PEDOT:PSS/QCM-based multimodal humidity and pressure sensor

A room temperature multimodal sensor composed of poly(3,4-ethylenedioxythiophene):polystyrene sulfonate (PEDOT:PSS) deposited on an AT-cut quartz crystal microbalance (QCM) crystal was fabricated. The sensor's nonlinear motional resistance and frequency responses are deconvoluted using a feedforward backpropagation neural network (FBN), which allows a single sensor to function simultaneously as a relative humidity (RH) sensor and a pressure sensor using only two electrodes. We demonstrate that the predictive ability of the sensor is highly influenced by the data used to train the FBN. When training sets are tailored to resemble the operating conditions of the sensor, the sensor achieves an average resolution of <4% RH from 0 to 100% RH, even after H₂O saturation occurs on the surface. Our results indicate that FBNs show strong promise for improving the resolution of low cost gas sensors and for expanding the range of environmental conditions in which a given sensor can operate.