Data on Machine Learning Reported by Rafik Djemili and Colleagues (Seizure detec tion using nonlinear measures over EEG frequency bands and deep learning classif iers)
Data on Machine Learning Reported by Rafik Djemili and Colleagues (Seizure detec tion using nonlinear measures over EEG frequency bands and deep learning classif iers)
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting originating from Skikda, Alge ria, by NewsRx correspondents, research stated, “Epilepsy is a brain disorder th at causes patients to suffer from convulsions, which affects their behavior and way of life. Epilepsy can be detected with electroencephalograms (EEGs), which r ecord brain neural activity.” Our news editors obtained a quote from the research, “Traditional approaches for detecting epileptic seizures from an EEG signal are time-consuming and annoying . To supersede these traditional methods, a myriad of automated seizure detectio n frameworks based on machine learning techniques have recently been developed. Feature extraction and classification are the two essential phases for seizure d etection. The classifier assigns the proper class label after feature extraction lowers the input pattern space while maintaining useful features. This paper pr oposes a new feature extraction method based on calculating nonlinear features f rom the most relevant EEG frequency bands. The EEG signal is first decomposed in to smaller time segments from which a vector of nonlinear features is computed a nd supplied to machine learning (ML) and deep learning (DL) classifiers. Experim ents on the Bonn dataset reveals an accuracy of 99.7% reached in c lassifying normal and ictal EEG signals; and an accuracy of 98.8% in the discrimination of ictal and interictal EEG signals. Furthermore, a perfor mance of 100% is achieved on the Hauz Khas dataset. The classifica tion results of the proposed approach were compared to those from published stat e of the art techniques.”
Key words
Skikda/Algeria/Africa/Cyborgs/Emergi ng Technologies/Machine Learning
NETL
NSTL