• H K Shreedhar
• Sanjana K S
• Yaganti Aswini
• Joshika.B

This study has been undertaken to classify EEG signals as normal and epileptic by using deep learning techniques. In this work, 100 normal and 100 pathological single channel EEG signals were downloaded from the EEG database of University of Bonn, Germany. From these signals, alpha, beta, gamma, delta and theta waves were extracted by means of filtering. Energy and variance of these waves were calculated and these values were used to train both ANN and SVM classifiers. Performance of different classifiers is measured for different parameters for each wave. ANN provides high classification for Theta signal of 99% for energy as a training parameter and SVM provides high classification for both alpha and beta signals of 98.5% for variance parameter.

ANN, Data classification, EEG signal analysis, Epilepsy, Feature Extraction, SVM

"CLASSIFICATION OF EEG SIGNALS BY USING DEEP LEARNING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 7, page no.f478-f482, July-2022, Available :http://www.jetir.org/papers/JETIR2207559.pdf

"CLASSIFICATION OF EEG SIGNALS BY USING DEEP LEARNING TECHNIQUES", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 7, page no. ppf478-f482, July-2022, Available at : http://www.jetir.org/papers/JETIR2207559.pdf