Search results

The use of conductive yarns or wires to design and construct fabric-based strain sensors is a research area that is gaining much attention in recent years. This is based on a profound theory that conductive yarns will have a variation in resistance if subjected to tension. What is not clear is to which types of conductive yarns are most suited to delivering the right sensitivity. The purpose of this paper is to look at strain sensors knitted with conductive composite and coated yarns which include core spun, blended, coated and commingled yarns. The conductive components are stainless steel and silver coating respectively with polyester as the nonconductive part. Using Stoll CMS 530 flat knitting machine, five samples each were knitted with the mentioned yarn categories using 1×1 rib structure. Sensitivity tests were carried out on the samples. Piezoresistive response of the samples reveals that yarns with heterogeneous external structures showed both an increase and a decrease in resistance, whereas those with homogenous structures responded linearly to stress. Stainless steel based yarns also had higher piezoresistive range compared to the silver-coated ones. However, comparing all the knitted samples, silver-coated yarn (SCY) proved to be more suitable for strain sensor as its response to tension was unidirectional with an appreciable range of change in resistance.

Conductive composite yarns, namely, core spun yarn (CSY1), core spun yarn (CSY2), silver-coated blended yarn (SCBY), staple fiber blended yarn (SFBY) and commingled yarn (CMY) were sourced based on specifications and used to knit strain sensor samples. Electro-mechanical properties were investigated by stretching on a fabric tensile machine to ascertain their suitability for a textile strain sensor.

In order to generate usable signal for a strain sensor for a conductive yarn, it must have persistent and consistent conductive links, both externally and internally. In the case of composite yarns such as SFBY, SCBY and CMY where there were no consistent alignment and inter-yarn contact, resistance change fluctuated. Among all six different types of yarns used, SCY presented the most suitable result as its response to tension was unidirectional with an appreciable range of change in resistance.

This is an original research carried out by the authors who studied the electro-mechanical properties of some composite conductive yarns that have not been studied before in textile strain sensor research. Detailed research methods, results and interpretation of the results have thus been presented.

The purpose of this paper is to introduce a novel respiration pattern-based biometric prediction system (BPS) by using artificial neural network (ANN).

Respiration patterns were obtained using a knitted piezoresistive smart chest band. The ANN model was implemented by using four hidden layers to help achieve the best complexity to produce an adequate fit for the data. Not only did this study give a detailed distribution of an ANN model construction including the scheme of parameters and network layers, ablation of the architecture and the derivation of back-propagation during the iterations but also engaged a step-based decay to systematically drop the learning rate after specific epochs during training to minimize the loss and increase the model’s accuracy as well as to limit the risk of overfitting.

Findings establish the feasibility of using respiratory patterns for biometric identification. Experimental results show that, with a learning rate drop factor = 0.5, the network is able to continue to learn past epoch 40 until stagnation occurs which yielded a classification accuracy of 98 per cent. Out of 51,338 test set, the model achieved 51,557 correctly classified instances and 169 misclassified instances.

The findings provide an impetus for possible studies into the application of chest breathing sensors for human machine interfaces in the area of entertainment.

This is the first time respiratory patterns have been applied in biometric prediction system design.