EEG Discrimination with Artificial Neural Networks

Sérgio Daniel Rodrigues, João Paulo Teixeira, Pedro Miguel Rodrigues

2013

Abstract

Neurodegenerative disorders associated with aging as Alzheimer’s disease (AD) have been increasing significantly in the last decades. AD affects the cerebral cortex and causes specific changes in brain electrical activity. Therefore, the analysis of signals from the electroencephalogram (EEG) may reveal structural and functional deficiencies typically associated with AD. This study aimed to develop an Artificial Neural Network (ANN) to classify EEG signals between cognitively normal control subjects and patients with probable AD . The results showed that the EEG can be a very useful tool to obtain an accurate diagnosis of AD. The best results were performed using the Power Spectral Density (PSD) determined by Short Time Fourier Transform (STFT) with a ANN developed using Levenberg - Marquardt training algorithm, Logarithmic Sigmoid activation function and 9 nodes in the hidden layer (correlation coefficient training: 0.99964, test: 0.95758 and validation: 0.9653 and with a total of: 0.99245).

References

  1. Baker, M., Akrofi, K., Schiffer, R., and Michael, W. O. B. (2008). Eeg patterns in mild cognitive impairment (mci) patients. Open Neuroimag J., 2:52-55.
  2. Blennow, K. (2005). Amesterda˜o: European College of Neuropsychopharmacology. ECNP.
  3. Blennow, K., Leon, M., and Zetterberg, H. (2006). Alzheimer's disease. The Lancet, 368:387-403.
  4. Feldman, H. and Woodward, M. (2005). The staging and assessment of moderate to severe alzheimer disease. Neurology, 65:10-17.
  5. Hagan, M. T. and Menhaj, M. (1994). Training feedforward networks with the marquardt algorithm. IEEE Transactions on Neural Networks, 5:989-993.
  6. Hort, J., O'Brien, J. T., Gainotti, G., Pirttila, T., Popescu, B. O., Rektorova, I., Sorbi, S., and Scheltens, P. (2010). Efns guidelines for the diagnosis and management of alzheimer's disease. European Journal of Neurology, 17:1236-1248.
  7. Jeong, J. (2004). Eeg dynamics in patients with alzheimer's disease. Clin. Neurophysiol, 115:1490-1505.
  8. Marquardt, D. (1963). An algorithm for least-squares estimation of nonlinear parameters. SIAM Journal on Applied Mathematics, 11:431-441.
  9. Melissant, C., Ypma, A., Frietman, E., and Stam, C. (2005). A method for detection of alzheimer's disease using icaenhanced eeg measurements. Artif Intell Med, 33:209- 222.
  10. Moreira, P. and Oliveira, C. (2005). A Doenc¸a de Alzheimer e outras Demeˆncias em Portugal, chapter Fisiopatologia da doenc¸a de Alzheimer e de outras demeˆncias., pages 41-60. Lisboa: Lidel Edic¸o˜es Técnicas.
  11. Riedmiller, M. and Braun, H. (1993). A direct adaptive method for faster backpropagation learning: The rprop algorithm. Proceedings of the IEEE International Conference on Neural Networks, 1:586-591.
  12. Rioul, O. and Vetterli, M. (1992). Wavelets and signal processing. IEEE Signal Processing Magazine, 8:14-38.
  13. Rodrigues, P. (2011). Diagnóstico da doenc¸a de alzheimer com base no electroencefalograma. Master's thesis, Instituto Politénico de Braganc¸a - Escola Superior de Tecnologia e Gesta˜o.
  14. Rodrigues, P. and Teixeira, J. (2011). Artificial neural networks in the discrimination of alzheimer's disease. Communications in Computer and Information Science, 221:272-281.
  15. Rodrigues, P., Teixeira, J., Hornero, R., Poza, J., and Carreres, A. (2011). Classification of alzheimer's electroencephalograms using artificial neural networks and logistic regression. Japan - Portugal Nano-Biomedical Engineering Symposium 2011, 1(ISBN-4-904157-20- 6):33-34.
  16. Stahl, S. (2008). Stahl's Essential Psychopharmacology. Neuroscientific Basis and Practical Applications. Cambridge University Press, third edition.
  17. Vialatte, F., Cichocki, A., Dreyfus, G., Musha, T., Rutkowski, T., and Gervais, R. (2005a). Blind early detection of alzheimer's disease by blind source separation and bump modelling of eeg signals. Lectues Notes in Computer Science, 3596:683-692.
  18. Vialatte, F., Cichocki, A., Dreyfus, G., Musha, T., Shishkin, S., and Gervais, R. (2005b). Early detection of alzheimer's disease by blind source separation, time frequency representation, and bump modeling of eeg signals. Lecture Notes in Computer Science, 3696:683- 692.
  19. Vialatte, F., Maurice, M., and Cichocki, A. (2008). Why sparse bump models? Neuroimage, 41:159.
Download


Paper Citation


in Harvard Style

Daniel Rodrigues S., Paulo Teixeira J. and Miguel Rodrigues P. (2013). EEG Discrimination with Artificial Neural Networks . In Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013) ISBN 978-989-8565-36-5, pages 236-241. DOI: 10.5220/0004249702360241


in Bibtex Style

@conference{biosignals13,
author={Sérgio Daniel Rodrigues and João Paulo Teixeira and Pedro Miguel Rodrigues},
title={EEG Discrimination with Artificial Neural Networks},
booktitle={Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013)},
year={2013},
pages={236-241},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004249702360241},
isbn={978-989-8565-36-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bio-inspired Systems and Signal Processing - Volume 1: BIOSIGNALS, (BIOSTEC 2013)
TI - EEG Discrimination with Artificial Neural Networks
SN - 978-989-8565-36-5
AU - Daniel Rodrigues S.
AU - Paulo Teixeira J.
AU - Miguel Rodrigues P.
PY - 2013
SP - 236
EP - 241
DO - 10.5220/0004249702360241