Performance Analysis of Local Linear Embedding (LLE) and Hessian LLE with Hybrid ABC-PSO for Epilepsy Classification from EEG signals

If the neurological disorders are taken into consideration, epilepsy next to stroke. Because of sudden, temporary, frequent and electrical disturbances occurring into the brain, epileptic seizures occur. The occurrence of seizures is unpredictable and causes a lot of trouble to the patients. The main reason for such seizure attacks may be due to brain infections, accidents, substance abuse etc. The Electroencephalography (EEG) signals are of high utility to diagnose this disorder. To find the various patterns in EEG signals, data mining techniques, artificial intelligence techniques along with machine learning schemes are utilized effectively. The electrical activity which is generated by the synapses among the populations of neuron is monitored with the help of EEG signals. When the recordings of EEG are stored in huge database and to process it further, necessary techniques of the reduction in dimensionality are employed in EEG Data. Here, Local Linear Embedding (LLE) and Hessian Local Linear Embedding (HLLE) are utilized to reduce the dimensions of the EEG data and then it is categorized by the algorithm of Hybrid Artificial Bee Colony – Particle Swarm Optimization (ABC-PSO) for getting the epilepsy risk level from EEG signals. Results show that when LLE is classified with Hybrid ABC-PSO an average classification accuracy of 95.48% is obtained and when HLLE is classified with Hybrid ABC-PSO an average classification accuracy of about 97.39% is obtained.

[1]  R. Harikumar,et al.  Dimensionality Reduction with Linear Graph Embedding Technique for Electroencephalography Signals of an Epileptic Patient , 2015 .

[2]  Harikumar Rajaguru,et al.  Bayesian linear discriminant analysis with hybrid ABC-PSO classifier for classifying epilepsy from EEG signals , 2017, 2017 International Conference on Computing Methodologies and Communication (ICCMC).

[3]  R. Harikumar,et al.  Dimensionality Reduction Techniques for Processing Epileptic Encephalographic Signals , 2015 .

[4]  J. Gotman,et al.  Wavelet based automatic seizure detection in intracerebral electroencephalogram , 2003, Clinical Neurophysiology.

[5]  R. Harikumar and P. Sunil Kumar.  Fuzzy Mutual Information as a Dimensionality Reduction Technique for Epileptic Electroencephalography Signals , 2015 .

[6]  Harikumar Rajaguru,et al.  Conceptual analysis of epilepsy classification using probabilistic mixture models , 2017, 2017 5th International Winter Conference on Brain-Computer Interface (BCI).

[7]  Shufang Li,et al.  Feature extraction and recognition of ictal EEG using EMD and SVM , 2013, Comput. Biol. Medicine.

[8]  Harikumar Rajaguru,et al.  Analysis of centre tendency mode chaotic modeling for electroencephalography signals obtained from an epileptic patient , 2015 .

[9]  Harikumar Rajaguru,et al.  Performance Analysis of ApEn as a Feature Extraction Technique and Time Delay Neural Networks, Multi Layer Perceptron as Post Classifiers for the Classification of Epilepsy Risk Levels from EEG Signals , 2016 .

[10]  Harikumar Rajaguru,et al.  Metric multidimensional scaling and aggregation operators for classifying epilepsy from EEG signals , 2017, 2017 International conference of Electronics, Communication and Aerospace Technology (ICECA).

[11]  P. Sunil Kumar,et al.  Frequency Behaviours of Electroencephalography Signals in Epileptic Patients from a Wavelet Thresholding Perspective , 2015 .

[12]  Eric Laciar,et al.  Review: A Survey of Performance and Techniques for Automatic Epilepsy Detection , 2013 .