Modeling of Carbon Nanotube-based Wearable Textile Temperature Sensor via Artificial Intelligence

Abstract

In this study, for wearable temperature sensor applications, the behaviour of the carbon nanotube-based formulated ink printed temperature sensor on the textile surface against temperature was modelled using artificial neural networks, which are among the artificial intelligence techniques. While sensor design parameters and temperature are defined as network input variables, linear electrical resistance value is defined as network output variable. In the study, 83 experimental results were entered as data set, 70% of them were used for ANN training, 15% for validation of the proposed model, and 15% for testing. Levenberg Marquardt (LM), Bayesian Regularization (BR) and Scaled Conjugate Gradient (SCG) were used as the learning algorithm. The logarithmic sigmoid in hidden neurons and fitnet in output neurons were used as an activation function. It has been observed that the developed artificial neural network model has an important performance in predicting the electrical resistance value against temperature for textile-based sensors developed in different designs and a good agreement with experimental data.