Intelligent Algorithms for On-Line Anomaly Detection in Photoplethysmography Signals

Photoplethysmography signals (PPG) can produce a wide variety of biological information that can be useful for the detection and diagnosis of heart disease. These signals are produced by photoplethysmography sensors that are typically found in devices such as a vital signs monitor or pulse oximeter. The information produced is susceptible to common artifacts (e.g., sensor movements, poor skin contact) that can cause alerts in monitoring devices and lead to confusion in providing treatment or diagnosis. The present work deals with intelligent algorithms for on-line detection of anomalies that may occur in photoplethysmography signals and that can help to improve diagnostics where this technology is used.