impaired in Parkinson's disease , 2009, Neuroscience.

[9]  Yun Wu,et al.  The Combining Kernel Principal Component Analysis with Support Vector Machines for Time Series Prediction Model , 2008, 2008 Second International Symposium on Intelligent Information Technology Application.

[10]  H. Robbins.  Some aspects of the sequential design of experiments , 1952 .

[11]  M. Coles,et al.  Event-related brain potentials: An introduction. , 1995 .

[12]  Girijesh Prasad,et al.  Neural time-series prediction preprocessing meets common spatial patterns in a brain-computer interface , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  R. Tuduce,et al.  Application of neural networks, PCA and feature extraction for prediction of nucleotide sequences by using genomic signals , 2008, 2008 9th Symposium on Neural Network Applications in Electrical Engineering.

[14]  Ravi Sankar,et al.  Time Series Prediction Using Support Vector Machines: A Survey , 2009, IEEE Computational Intelligence Magazine.

[15]  F. Mormann,et al.  Seizure prediction: the long and winding road. , 2007, Brain : a journal of neurology.