Validated data mining technique: A case study on pressure-field digital MEMS microphone calibration

Recently, in the field of environmental noise control and monitoring, a diffusion of a new generation of microphone sensors has been observed. This was met by the rapid development of MEMS (MicroElectroMechanical Systems) microphones, whose technology could open up the possibility of noise measurements based on extensive acoustic sensor networks, that use a large number of microphones spread across wide areas. Nevertheless, current standards do not provide proper calibration and test procedures for these microphones. In this work, calibration standard procedures was adapted for the complete characterization of digital MEMS microphones by comparison with laboratory standard microphones in pressure field condition. Large data-set obtained from comparison, is subjected to a statistical analysis in order to highlight any possible factor affecting calibration accuracy and robustness.