Pattern Mismatch Guided Interference Elimination

Abstract

Electronic nose composed of MOS sensors cannot be used when there are unwanted gases; therefore, it is urgent to solve the problem of interferences elimination. The presented method in Chap. 15 tends to discriminate the interference gases and target gases and depends on the number of types of interference gases. However, there are numerous interferences in real-world application scenario, which is impossible to be sampled in laboratory experiments. Considering that the target gases rather than interferences can be fixed as invariant information, a novel and effective pattern mismatch-based interference elimination (PMIE) method is proposed in this chapter. It contains two parts: discrimination (i.e., pattern mismatch) and correction (i.e., interference elimination). Specifically, the principle behind is that the interference discrimination is achieved by deciding whether a new pattern violates the rules established on the invariant target gases information (i.e., interference gas) or not (i.e., target gas). If the current pattern of the sensor array is interference, orthogonal signal correction (OSC) algorithm is used for interference correction. Experimental results prove that the proposed PMIE method is very effective for interferences elimination in electronic nose.