Glucose Oxidase Biosensor Modeling by Machine Learning Methods

Biosensors are small analytical devices incorporating a biological element for signal detection. The main function of a biosensor is to generate an electrical signal which is proportional to a specific analyte i.e. to translate a biological signal into an electrical reading. Nowadays its technological attractiveness resides in its fast performance, and its highly sensitivity and continuous measuring capabilities; however, its understanding is still under research. This paper focuses to contribute to the state of the art of this growing field of biotechnology specially on Glucose Oxidase Biosensors (GOB) modeling through statistical learning methods from a regression perspective. It models the amperometric response of a GOB with dependent variables under different conditions such as temperature, benzoquinone, PH and glucose, by means of well known machine learning algorithms. Support Vector Machines(SVM), Artificial Neural Networks (ANN) and Partial least squares (PLS) are the algorithms selected to do the regression task.