Novel estimation technique for the carrier-to-noise ratio of wireless medical telemetry using software-defined radio with machine-learning

Abstract

In this study, we developed a novel machine-learning model to estimate the carrier-to-noise ratio (CNR) of wireless medical telemetry (WMT) using time-domain waveform data measured by a low-cost software-defined radio. With automatic estimation of CNR, the management of the electromagnetic environment of WMT can be made easier. Therefore, we proposed a machine-learning method for estimating CNR. According to the performance evaluation results by 5-segment cross-validation on 704 types of measured data, CNR was estimated with 99.5% R-square and 0.844 dB mean absolute error using a gradient boosting regression tree. The gradient boosting decision tree classifiers predicted if the CNR exceeded 30 dB with 99.5% accuracy. The proposed method is effective for investigating electromagnetic environments in clinical settings.