2014 | OriginalPaper | Buchkapitel
Classification of Epileptoid Oscillations in EEG Using Shannon’s Entropy Amplitude Probability Distribution
verfasst von : Ronald Broberg, Rory Lewis
Erschienen in: Similarity Search and Applications
Verlag: Springer International Publishing
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This paper presents an additional tool the authors have developed to continue merging the fields of computational neuroscience with medical based neurodiagnostic clinical research, particularly those associated with machine learning in Big Electroencephalogram (EEG) Data. The authors introduce a means to identify various types of epileptic pathologic oscillations using a parameter based on the Shannon entropy of the probability distribution of the amplitudes within EEG signals. Multiple entropy and entropy-like measures have been explored to aid in epileptic seizure classification including Kolmogorov-Sinai entropy, spectral entropy, Renyi entropy, approximate entropy, and equal frequency discretization. Here we propose a more computational efficient measure which calculates a discrete probability distribution directly from the recorded amplitudes of an EEG recording over a specified window and uses an entropy-like calculation to reduce dimensionality.