BME Seminar Series: Dr. Behnaz Ghoraani
Biomedical Signal Feature Extraction: Advanced Methods and Applications
Behnaz Ghoraani, Ph.D.
Department of Biomedical Engineering
Over the last several years, several feature extraction techniques have been introduced. In general, all the feature extraction methods utilize one of the following three signal representation domains: temporal domain, spectral or joint time-frequency (TF) domain. In this seminar, advantages and challenges associated with feature extraction from temporal and spectral domains will be discussed. Spectral features generally assume the stationarity of the signal in the analysis frame, and do not provide any information on the temporal evolution or localization of the extracted features. The talk will cover the recent advancements in TF feature extraction using methods based on adaptive signal representations such as pursuits-based. The application of the extraction and classification of complex instantaneous signal parameters with respect to real world biomedical signals such as cardiac electrograms and brain auditory response signals will be discussed.