Research and Development of Automatic Methods for Detecting Features of Parkinson's Disease and Essential Tremor Based on AUC Diagrams

Methods for the automatic detection of features of neurodegenerative diseases such as Parkinson's disease and essential tremor based on AUC diagrams and optimization algorithms are researched and developed. A characteristic feature of developed methods is that they combine the advantages of spectral analysis and wavelet analysis. The novelty of these methods is that they consider the biomedical signal as a combination of so-called wave trains. The wave train is an increase of the power spectral density of the signal localized in time and frequency. The advantage of developed methods is that they allow us to extract much more useful information from biomedical signals than standard spectral methods.