Compressing and Filtering Medical Data in a Low Cost Health Monitoring System

Abstract

Current work evaluates the precision of low-cost medical sensors, which are incorporated in an e-health platform presented recently by the authors. The sensors' accuracy is an important issue that is investigated in this paper in order to highlight the medical cases where the low-cost developed e-health platform can be used in a fairly reliable way. Specifically, the sensor values obtained from the e-health platform were filtered using the methods of moving average window (MAW), Principal component analysis (PCA) and simplified Kalman filter. It is shown that although moving average window achieves a significant error reduction, the produced output introduces a latency penalty in the original sensor signal. Kalman filter exhibits worse performance from both the MAW and the PCA methods. Finally, it is demonstrated that the PCA method sustains advanced compression of about 30% while in the same time reduces the error of the primary signal measurement, thus improving the sensor accuracy.