Performance analysis of KNN classifier and K-means clustering for robust classification of epilepsy from EEG signals

Epilepsy is a neurological disorder which affects persons of all age. The brain waves are studied for epilepsy detection. The Electroencephalogram (EEG) is the simplest diagnostic technique available for brain wave analysis. In this paper, we investigate the performance of KNN classifier and K-means clustering for the classification of epilepsy risk level from EEG signals. To identify the non linearity present in the data, detrend analysis is done. An EEG record of twenty patients is analyzed. The power spectral density is determined which is further used for dimensionality reduction. The performance index achieved by KNN classifier and K-means clustering are 78.31% and 93.02% respectively. A high Quality value of 22.37 with K-means clustering and a low value of 18.02 are obtained with KNN classifier. The results show that K-means outperforms KNN classifier in epilepsy risk level classification.

[1]  Ye Yuan,et al.  Detection of epileptic seizure based on EEG signals , 2010, 2010 3rd International Congress on Image and Signal Processing.

[2]  R. Harikumar,et al.  Performance analysis of SVD and K-means clustering for optimization of fuzzy outputs in classification of epilepsy risk level from EEG signals , 2012, 2012 9th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology.

[3]  Gareth M. James,et al.  Interpretable dimension reduction for classifying functional data , 2013, Comput. Stat. Data Anal..

[4]  Belur V. Dasarathy,et al.  Nearest neighbor (NN) norms: NN pattern classification techniques , 1991 .

[5]  Alan S. Gevins,et al.  Analysis of the Electromagnetic Signals of the Human Brain: Milestones, Obstacles, and Goals , 1984, IEEE Transactions on Biomedical Engineering.

[6]  A. Golinska.  Detrended Fluctuation Analysis ( DFA ) in biomedical signal processing : selected examples , 2013 .

[7]  R. Harikumar,et al.  Performance Analysis of Support Vector Machine (SVM) for Optimization of Fuzzy Based Epilepsy Risk Level Classifications Using Different Types of Kernel Functions from EEG Signal Parameters. , 2009 .

[8]  Prathibha Kiran,et al.  A Novel Method for Analysis of EEG Signals Using Brain Wave Data Analyzer , 2015 .

[9]  M. Kaltenhäuser,et al.  Detection of epileptic spikes by magnetoencephalography and electroencephalography after sleep deprivation , 2010, Seizure.

[10]  Mahmut Ozer,et al.  EEG signals classification using the K-means clustering and a multilayer perceptron neural network model , 2011, Expert Syst. Appl..

[11]  Carla E. Brodley,et al.  Feature Selection for Unsupervised Learning , 2004, J. Mach. Learn. Res..

[12]  A. Geva,et al.  Forecasting generalized epileptic seizures from the EEG signal by wavelet analysis and dynamic unsupervised fuzzy clustering , 1998, IEEE Transactions on Biomedical Engineering.

[13]  P. Gifani,et al.  Optimal fractal-scaling analysis of human EEG dynamic for depth of anesthesia quantification , 2007, J. Frankl. Inst..

[14]  Zakaria Hussain,et al.  Alpha and beta EEG brainwave signal classification technique: A conceptual study , 2014, 2014 IEEE 10th International Colloquium on Signal Processing and its Applications.

[15]  Mohd Nasir Taib,et al.  Brainwave Classification for Brain Balancing Index (BBI) via 3D EEG Model Using k-NN Technique , 2014 .

[16]  Brian Litt,et al.  Detection of seizure precursors from depth-EEG using a sign periodogram transform , 2003, IEEE Transactions on Biomedical Engineering.

[17]  Ashwini D. Bhople,et al.  Performance Evaluation of Different Neural Networks Used for Seizure Detection , 2011 .

[18]  R. Harikumar,et al.  Performance Analysis of Extreme Learning Machine for Robust Classification of Epilepsy from EEG Signals , 2014 .

[19]  K. Linkenkaer-Hansen,et al.  Long-Range Temporal Correlations and Scaling Behavior in Human Brain Oscillations , 2001, The Journal of Neuroscience.

[20]  S. Imandoust,et al.  Application of K-Nearest Neighbor (KNN) Approach for Predicting Economic Events: Theoretical Background , 2013 .

[21]  K. D. Joshi,et al.  Modified K-Means for Better Initial Cluster Centres , 2013 .

[22]  A. Wennberg,et al.  Computer analysis of EEG signals with parametric models , 1981, Proceedings of the IEEE.

[23]  Don-Lin Yang,et al.  An Efficient k-Means Clustering Algorithm Using Simple Partitioning , 2005, J. Inf. Sci. Eng..

[24]  W.R. Fright,et al.  A multistage system to detect epileptiform activity in the EEG , 1993, IEEE Transactions on Biomedical Engineering.