Neural Network Model for Predicting Sub Bandage Pressure of High Compression Bandages

Abstract

In this paper artificial neural network (ANN) model has been designed to predict the sub bandage pressure of high compression bandages during wrapping on the limb. Two different types of bandage fabrics (knitted and woven) were taken for the study. The other input parameters include bandage fabric type, circumference of limb, number of bandage layers, stretch% and width of the bandage. In order to reduce the dependency of the results on a specific partition of the data into training and testing sets, a threeway cross validation tests were performed, i.e. total data was divided into training and testing set in three different ways. The predicted sub bandage pressure was correlated to the experimental sub bandage pressure and correlation coefficient between the actual and predicted values obtained. It was observed that the neural network system is able to predict the sub bandage pressure after application with good correlation and less average error.