A novel respiration pattern biometric prediction system based on artificial neural network

Abstract

Purpose The purpose of this paper is to introduce a novel respiration pattern-based biometric prediction system (BPS) by using artificial neural network (ANN). Design/methodology/approach 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 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. Practical implications The findings provide an impetus for possible studies into the application of chest breathing sensors for human machine interfaces in the area of entertainment. Originality/value This is the first time respiratory patterns have been applied in biometric prediction system design.