JOURNAL BROWSE
Search
Advanced SearchSearch Tips
Exploiting Patterns for Handling Incomplete Coevolving EEG Time Series
facebook(new window)  Pirnt(new window) E-mail(new window) Excel Download
 Title & Authors
Exploiting Patterns for Handling Incomplete Coevolving EEG Time Series
Thi, Ngoc Anh Nguyen; Yang, Hyung-Jeong; Kim, Sun-Hee;
  PDF(new window)
 Abstract
The electroencephalogram (EEG) time series is a measure of electrical activity received from multiple electrodes placed on the scalp of a human brain. It provides a direct measurement for characterizing the dynamic aspects of brain activities. These EEG signals are formed from a series of spatial and temporal data with multiple dimensions. Missing data could occur due to fault electrodes. These missing data can cause distortion, repudiation, and further, reduce the effectiveness of analyzing algorithms. Current methodologies for EEG analysis require a complete set of EEG data matrix as input. Therefore, an accurate and reliable imputation approach for missing values is necessary to avoid incomplete data sets for analyses and further improve the usage of performance techniques. This research proposes a new method to automatically recover random consecutive missing data from real world EEG data based on Linear Dynamical System. The proposed method aims to capture the optimal patterns based on two main characteristics in the coevolving EEG time series: namely, (i) dynamics via discovering temporal evolving behaviors, and (ii) correlations by identifying the relationships between multiple brain signals. From these exploits, the proposed method successfully identifies a few hidden variables and discovers their dynamics to impute missing values. The proposed method offers a robust and scalable approach with linear computation time over the size of sequences. A comparative study has been performed to assess the effectiveness of the proposed method against interpolation and missing values via Singular Value Decomposition (MSVD). The experimental simulations demonstrate that the proposed method provides better reconstruction performance up to 49% and 67% improvements over MSVD and interpolation approaches, respectively.
 Keywords
Multivariate Time Series;Electroencephalogram (EEG);Handling Missing Values;Interpolation;Linear Dynamical System;Kalman Filter;MSVD;Expectation maximization;
 Language
English
 Cited by
 References
1.
N. F. Guler, E. D. Ubeyli, and I. Guler, "Recurrent neural networks employing Lyapunov exponents for EEG signals classification," In Expert System Appl, vol. 29, 2005, pp. 506-514. crossref(new window)

2.
K. Polat and S. Gunes, "Classification of epileptiform EEG using a hybrid system based on decision tree classifier and fast Fourier transform," In Applied Mathematics and Computation-AMC, vol. 187, no. 2, 2006, pp. 1017-1026.

3.
H. Adeli, Z. Zhou, and N. Dadmehr, "Analysis of EEG records in an epileptic patient using wavelet transform," In Journal of Neuroscience methods, vol. 123, 2003, pp. 69-87. crossref(new window)

4.
N. Sivasankari and Dr. K. Thanushkodi, "Automated Epileptic Seizure Detection in EEG signals Using FastICA and Neural Network," In Int. J. Advances, Soft computer, Appl, vol. 1, no. 2, 2009, pp. 91-99.

5.
N. F Guler, E. D Ubeyli, and I. Guler, "Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficient," In Journal of Neuroscience methods, vol. 148, no. 2, 2005, pp. 113-121. crossref(new window)

6.
N. Kannathal, M. L. Choo, U. R. Acharya, and P. K. Sadasivana, "Entropies for detection of epilepsy in EEG," In Computer Methods Programs Biomed, vol. 80, no. 3, 2005, pp. 187-194. crossref(new window)

7.
A. Subasi, "EEG signal classification using wavelet feature extraction and a mixture of expert model," In Expert Systems with Applications, vol.32, no. 4, 2007, pp. 1084-1093. crossref(new window)

8.
E. Acar, D. M. Dunlavy, T. G Kolda, and M. Morup, "Scalable Tensor Factorizations with Missing Data," In Proceedings of the 2010 SIAM International Conference on Data Mining, 2010, pp. 701-702.

9.
A. Sorjamaa, J. Hao, N. Reyhani, Y. Ji, and A. Lendasse, "Methodology for long-term prediction of time series," In Neurocomputing, vol. 70, 2007, pp. 16-18.

10.
C. Chatfield, The Analysis of Time Series: An Introduction, 2008.

11.
C. F. Gerald and P. O. Wheatley, Applied Numerical Analysis in 7th Edition, 2007.

12.
G. Liu and L. McMillan, "Estimation of missing markers in human motion capture," In International Journal of Computer Graphics, vol. 22, no. 9, 2009, pp. 721-728.

13.
S. I. Park and J. K. Hodgins, "Capturing and animating skin deformation in human motion," In ACM Trans. Graph, vol. 25, no. 3, 2006, pp. 881- 889. crossref(new window)

14.
M. Kurucz, A. Benczur, and K. Csalogany, "Method for large scales SVD with missing values," In KDDCup. 07, San Jose, California, USA, 2007.

15.
S. H. Kim, H. J. Yang, and Ng. KamSwee, "Incremental expectation maximization principal component analysis for missing value imputation for coevolving EEG data,"Journal of Zhejiang University-SCIENCE C (Computer & Electronics), vol. 12, no. 8, 2011, pp. 687-697.

16.
S. Guha, D. Gunopulos, and N. Koudas, "Correlating synchronous and asynchronous data stream," In Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining, KDD, 2003.

17.
S. Papadimitriou, J. Sun, and C. Faloutsos, "Streaming pattern discovery in multiple time series," In Proceeding of the 31st VLDB, 2005.

18.
N. S Nati and T. Jaakkola, "Weighted low-rank approximation," In 20th International Conference on Machine Learning, AAAI Press, 2003, pp. 720- 727.

19.
O. Troyanskaya, M. Cantor, G. Sherlock, P. Brown, T. Hastie, R. Tibshirani, D. Botstein, and R. B. Altman, "Missing value estimation methods for DNA microarrays," In Bioinformatics, vol. 7, 2001, pp. 520-525.

20.
C. Phong and R. Singh, "Missing value estimation for time series microarray data using linear dynamical systems modeling," In Advanced Information Networking and Applications-AINA, 2008, pp. 814-819.

21.
A. Aristidou, J. Cameron, and J. Lasenby, "Predicting missing marker to drive real- time center of rotation estimation," In AMDO '08: Proceeding of the 5th international conference on articulated motion and deformable objects, Springer-Verlarg, 2008, pp. 238-249.

22.
K. Dorfmuller-Ulhaas, Robust Optical User Motion Tracking Using a Kalman Filter, In Technique report, Technical Report of Augsburg University, 2003.

23.
R. E. Kalman, "A New Approach to Linear Filtering and Prediction Problems," In Journal of Basic Engineering, vol. 81, 1960, pp. 35-45.

24.
L. Ralaivola and F. d'Alche-Buc, "Time series Filtering, Smoothing and Learning using the Kernel Kalman Filter," In Proceedings of International Joint Conference on Neural Network, Montreal, Canada, 2005.

25.
L. Li, W. Fu, F. Guo, T. C Mowry, and C. Faloutsos, "Cut- And- Stitch: Efficient Parallel Learning of Linear Dynamical Systems on SMPs," In KDD'08, Las Vegas, Nevada, USA, 2008.

26.
L. Li, J. McaCann, N. Pollard, and C. Faloutsos, "Dynammo: Mining and summarization of coevolving sequences with missing values," In KDD, New York, NY, USA, 2009.

27.
R. H. Shumway and D. S. Stoffer, "An approach to time series smoothing and forecasting using the EM algorithm," In Journal of Time Series Analysis, vol. 3, 1982, pp. 253-264. crossref(new window)

28.
R. G. Andrzejak, "Indications of nonlinear deterministic and finite dimensional structures in time series of brain electrical activity," in Physical Review E, 2001.

29.
B. Blankertz, G. Curio, and K. R. Muller, "Classifying Single Trial EEG: Towards Brain Computer Interfacing," In Advances in Neural Inf, 2002.