Variational Autoencoder for Calibration: A New Approach
This work addresses sensor calibration for applications like gas sensing, but it is incremental as it applies an existing VAE method to a new calibration task without major innovations.
The paper tackles sensor calibration by proposing a Variational Autoencoder (VAE) that uses the latent space as a calibration output, demonstrating in a proof-of-concept with a multi-sensor gas dataset that it can perform calibration and autoencoding simultaneously while producing statistically similar outputs to truth data.
In this paper we present a new implementation of a Variational Autoencoder (VAE) for the calibration of sensors. We propose that the VAE can be used to calibrate sensor data by training the latent space as a calibration output. We discuss this new approach and show a proof-of-concept using an existing multi-sensor gas dataset. We show the performance of the proposed calibration VAE and found that it was capable of performing as calibration model while performing as an autoencoder simultaneously. Additionally, these models have shown that they are capable of creating statistically similar outputs from both the calibration output as well as the reconstruction output to their respective truth data. We then discuss the methods of future testing and planned expansion of this work.