Biomedical signals are observations of physiological activities of organisms, ranging from gene and protein sequences, to neural and cardiac rhythms, to tissue and organ images. Biomedical signal processing aims at extracting significant information from biomedical signals. With the aid of biomedical signal processing, biologists can discover new biology and physicians can monitor distinct illnesses.
Decades ago, the primary focus of biomedical signal processing was on filtering signals to remove noise [1]–[6]. Sources of noise arise from imprecision of instruments to interference of power lines. Other sources are due to the biological systems themselves under study. Organisms are complex systems whose subsystems interact, so the measured signals of a biological subsystem usually contain the signals of other subsystems. Removing unwanted signal components can then underlie subsequent biomedicine discoveries. A fundamental method for noise cancelation analyzes the signal spectra and suppresses undesired frequency components. Another analysis framework derives from statistical signal processing. This framework treats the data as random signals; the processing utilizes statistical characterizations of the signals to extract desired signal components.
Biomedical signal processing is a rapidly developing field. Biomedical data classification in particular plays an important role in biological findings and medical practice. Due to high data throughput in modern biomedical experiments, manually classifying a large volume of data is no longer feasible. It is desirable to have automatic algorithms to efficiently and effectively classify the data on behalf of domain experts. A reliable classifier avoids bias induced by human intervention and yields consistent classification results.
