No abstract

Epilepsy is a nervous disorder occurring in the cerebral cortex location of the brain which is caused by irregular harmonization of neurons. Since the existence of this disorder is between the neurons, it is tedious to diagnose correctly. Research works of epilepsy mostly done on an Electroencephalogram (EEG) signals for analyzing the neuron activity of the brain during seizures. Analyzing the continuing EEG reports manually for a patient affected by epilepsy is time-consuming, and it needs a large storage volume. The proposed paper is based on a unique method for detecting epileptic seizures by Adjustable Analytic Wavelet Transform (AAWT). This work is also focused on testing the practicability of utilizing the Kohonen network maps for predicting the dynamics of the brain states in the form of the trajectory which may provide the occurrence of the seizure event. AAWT is applied on each EEG signal to decompose EEG signals into the sub-band signals. The fractal dimension is applied to these sub-bands signals as a discriminating feature due to its nonlinear chaotic trait. The received solutions are fed into Kohonen self-organizing network map (KSOM) to get a stable performance rate for the categorization of an epileptic seizure. The results proved that the introduced methodology achieved 98.72% sensitivity, 93.90% specificity, 93.03% selectivity, and 94.12% efficiency than the existing models and provided promising classification accuracy. Keywords Epilepsy . Electroencephalogram (EEG) . Adjustable analytic wavelet transform (AAWT) . Fractal dimension . Kohonen self-organizing network map (KSOM)

One can determinate the occurrence of epileptic seizure from the electroencephalogram (EEG) signal. Nonautomatic epilepsy detection is onerous and may be prone to error. They have augmented automated detection of seizure methods to attain accurate results. In view of this research work, we designed a frequency localized optimal filter bank to assess their effectiveness for automatic detection of seizures from EEG records. The basic preferred requirement of optimal filters relies on low bandwidth in the discipline of biomedical signal processing. This work provides a novel filter bank method called optimal equilateral wavelet filter bank (OEWFB) to satisfy the regularity criteria. This regularity constraint is being satisfied with semi‐definite programming (SDP) framework, which specifically does nothing with any parameterization. Implementing the proposed filter banks, it disbands EEG signals into five wavelet sub‐bands. The fuzzy entropy (FuEn), Renyi's entropy (ReEn), and the Kraskov entropy (KrEn) are being used for extracting the features from the wavelet sub‐bands. The P values provide the distinctive ability of the features. Classification with 10‐fold cross‐validation for several classifiers such as quadratic discriminant, linear quadratic discriminant, K‐nearest neighbor, support vector machine, logistic regression, and complex tree is utilized to classify the EEG signals into seizure vs non‐seizure class and seizure‐free vs seizure affected class. The proposed research work has gained the highest accuracy, specificity, sensitivity, and positive predictive values of 99.4%, 99%, 99.66%, and 99.35%, respectively, for class‐1 (ABCD vs E). The performances of the proposed work using the Bonn EEG data set ensure validation concerning compatibility and robustness.

Emotions are biologically based psychological states brought on by neurophysiologic changes, variously associated with thoughts, feelings, behavioral responses, and a degree of pleasure or displeasure. In order to assure active collaboration and trigger appropriate emotional input, accurate identification of human emotions is important. Poor generalization capacity induced by individual variations in emotion perceptions is indeed a concern in the current methods of emotion recognition. This work proposes a new dynamic pattern learning system based on entropy to allow electroencephalogram (EEG) signals for subject-independent emotion recognition with strong generalization and classification through Recurrent Neural Network and Ensemble learning.

No abstract