Automated Pre-Seizure Detection for Epileptic Patients Using Machine Learning Methods

Full Text (PDF, 936KB), PP.1-9

Views: 0 Downloads: 0


Sevda GUl 1,* Muhammed K. UCAR 1 Gokcen Cetinel 1 Erhan BERGIL 2 Mehmet R. BOZKURT 1

1. Electrical-Electronics Engineering, Sakarya University, Esentepe, Sakarya 54187, Turkey

2. Technical Sciences Vocational School, Amasya University, Amasya, 05189, Turkey

* Corresponding author.


Received: 2 Mar. 2017 / Revised: 21 Apr. 2017 / Accepted: 26 May 2017 / Published: 8 Jul. 2017

Index Terms

Epilepsy, Pre-seizure detection, Systematic Sampling, Eta Correlation, k-Nearest neighbors classification


Epilepsy is a neurological disorder resulting from unusual electrochemical discharge of nerve cells in the brain, and EEG (Electroencephalography) signals are commonly used today to diagnose the disorder that occurs in these signals. In this study, it was aimed to use EEG signals to automatically detect pre-epileptic seizure with machine learning techniques. EEG data from two epileptic patients were used in the study. EEG data is passed through the preprocessing stage and then subjected to feature extraction in time and frequency domain. In the feature extraction step 26 features are obtain to determine the seizure time. When the feature vector is analyzed, it is observed that the characteristics of the pre-seizure and non-seizure period are unevenly distributed. A systematic sampling method has been applied for this imbalance. For the balanced data, two test sets with and without Eta correlation are established. Finally, the classification process is performed using the k-Nearest Neighbor classification method. The obtained data are evaluated in terms of Eta-correlated and uncorrelated accuracy, error rate, precision, sensitivity and F-criterion for each channel. 

Cite This Paper

Sevda GÜl, Muhammed K. UÇAR, Gökçen ÇETİNEL, Erhan BERGİL, Mehmet R. BOZKURT,"Automated Pre-Seizure Detection for Epileptic Patients Using Machine Learning Methods", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.9, No.7, pp.1-9, 2017. DOI: 10.5815/ijigsp.2017.07.01


[1]K. I. Qazi, H. K. Lam, B. Xiao, G. Ouyang, and X. Yin, “Classification of epilepsy using computational intelligence techniques,” CAAI Trans. Intell. Technol., vol. 1, no. 2, pp. 137–149, 2016.

[2]F. Es.haghi, J. Frounchi, P. Shahabi, and M. Sadighi, “Absence epilepsy seizure onsets detection based on ECG signal analysis,” 2013 20th Iran. Conf. Biomed. Eng., no. Icbme, pp. 219–222, 2013.

[3]M. Soodi and H. Pradesh, “Prognosis of Epileptic seizures using EEG signals,” pp. 12–16, 2015.

[4]S. Ramgopal et al., “Seizure detection, seizure prediction, and closed-loop warning systems in epilepsy,” Epilepsy Behav., vol. 37, pp. 291–307, 2014.

[5]M. Manjusha and R. Harikumar, “Performance analysis of KNN classifier and K-means clustering for robust classification of epilepsy from EEG signals,” 2016 Int. Conf. Wirel. Commun. Signal Process. Netw., pp. 2412–2416, 2016.

[6]F. Yiğit “How to draw an EEG?” Available FTP:, 2016.

[7]Y. Peng, B. Lu, and S. Member, “IMMUNE CLONAL ALGORITHM BASED FEATURE SELECTION FOR EPILEPTIC EEG SIGNAL CLASSIFICATION Department of Computer Science and Engineering, Shanghai Jiao Tong University MOE-Microsoft Key Lab. for Intelligent Computing and Intelligent Systems, Shanghai Jia,” no. 2009, pp. 848–853, 2012.

[8]Ateke Goshvarpour, Hossein Ebrahimnezdah, Atefeh Goshvarpour, "Classification of Epileptic EEG Signals using Time-Delay Neural Networks and Probabilistic Neural Networks", IJIEEB, vol.5, no.1, pp.59-67, 2013. DOI: 10.5815/ijieeb.2013.01.07

[9]A. V. R. Holla and P. Aparna, “A nearest neighbor based approach for classifying epileptiform EEG using nonlinear DWT features,” 2012 Int. Conf. Signal Process. Commun. SPCOM 2012, pp. 5–9, 2012.

[10]Available FTP:, 2016.

[11]Akhenaton, “Brain Waves I”, Available FTP:,-I.htm, 2016. 

[12]S. P. K. S, “Early Detection of Epilepsy using EEG signals,” pp. 1509–1514, 2014.

[13]Available FTP https: //, 2017.

[14]International database (6.12.2011).

[15]Baykul, Y. Statistical methods and applications. Ankara: Anı Publishing, 1999.

[16]R. Alpar, "Applied Statistics and Validity - Reliability", Detay Publishing, 2016.

[17]P. S. Hiremath, Manjunatha Hiremath,"3D Face Recognition based on Radon Transform, PCA, LDA using KNN and SVM", IJIGSP, vol.6, no.7, pp.36-43, 2014.DOI: 10.5815/ijigsp.2014.07.05

[18]M. Murugappan, “Human emotion classification using wavelet transform and KNN,” vol. 1, no. June, pp. 148–153, 2011.

[19]H. Nizam and S. S. Akın, “Comparison of Performances of Balanced and Unbalanced Data Sets in Emotion Analysis in Social Media Machine Learning” 19. Internet in Turkey Izmir, 2014.