An Improved EEG Signal Classification Using Neural Network with the Consequence of ICA and STFT

Abstract

-Signals of the Electroencephalogram (EEG) can reflect the electrical background activity of the brain generated by the cerebral cortex nerve cells. This has been the mostly utilized signal, which helps in effective analysis of brain functions by supervised learning methods. In this paper, an approach for improving the accuracy of EEG signal classification is presented to detect epileptic seizures. Moreover, Independent Component Analysis (ICA) is incorporated as a preprocessing step and Short Time Fourier Transform (STFT) is used for denoising the signal adequately. Feature extraction of EEG signals is accomplished on the basis of three parameters namely, Standard Deviation, Correlation Dimension and Lyapunov Exponents. The Artificial Neural Network (ANN) is trained by incorporating Levenberg-Marquardt(LM) training algorithm into the backpropagation algorithm that results in high classification accuracy. Experimental results reveal that the methodology will improve the clinical service of the EEG recording and also provide better decision making in epileptic seizure detection than the existing techniques. The proposed EEG signal classification using feed forward Backpropagation Neural Network performs better than to the EEG signal classification using Adaptive Neuro Fuzzy Inference System (ANFIS) classifier in terms of accuracy, sensitivity, and specificity.

Seizure detection approach using S-transform and singular value decomposition

“…Nicolaou and Georgiou proposed a seizure detection algorithm based on permutation entropy (PE) and support vector machine (SVM) [7] to classify segments of normal and epileptiform EEGs. In addition, timefrequency analysis methods have also been employed for seizure detection [8][9][10][11], such as short-time Fourier transform (STFT) and wavelet transform (WT). Short-time Fourier transform decomposes EEG signals into time-frequency domain using a fixed and moving window function, but it has the limitation of analyzing signals at single resolution because of fixed window width.…”

An automated methodology for the classification of focal and nonfocal EEG signals using a hybrid classification approach

“…1 Though these methods are simple to detect epilepsy disease in human brain, the accuracy levels of these signals are captured using an electroencephalogram (EEG) sensor placed over the scalp of the human head. This will create epilepsy disease in the human brain.…”

Estimation of Brain Connectivity during Motor Imagery Tasks using Noise-Assisted Multivariate Empirical Mode Decomposition

“…1 (a) and (b), we extracted the frequency components between 1 Hz and two and three AR processes using conventional IIR filter (5 th -order Butterworth), CWT 3 (widely used Morlet wavelet [10]), original EMD, EEMD and NA standard single channel EMD algorithms (EMD, EEMD) were applied to each channel separately, while NA was applied to the two/three channel data and one 3 CWT is given by W  a , b  ; V, φ = |a | / ∫ V(t   is the mother wavelet, a  the dilation factor and b  origin.…”

“…Based on the power spectral density (PSD) of the , we extracted the 1 Hz and 30 Hz for both two and three AR processes using conventional IIR filter 3 (widely used Morlet and NA-MEMD. The standard single channel EMD algorithms (EMD, EEMD) while NA-MEMD two/three channel data and one investigation of the spectral information based on the periodogram indicated that EMD and frequency components in their first and second IMFs, and NA-MEMD has frequency components in its second and third IMFs.…”

“…Electroencephalogram (EEG), which is the most commonly used method for brain computer interface (BCI) studies, facilitates the implementation of computer-aided control by exclusively using brain activity due to its noninvasive nature and affordable recording equipment [1] [2] [3]. In particular, the motor imagery (MI) paradigm, defined as the mental rehearsal of simple or complex motor acts that is not accompanied by overt body movements, has been widely used for EEG-based BCI systems [1].…”