Non-linear carbon dioxide determination using infrared gas sensors and neural networks with Bayesian regularization

Abstract

Carbon dioxide gas concentration determination using infrared gas sensors combined with Bayesian regularizing neural networks is presented in this work. Infrared sensor with a measuring range of 0~5% was used to measure carbon dioxide gas concentration within the range 0~15000 ppm. Neural networks were employed to fulfill the nonlinear output of the sensor. The Bayesian strategy was used to regularize the training of the back propagation neural network with a Levenberg-Marquardt (LM) algorithm. By Bayesian regularization (BR), the design of the network was adaptively achieved according to the complexity of the application. Levenberg-Marquardt algorithm under Bayesian regularization has better generalization capability, and is more stable than the classical method. The results showed that the Bayesian regulating neural network was a powerful tool for dealing with the infrared gas sensor which has a large non-linear measuring range and provide precise determination of carbon dioxide gas concentration. In this example, the optimal architecture of the network was one neuron in the input and output layer and two neurons in the hidden layer. The network model gave a relationship coefficient of 0.9996 between targets and outputs. The prediction recoveries were within 99.9~100.0%.

Bayesian neural networks for stock price forecasting before and during COVID-19 pandemic

“…Chandra et al [15] presented Langevin gradient Bayesian neural networks with parallel tempering MCMC, which used high-performance computing for time series prediction. Bayesian neural networks have been applied to various fields such as railway passenger flow [71], a certain index of the national economy [72], and short-term commodity prices [73]; these applications have reported promising forecasting performance.…”

Ion selective electrodes in environmental analysis

“…In this respect, methods of statistical calibration are becoming increasingly popular in the analysis of chemical data, 70,71 including ISEs. Since no estimate of uncertainty is given, these so called "point estimates" imply a level of precision that is not achieved with ISEs.…”

Real‐time force doors detection system using distributed sensors and neural networks

“…There are many success stories using distributed sensors and neural networks to detect dangerous situations or to classify processes. Many of these successes are related to the chemical industry, wastewater treatment processes or gases …”

“…Many of these successes are related to the chemical industry, 14 wastewater treatment processes 15 or gases. 16,17 This study aims to propose a novel electronic device, which will be able to detect attempts to force a door, minimizing the false alarm problems. The electronic device that will be created for this aim uses connected sensors and artificial intelligence techniques.…”