Performance Analysis of Morphological Operators Based Feature Extraction and SVD, Neural Networks as Post Classifier for the Classification of Epilepsy Risk Levels
Most research to date using hybrid Models focused on the Multi-Layer Perceptron (MLP). Alternative neural network approaches such as the Radial Basis Function (RBF) and Elman network, and their representations appear to have received relatively little attention. Here we focus on Singular value Decomposition (SVD), RBF and Elman network as an optimizer for classification of epilepsy risk levels obtained from code converter using the EEG signals parameters which are extracted by morphological operators. The obtained risk level patterns from code converters are found to have low values of Performance Index (PI) and Quality Value (QV). These neural networks are trained and tested with 960 patterns extracted from three epochs of sixteen channel EEG signals of twenty known epilepsy patients. Different architectures of MLP, Elman and RBF networks are compared based on the minimum Mean Square Error (MSE), the better networks in MLP (16-16-1) and RBF (1-16-1) are selected. RBF out performs the MLP, Elman network, SVD Technique and code converter with the high Quality Value of 25 when compared to the Quality Values of 23.03, 22.2, 20.62 and 12.74 respectively.
KeywordsEEG signals Morphological operators Code converter SVD RBF MLP Elman neural networks Epilepsy risk levels
The authors express their sincere thanks to the Management and the Principal of Bannari Amman Institute of Technology, Sathyamangalam for providing the necessary facilities for the completion of this paper. This research is also funded by AICTE RPS.:F No 8023/BOR/RID/RPS-41/2009-10, dated 10th Dec 2010.
- 1.Lasemidis LD et al (2003) Adaptive epileptic seizure prediction system. IEEE Trans Biomed Eng 50(5): 616–627Google Scholar
- 3.Qu H, Gotman J (1997) A patient specific algorithm for detection onset in long-term EEG monitoring possible use as warning device. IEEE Trans Biomed Eng 44(2): 115–122Google Scholar
- 5.Harikumar R, Dr, Sukanesh R, Bharathi PA (2005) Genetic algorithm optimization of fuzzy outputs for classification of epilepsy risk levels from EEG signal. J Interdisciplinary Panels 86(1): 1–10Google Scholar
- 6.Mohseni HR, Maghsoudi A, Shamsollahi MB (2006) Seizure detection in EEG signals: A comparison of different approaches. In: Proceedings of the 28th IEEE EMBS annual international conference New York City. 30 Aug– 3 Sep 2006, pp 6724–6727Google Scholar
- 7.Yuan Y (2010) Detection of epileptic seizure based on EEG signals. In: Proceeding of IEEE EMBS sponsored 3rd international congress on image and signal processing (CISP 2010), July 2010, pp 4209–4211Google Scholar
- 8.McCauley-Bell P, Badiru AB (1996) Fuzzy modeling and analytic hierarchy processing to quantify risk levels associated with occupational injuries-Part I: The development of fuzzy-linguistic risk levels. IEEE Trans Fuzzy Syst 4(2): 124–131Google Scholar
- 9.Tarassenko L, Khan YU, Holt MRG (1998) Identification of inter-ictal spikes in the EEG using neural network analysis. IEE Proce Sci Measure Technol 145(6): 270–278Google Scholar
- 10.Yamaguchi T, Fujio M, Inoue K (2008) Feature extraction of EEG waves based on morphological multiresolution analysis. In: Proceedings of 3rd international conference innovative computing information and control (ICICIC’08) IEEE, pp 22–28Google Scholar
- 12.Lee S, Hayes MH (2004) Properties of the singular value decomposition for efficient data clustering. IEEE Signal Process Lett 11(11): 862–866Google Scholar
- 13.Sadasivam PK, Dutt DN (1996) SVD based technique for noise reduction in electroencephalographic signals. Elsevier Signal Process 55: 179–189Google Scholar
- 14.Haykin S (1999) Neural networks a comprehensive foundation, 2nd edn. Prentice- Hall Inc, New JerseyGoogle Scholar
- 15.Hwang YS et al (1997) Recognition of unconstrained handwritten numerals by a radial basis function network classifier. Pattern Recogn Lett 18: 657–664Google Scholar