PERFORMANCE ANALYSIS USING CODE CONVERTER APPROACH AND THE APPLICATION OF APPROXIMATE ENTROPY AS POST CLASSIFIER FOR THE CLASSIFICATION OF EPILEPSY RISK LEVELS FROM EEG SIGNALS
Objective: The electroencephalogram (EEG) is actually a measure of the cumulative firing of neurons in various parts of the brain. The EEG contains
the information with regard to the changes in the electrical potential of the brain which is obtained from a set of recording electrodes. The aim of this
paper is to give a performance analysis by considering the advantage of Code Converter technique and Approximated Entropy (ApEn) is used as a post
classifier for the classification of the epilepsy risk levels obtained from EEG signals.
Methods: The Data Acquisition of EEG signals are done initially from the hospital. Then the code converter approach is presented, as working on
definite alphabets is much easier when compared to that of working on numericals. Finally, ApEn is used as a Post Classifier for the classification of
epilepsy risk levels from EEG signals.
Results: The Performance Index and Quality Values are the two important parameters that are used to assess the performance of the Code Converters
and the Classifier. The Perfect Classification rate of 83.94% is achieved along with an Accuracy of 91.97% and a Quality Value of 18.5.
Conclusion: The computation of this procedure seems to be very simple and versatile. Future works may use different Dimensionality Reduction
techniques to analyze its performance with Approximated Entropy as Post Classifier.
Keywords: Electroencephalogram signals, Code converter, Performance index, Quality values.
1. Niederhauser JJ, Esteller R, Echauz J, Vachtsevanos G, Litt B. Detection of seizure precursors from depth-EEG using a sign periodogram transform. IEEE Trans Biomed Eng 2003;50(4):449-58.
2. Zumsteg D, Wieser HG. Presurgical evaluation: Current role of invasive EEG. Epilepsia 2000;41 Suppl 3:S55-60.
3. Dingle AA, Jones RD, Carroll GJ, Fright RR. A multistage system to detect epileptic form activity in the EEG. IEEE Trans Biomed Eng 1993;40(12):1260-8.
Asian J Pharm Clin Res, Vol 8, Issue 4, 2015, 287-290
Harikumar and Kumar
4. Harikumar R, Narayanan BS. Fuzzy Techniques for Classification of Epilepsy risk level from EEG Signalsâ€, Proceedings of IEEE Tencon â€“ 2003, Conference on Convergent Technologies for the Asia-Pacific Region Bangalore, India 2003;209-13:14-7.
5. Qu H, Gotman J. A patient-specific algorithm for the detection of seizure onset in long-term EEG monitoring: possible use as a warning device. IEEE Trans Biomed Eng 1997;44:115-22.
6. Harikumar R, Sukanesh R, Bharathi PA. Genetic algorithm optimization of fuzzy outputs for classification of epilepsy risk levels from EEG signals. India J Interdiscip Panels 2005;86(1):9-17.
The publication is licensed under CC By and is open access. Copyright is with author and allowed to retain publishing rights without restrictions.