ORIGINAL ARTICLE Modelling and prediction of antibacterial activity of knitted fabrics made from silver nanocomposite fibres using soft computing approaches Prakash Khude 1 • Abhijit Majumdar 1 • Bhupendra Singh Butola 1 Received: 11 June 2018 / Accepted: 24 August 2019 Ó Springer-Verlag London Ltd., part of Springer Nature 2019 Abstract Antibacterial activity of knitted fabrics has been modelled and predicted by using two soft computing approaches, namely artificial neural network (ANN) and adaptive network-based fuzzy inference system (ANFIS). Four parameters, namely proportion of polyester–silver nanocomposite fibres in yarn, yarn count (diameter), machine gauge and type of fabric (100% polyester or 50:50 polyester–cotton), were used as input parameters for predicting antibacterial activity of knitted fabrics. For each of the input parameters, two fuzzy sets (low and high) were considered to reduce the complexity of ANFIS model. The sixteen linguistic fuzzy rules trained by ANFIS were able to explain the relationship between input parameters and antibacterial activity. A comparison between ANN and ANFIS models has also been presented. Both the models predicted the antibacterial activity of knitted fabrics with very good prediction accuracy in the training and testing data sets with coefficient of determination greater than 0.92 and mean absolute prediction error less than 5%. The robustness of the prediction results against data partitioning between training and testing sets has also been investigated. It is found that prediction accuracy of both the models was quite robust with ANFIS showing better performance with lesser number of training data. Keywords Antibacterial activity  Artificial neural network  Adaptive network-based fuzzy inference system  Polyester–cotton blend  Machine gauge 1 Introduction Textile fabrics and apparel play an important role in acquisition and transmission of pathogens in hospitals as well as during domestic use. Apparel used by healthcare personnel act as a vehicle for cross-contamination and transmission of bacteria [1]. Healthcare-associated infec- tions affect 0.65 to 1.7 million hospitalized patients in USA annually [2]. Contamination of healthcare environ- ment with pathogenic organisms contributes to the burden of healthcare-associated infection [2]. In the last few dec- ades, consumer’s attitude towards hygiene has created a rapidly increasing need for functional fabrics equipped with antibacterial properties. Natural fibres, compared to synthetic fibres, are more likely to be attacked by microbes owing to their cellulosic or protein-based structure which acts as food for many microorganisms, especially in warm and humid conditions. Therefore, there is an utmost need for the development of biocidal textile materials which should be very effective against microorganisms, as well as nontoxic to humans, and are environmental friendly [3, 4]. Gupta et al. [1] found that microbial adhesion to white coats of nurses is influenced by type of fibre blend used in fabrics. They reported that microbial load on the polyester– cotton blended fabric was 60% higher than that on the polyester fabric. Therefore, there is a need to establish the correlation between fabric parameter and microbial con- tamination. Silver has been used for ages as an antibacterial material. Materials in nanoform show some unique prop- erties due to the scale and surface effects which are not available in bulk form. As the size becomes smaller, the surface-area-to-volume ratio increases and number of & Abhijit Majumdar majumdar@textile.iitd.ac.in 1 Department of Textile Technology, Indian Institute of Technology Delhi, New Delhi 110016, India 123 Neural Computing and Applications https://doi.org/10.1007/s00521-019-04463-8