A Decision Support System using Classification of the Blood Glucose and HbA1C Level Classes from Palm Perspiration Data

-The invasive measurement techniques which puncture the skin are used for blood data values detection generally. In this paper, artificial neural network structures were used for the classification of the relationship between blood data values and palm perspiration rate as a non-invasive measurement technique. For this purpose, a comparative study was realized by using feed forward multilayer, Elman, probabilistic, radial basis and learning vector quantisation neural network structures. The quartz crystal microbalance type and humidity sensors were used for detection of palm perspiration rate. A data set for 91 volunteers is used for this study. Data of 21 volunteers are used for training the neural networks and the remaining data were used as test data.