What is it about?

And when the variance of the data gives you more information than the mean? In this article, we performed analyzes to understand how the use of averaging can underestimate Electrical Resistance Tomography acquisition systems. We did experiments with variations in conductivity.

Featured Image

Why is it important?

This study favors the selection of statistical techniques that best fit data characterized by their variance and assists in future modeling proposals. In machine learning, feature engineering can contribute to modeling improvements by aggregating variables related to the dependent variable.

Perspectives

I hope this article reflects on the causes behind applying pattern recognition techniques (for example, PCA). The mean is usually a good representation of the data. However, the discovery that the variance is more correlated with the quality of the reconstructed image may stimulate the application of techniques that benefit this type of data.

Adriana da Mata
Universidade Federal do Espirito Santo

Read the Original

This page is a summary of: Signal-to-noise ratio variance impact on the image reconstruction of electrical resistance tomography in solutions with high background conductivity, Review of Scientific Instruments, July 2022, American Institute of Physics,
DOI: 10.1063/5.0088296.
You can read the full text:

Read

Contributors

The following have contributed to this page