Classification of Multi-Types of EEG Time Series Based on Embedding Dimension Characteristic Parameter

Ye Yuan; Zhi Qiang Huang; Ze Min Cai

doi:10.4028/www.scientific.net/KEM.474-476.1987

Paper Titles

Decision Based on Fuzzy Multi-Objective Programming Method of High-Tech Investment Portfolio
p.1961

Analysis on Cooperative GBN-ARQ Performance in TDMA Single Source and Single Relay Network
p.1966

Improved Large Spring / Stiffness Technique for Dynamic Response Analysis of Structures Subjected to Base Excitations
p.1974

Kinematic Analysis of Feed-Dog Mechanism in Overlock Machine
p.1980

Classification of Multi-Types of EEG Time Series Based on Embedding Dimension Characteristic Parameter
p.1987

Simulation Study on Wastewater Quality of Dongfeng Ditch with Artificial Constructed Rapid Infiltration System
p.1993

Research on a Remote Network Monitoring Model for Large-Scale Materials Manufacturing
p.1999

Estimation on Flux and Power Consumption of Twin Screw Pulping Extruder Based on Dimensional Analysis
p.2004

Research on Weight Reduction Design of the Drive System
p.2008

HomeKey Engineering MaterialsKey Engineering Materials Vols. 474-476Classification of Multi-Types of EEG Time Series...

Classification of Multi-Types of EEG Time Series Based on Embedding Dimension Characteristic Parameter

Abstract:

We have studied the detection of epileptic seizure by EEG signals based on embedding dimension as the input characteristic parameter of artificial neural networks has been studied in the research before. The results of the experiments showed that the overall accuracy as high as 100% can be achieved for distinguishing normal and epileptic EEG time series. In this paper, classification of multi-types of EEG time series based on embedding dimension as input characteristic parameter of artificial neural network will be studied, and the probabilistic neural network (PNN) will be also employed as the classifier for comparing the results with those obtained before. Cao’s method is also applied for computing the embedding dimension of normal and epileptic EEG time series. The results show that different types of EEG time series can be classified using the embedding dimension of EEG time series as characteristic parameter when the number of feature points exceed some value, however, the accuracy were not satisfied up to now, some work need to be done to improve the classification accuracy.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Key Engineering Materials (Volumes 474-476)

Pages:

1987-1992

DOI:

https://doi.org/10.4028/www.scientific.net/KEM.474-476.1987

Citation:

Cite this paper

Online since:

April 2011

Authors:

Ye Yuan, Zhi Qiang Huang, Ze Min Cai

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] N. Mc Grogan. Neural network detection of epileptic seizures in the electroencephalogram, [Online]. Available: http: /www. new. ox. ac. uk/ ˜nmcgroga/work/transfer, (1999).

Google Scholar

[2] M. Bauer, H. Heng, and W. Martienssen: Phys. Rev. W., vol. 71 (1993), pp.521-524.

Google Scholar

[3] V. Srinivasan, C. Eswaran, and N. Sriraam: IEEE Trans. Inf. Technol. Biomed., vol. 11(2007), p.288–295.

Google Scholar

[4] W. Weng and K. Khorasani: Neural Netw., vol. 9 (1996), p.1223–1240.

Google Scholar

[5] R. G. Andrzejak, K. Lehnertz, C. Rieke, F. Mormann, P. David, C. E. Elger: Phys. Rev. E., vol. 64 (2001), 061907.

Google Scholar

[6] L.Y. Cao: Physical D, vol. 110 (1997), pp.43-50.

Google Scholar