Improving semiconductor-based chemical sensor arrays using advanced algorithms for blind source separation

A novel approach to design low cost/high performance on-line physiological data and water monitoring systems is presented and discussed. The approach is based on a set of solid state chemical sensors (i.e. ISFETs/CHEMFETs), and a post-processing stage which performs the estimation of the ionic activities presented in the solution. This estimation is performed by a non-linear blind separation algorithm that uses some prior knowledge about how sensors simultaneously respond to several ionic activities. Additionally, the presented approach addresses some important problems of these sensors like temperature effects, cross sensitivity and drift; it also takes into account some hardware implementation constraints. Experimental results confirm the effectiveness of the proposed architecture.