Prediction of functional properties of nano $$\hbox {TiO}_2$$ coated cotton composites by artificial neural network

Abstract

This paper represents the efficiency of machine learning tool, i.e., artificial neural network (ANN), for the prediction of functional properties of nano titanium dioxide coated cotton composites. A comparative analysis was performed between the predicted results of ANN, multiple linear regression (MLR) and experimental results. ANN was applied to map out the complex input-output conditions to predict the optimal results. A backpropagation ANN model called a multilayer perceptron (MLP), trained with Bayesian regularization were used in this study. The amount of chemicals and reaction time were selected as input variables and the amount of titanium dioxide coated on cotton, self-cleaning efficiency, antimicrobial efficiency and ultraviolet protection factor were analysed as output results. The accuracy of the proposed algorithm was evaluated and compared with MLR results. The obtained results reveal that MLP provides efficient results that are statistically significant in the prediction of functional properties ($$p<0.1 e^{-10} $$ p < 0.1 e - 10 ) compared to MLR. The correlation coefficient of MLP model ($$>95\%$$ > 95 % ) indicates that there is a strong correlation between the measured and predicted functional properties with a trivial mean absolute error and root mean square errors values. MLP model is suitable for the functional properties and can be used for the investigation of other properties of nano coated fabrics.

Combined Use of Modal Analysis and Machine Learning for Materials Classification

“…Linear regression is one of the basic tools in statistics to correlate between different variables for a set of observations. Applications of linear regression can vary from simple tasks, such as simple line fitting, to a much more complex task, such as classification and pattern recognition [ 31 , 32 , 33 ]. To increase the model possibility for higher prediction probabilities, another column was added to the input data of the model, using the combined linear regression and ML method by constructing the “|𝑚 × 𝑏|” term for each material where “m” and “b” are the linear regression variables, in other words, applying linear regression separately to each of the material results.…”

Classification of Textile Polymer Composites: Recent Trends and Challenges

“…The use of machine learning in textiles, especially for classification, has shown its potential exponentially in the current era [ 13 , 14 ]. Zimmerling et al reported the application of Gaussian regression algorithm to improve the geometrical shapes of fiber reinforced textile composites.…”

Neural network-crow search model for the prediction of functional properties of nano TiO2 coated cotton composites

“…Here, in this current study, an attempt has been made to develop a prediction model by using machine learning tools that can work in two ways i.e., correlates the actual response of coated fabric with process variables, analyse the predicted response of DE and indicate which approach is better as a prediction model in reality. Nowadays, artificial neural network (ANN) exhibits a strong advantage in capturing any type of existing relationship from given data as it does not include a physical mechanism and a mathematical model 14 . Thanks to the training process, ANN can learn, understand and recognize the information treatment rules, adapt and predict the wanted output variables from database considered as input variables 15 , 16 .…”