Application of clustering techniques for visually evoked potentials based detection of vision impairments

• Autorzy: Vijean V. , M H. , Yaacob S. , Sulaiman M. N. B.

Identyfikatory

DOI

10.1016/j.bbe.2014.02.002

• Języki publikacji: EN

Abstrakty

EN

Visually evoked potentials (VEP) are evoked responses of the brain corresponding to a specific visual stimulus. Ophthalmologists often refer their patients to VEP test if the latter suffers any vision abnormalities that cannot be diagnosed using conventional analysis. By investigating the VEP responses, medical experts can narrow down the possible cause of the defect. Although this method provides valuable information to the medical practitioner, there are several drawbacks of the analysis that can affect the diagnosis result. The conventional averaging of the signals results in inter-trial variation between the VEP responses to be lost. This method also requires large number of trials, which causes fatigue in patients and reduces the diagnostic accuracy. Therefore, we have proposed a new method of analysis using statistical features derived from time and spectral space for the discrimination of vision impairments. Feature enhancement methods such as feature weighting and dimensional reduction are used to enhance the statistical features prior to the analysis. Four clustering methods are employed to increase the interclass separability of the control and myopic features while reducing the within class variability. The dimension of the weighted features is reduced using a combination of principal component analysis (PCA) and independent component analysis (ICA) techniques prior to classification. The proposed method is able to achieve 100% accuracy using extreme learning machine (ELM) and multi layer neural network (MLNN) classifiers.

Słowa kluczowe

EN

visually evoked potential; vision impairment; feature weighting; feature reduction; extreme learning machine; multi layer neural network

PL

potencjał wywołany; zaburzenie widzenia; redukcja cech; uczenie maszynowe; sieć neuronowa wielowarstwowa

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2014
• Tom: Vol. 34, no. 3
• Strony: 169--177
• Opis fizyczny: Bibliogr. 30 poz., tab., wykr.

Twórcy

autor

Vijean V.

• School of Mechatronic Engineering, Universiti Malaysia Perlis (UniMAP), 02600, Campus Pauh Putra, Perlis, Malaysia

autor

M H.

• School of Mechatronic Engineering, Universiti Malaysia Perlis (UniMAP), Perlis, Malaysia

autor

Yaacob S.

• School of Mechatronic Engineering, Universiti Malaysia Perlis (UniMAP), Perlis, Malaysia

autor

Sulaiman M. N. B.

• Ophthalmology Department, Hospital Tuanku Fauziah, Kangar, Perlis, Malaysia

Bibliografia

• [1] Odom JV, Bach M, Brigell M, Holder GE, McCulloch DL, Tormene AP. ISCEV standard for clinical visual evoked potentials (2009 update). Doc Ophthalmol 2009;120(1):111–9.
• [2] Quian Quiroga R, Rosso OA, Baar E, Schürmann M. Wavelet entropy in event-related potentials: a new method shows ordering of EEG oscillations. Biol Cybern 2001;84(4):291–9.
• [3] Ademoglu A, Micheli-Tzanakou E, Istefanopulos Y. Analysis of pattern reversal visual evoked potentials (PRVEP's) by spline wavelets. IEEE T Bio-med Eng 1997;44(9):881.
• [4] Momose K. Determination of the chromatic contrast responses using wavelet analysis of visual evoked potentials. 27th IEEE International Conference in Medicine and Biology Society, Shanghai, China, Sept 1–4; 2005.
• [5] Güven A, Polat K, Kara S, Günes S. The effect of generalized discriminate analysis (GDA) to the classification of optic nerve disease from VEP signals. Comput Biol Med 2008;38 (1):62–8.
• [6] Polat K, Kara S, Güven A, Günes S. Utilization of discretization method on the diagnosis of optic nerve disease. Comput Meth Prog Biol 2008;91(3):255–64.
• [7] Vijean V, Hariharan M, Yaacob S, Sulaiman MZB, Adom AH. Objective investigation of vision impairments using single trial pattern reversal visually evoked potentials. Comput Electr Eng 2013. http://dx.doi.org/10.1016/j.compeleceng.2012.12.022.
• [8] ISCEV. A guide to procedures, ISCEV (visual electrodiagnostics); 2005.
• [9] Palaniappan R, Raveendran P, Nishida S. Multi-channel noise reduced visual evoked potential analysis. IEEJ Trans Electron Inf Syst 2003;123(10):1721–7.
• [10] Ekstein K, Pavelka T. Entropy and entropy-based features in signal processing. Proceedings of PhD Workshop Systems & Control, Balatonfured; 2004.
• [11] Polat K. Application of attribute weighting method based on clustering centers to discrimination of linearly non- separable medical datasets. J Med Syst 2012;36(4):2657–73.
• [12] Srinivasa KG, Venugopal KR, Patnaik LM. Feature extraction using fuzzy c-means clustering for data mining systems. Int J Comput Sci Network Sec 2006;6.3A:230.
• [13] Arjmandi MK, Pooyan M, Mikaili M, Vali M, Moqarehzadeh A. Identification of voice disorders using long-time features and support vector machine with different feature reduction methods. J Voice 2011;25(6):e275–89.
• [14] Bacelar-Nicolau H, Nicolau F, Sousa Á, Bacelar-Nicolau L. Measuring similarity of complex and heterogeneous data in clustering of large data sets. Biocybern Biomed Eng 2009;29(2):9–18.
• [15] Hariharan M, Saraswathy J, Sindhu R, Wan K, Sazali Y. Infant cry classification to identify asphyxia using time– frequency analysis and radial basis neural networks. Expert Syst Appl 2012;39(10):9515–23.
• [16] MacQueen J. Some methods for classification and analysis of multivariate observations. Proc 5th Berkeley Symposium on Mathematical Statistics and Probability. University of California Press; 1967.
• [17] Bakhshi M, Derakhshi MRF, Zafarani E. Review and comparison between clustering algorithms with duplicate entities detection purpose. Int J Comput Sci Emerg Tech 2012;3:108–14.
• [18] Bezdek JC. Pattern recognition with fuzzy objective function algorithms. Norwell, U.S.A.: Kluwer Academic Publishers; 1981.
• [19] Leski J. Towards a robust fuzzy clustering. Fuzzy Set Syst 2003;137(2):215–33.
• [20] Chiu S. Fuzzy model identification based on cluster estimation. J Intell Fuzzy Syst 1994;2:267–78.
• [21] Polat K, Durduran SS. Subtractive clustering attribute weighting (SCAW) to discriminate the traffic accidents on Konya–Afyonkarahisar highway in Turkey with the help of GIS: a case study. Adv Eng Softw 2011;42(7):491–500.
• [22] Yuwono M, Su SW, Moulton B, Nguyen H. Fast unsupervised learning method for rapid estimation of cluster centroids. IEEE Congress on Evolutionary Computation (CEC), Brisbane, Australia, 10–15 Jun. 2012. pp. 1–8.
• [23] Yuwono M, Su SW, Moulton B, Nguyen H. Method for increasing the computation speed of an unsupervised learning approach for data clustering. IEEE Congress on Evolutionary Computation (CEC), Brisbane, Australia, 10–15 Jun. 2012. pp. 1–8.
• [24] Jolliffe I. Principal component analysis. Encyclopedia of statistics in behavioral science. Chichester, UK: John Wiley & Sons, Ltd.; 2005.
• [25] Hariharan M, Fook CY, Sindhu R, Bukhari I, Sazali Y. A comparative study of wavelet families for classification of wrist motions. Comput Electr Eng 2012;38(6):1798–807.
• [26] Giri D, Rajendra UA, Martis RJ, Vinitha SS, Lim TK, Ahamed VT, et al. Automated diagnosis of coronary artery disease affected patients using LDA, PCA, ICA and discrete wavelet transform. Knowl-Based Syst 2013;37(0):274–82.
• [27] Guang-Bin H, Qin-Yu Z, Chee-Kheong S. Extreme learning machine: a new learning scheme of feedforward neural networks. IEEE International Joint Conference on Neural Networks, Budapest, Hungary, 25–29 July; 2004.
• [28] da S, Gomes G, Ludermir T, Lima L. Comparison of new activation functions in neural network for forecasting financial time series. Neural Comput Appl 2011;20(3):417–39.
• [29] Tan T, Teo J, Anthony P. A comparative investigation of non-linear activation functions in neural controllers for search-based game AI engineering. Artif Intell Rev 2011;41:1–25.
• [30] Karlık B, Olgaç AV. Performance analysis of various activation functions in generalized MLP architectures of neural networks. Int J Art Intel Expert Syst 2011;4(1):111–2.