The how and why of electronic noses
IEEE Spectrum
Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications
Adaptive Blind Signal and Image Processing: Learning Algorithms and Applications
Neural Networks: A Comprehensive Foundation (3rd Edition)
Neural Networks: A Comprehensive Foundation (3rd Edition)
Fast and robust fixed-point algorithms for independent component analysis
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
Electronic noses and tongues are two recent examples in chemical sensing that employ statistical array techniques in order to overcome the intrinsic limitations of current solid-state chemical sensors like ion-selective field transistors (ISFET). In particular, ISFETs are sensitive to the concentration of a particular ion in a solution to be measured, but they can be also strongly affected by several interfering ions found in the solution. Hence, they must be employed in regions in which the effect of interferences is negligible thus limiting their range of operation. However, as we show, ISFETs behave as non-linear mixers of main ion activities and interfering ones and thus an attempt to separate the original main ion activity and interferences from the mixed response is suitable with independent component analysis (ICA) methods. In this direction, a novel learning algorithm is proposed which synergistically combines ICA and linear regression for dealing with the separation in ISFET responses and further reconstruction of ion activities in those operating regions in which interferences notably affect their response. Several experiments with real ISFET measurements demonstrate the interest of proposed methods.