Parkinson's diagnosis from EEG signal spectrogram based on optimized deep features
Subject Areas :Zahra Hekmati 1 , Mohammad Sajedi pour 2 , Zahra Moradineghad 3
1 - Faculty of Engineering, Kazerun Branch, Islamic Azad University, Kazerun, Iran,
2 - Department of Medical Engineering, Faculty of Engineering, Kazerun Branch, Islamic Azad University, Kazerun, Iran
3 - Faculty of Engineering, Kazerun Branch, Islamic Azad University, Kazerun, Iran
Keywords: Parkinson's disease, convolutional neural network, deep learning, EEG signal.,
Abstract :
Parkinson's disease (PD) is a progressive disorder of the nervous system that affects movement. Symptoms begin gradually, sometimes with just a small tremor in one hand that is barely noticeable. In addition to tremors, which are very common, the disorder also usually causes stiffness or slowness of movement. One way to diagnose Parkinson's disease is electroencephalography, which records brain information and diagnoses the disease. Deep learning methods are the most important and common methods for automatic diagnosis without manual intervention. In this paper, using a deep learning method based on a convolutional neural network, features are extracted from the EEG signal spectrogram and then optimized by selecting the best features. Two modes are used to do this: a) 1000 features extracted and top 10 features b) 1000 features extracted and top 20 features, then the modes were examined for diagnosing Parkinson's disease and the necessary simulations were performed. After evaluation, it was concluded that in the second mode (extraction of top 20 features), the support vector machine classification achieved better results with an accuracy of 97.33% for diagnosing Parkinson's than the first mode and the other classifiers. The results indicate that the proposed method is a suitable and efficient method for diagnosing Parkinson's disease using EEG signals
[1] N. Kannathal, C. M. Lim, U. R. Acharya, P. K. Sadasivan, “Entropies for detection of epilepsy in EEG”, Comput. Methods Programs Biomed., vol. 80, no. 3, pp. 187–194, 2005.
[2] L. Pezard, R. Jech, E. Růžička, “Investigation of nonlinear properties of multichannel EEG in the early stages of Parkinson’s disease”, Clin. Neurophysiol., vol. 112, no. 1, pp. 38–45, 2001.
[3] I. T. French, K. A. Muthusamy, “A review of the pedunculopontine nucleus in Parkinson’s disease”, Front. Aging Neurosci., vol. 10, p. 99, 2018.
[4] B. T. Klassen, J. G. Hentz, H. A. Shill, E. Driver-Dunckley, V. G. H. Evidente, M. N. Sabbagh, J. N. Caviness, “Quantitative EEG as a predictive biomarker for Parkinson disease dementia”, Neurology, vol. 77, no. 2, pp. 118–124, 2011.
[5] A. A. Handojoseno, J. M. Shine, T. N. Nguyen, Y. Tran, S. J. Lewis, H. T. Nguyen, “The detection of Freezing of Gait in Parkinson's disease patients using EEG signals based on Wavelet decomposition”, in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. (EMBC), 2012.
[6] P. Miguel, J. Paulo, “Classification of Electroencephalogram Signals Using Artificial Neural Networks”, in Proc. 3rd Int. Conf. Biomed. Eng. Informatics (BMEI), 2010.
[7] N. E. Huang, Z. Shen, S. R. Long, M. C. Wu, H. H. Shih, Q. Zheng, N. Yen, C. C. Tung, H. H. Liu, “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis”, Proc. R. Soc. Lond. Ser. A Math. Phys. Eng. Sci., vol. 454, no. 1971, pp. 903–995, 1998.
[8] W. Chen, J. Zhuang, W. Yu, and Z. Wang, “Measuring complexity using fuzzyEn, ApEn, and SampEn”, Med. Eng. Phys., vol. 31, pp. 61–68, 2009.
[9] M. A. Colominas, G. Schlotthauer, and M. E. Torres, “Improved complete ensemble EMD: a suitable tool for biomedical signal processing”, Biomed. Signal Process. Control, vol. 14, pp. 19–29, 2020.
[10] M. A. Colominas, G. Schlotthauer, M. E. Torres, and P. Flandrin, “Noise-assisted EMD methods in action”, Adv. Adapt. Data Anal., vol. 4, no. 1250025, 2020.
[11] I. Daly, S. J. Nasuto, and K. Warwick, “Brain computer interface control via functional connectivity dynamics”, Pattern Recogn., vol. 45, pp. 2123–2136, 2012.
[12] R. Silva, P. Almeida, C. Santos, “Exploring the complexity of EEG patterns in Parkinson’s disease: Insights into disease progression”, Neurobiol. Aging, vol. 138, p. 39, 2024
