Call for Paper - January 2023 Edition
IJCA solicits original research papers for the January 2023 Edition. Last date of manuscript submission is December 20, 2022. Read More

A New Quantum Radial Wavelet Neural Network Model Applied to Analysis and Classification of EEG Signals

Print
PDF
International Journal of Computer Applications
© 2014 by IJCA Journal
Volume 85 - Number 7
Year of Publication: 2014
Authors:
Saleem M. R. Taha
Abbas K. Nawar
10.5120/14851-3216

Saleem M R Taha and Abbas K Nawar. Article: A New Quantum Radial Wavelet Neural Network Model Applied to Analysis and Classification of EEG Signals. International Journal of Computer Applications 85(7):7-11, January 2014. Full text available. BibTeX

@article{key:article,
	author = {Saleem M. R. Taha and Abbas K. Nawar},
	title = {Article: A New Quantum Radial Wavelet Neural Network Model Applied to Analysis and Classification of EEG Signals},
	journal = {International Journal of Computer Applications},
	year = {2014},
	volume = {85},
	number = {7},
	pages = {7-11},
	month = {January},
	note = {Full text available}
}

Abstract

In this paper, a new model of multi-level transfer function radial wavelet neural network using quantum computing is achieved. This model is applied to analyze and classify the electroencephalographic (EEG) signals. The independent component analysis (ICA) is used as processing after normalization of these signals. Some features are extracted from the data using the clustering technique (CT). A new factor that combines the accuracy and the time of classification is suggested to evaluate the performance of the proposed model with other previous models. This factor represents the accuracy to time ratio (ATR). The average accuracy of the proposed quantum radial wavelet neural network (QRWNN) model is 90. 5619125% at 50 minutes. The ATR value is 1. 8112, which shows the superiority of the proposed model.

References

  • Taha, Z. K. 2012 Quantum Neural Network Model with Wavelet Theory. M. Sc. Thesis. Electrical Engineering Dept. , University of Baghdad.
  • Ropper, A. H. and Brown, R. H. 2011 Adams and Victor's Principles of Neurology, 8th edition.
  • Karayiannis, N. B. and Purushothaman, G. 1997. Quantum neural networks (QNN's): inherently fuzzy feed forward neural networks, IEEE Transactions on Neural Networks, vol. 8, no. 3.
  • More on Regression Gradient Descent Classification. COMP-652 Lecture 2, September 6, 2005. Available: http://www. facweb. litkgp. ernet. in/~sudeshna/courses/
  • Mahdi, A. A. H. 2010 The Application of Neural Network in Financial Time Series Analysis and Prediction Using Immune System. M. Sc. Thesis. School of Computing and Mathematical Sciences, Liverpool John Moores University.
  • EEG Time Series (epileptic data). 2005. Available: http://www. meb. Unibonn. de/epileptologie/science/physikleegdata. html
  • Siuly, Y. L. and Wen, P. 2010. Analysis and classification of EEG signals using a hybrid cluster technique. In Proceedings of the IEE/ICME International Conference on Complex Medical Engineering, Gold Cost, Australia, July 13-15, pp. 34 – 39.
  • Horlings, R. 2008. Emotion Recognition Using Brain Activity. Man-machine Interaction Group, Delft University of Technology, Faculty of Electrical Engineering, Mathematics, and Computer Science.
  • Principal Component Analysis (PCA) and Independent Component Analysis (ICA). Available: http://www. cis. hut. fi/projects/ica/fastica/