Measurement and calibration of EMF: A study using phone and GBDT for mobile communication signals

Electromagnetic exposure caused by mobile communication signals has always been a cause of concern. Due to the cost and inconvenience of professional measurement equipment, researchers have turned to smartphone APPs to study and assess the electric field strength caused by mobile communication signals. However, existing cell phone-based measurements have two weaknesses. First, no system architecture suitable for large-scale crowdsourced testing has been proposed. Second, since smartphone sensors cannot measure electric field strength directly, existing methods for converting the received signal power of the phone and electric field strength have errors of more than 5 dB. This paper proposes a measurement and calibration method for electric field strength of mobile communication signals based on a smartphone app and gradient boosting decision tree (GBDT). This method consists of a downlink signal acquisition system based on an APP and a calibration model based on GBDT to convert received signal power into electric field strength. The experimental results show that the proposed model achieves a R ² score of 0.93 and a MAE of 0.97 dB. Compared with the existing methods, our method improves the calibration accuracy by 4 dB, enabling large-scale, low-cost, and high-precision direct measurement of the electric field strength of mobile communication signals.