Development of a Novel Gas Sensing Algorithm Based on Impedance Spectroscopy

Abstract

A novel pattern recognition algorithm is developed, which detects concentration of different gases automatically with impedance spectroscopy (IS) using a conducting poly sensor or a WO3 sensor. It consists of adaptive- simulated-annealing-supported-parameter-estimation (ASA-PE) for feature-extraction and committee-machine (CM) for classification. The results of ASA-PE, complex-principle-component-analysis (CPCA) and discriminant- analysis-via-support-vector (SVDA) are compared. All algorithms are satisfied. But ASA-PE ensures minimal loss of information. The classifiers: distance-weighted-k-nearest-neighbor (DW-kNN), multiple-layer-perceptron (MLP), support-vector-machine (SVM) and CM are combined with feature-extraction methods and compared with each other. Recognition result is satisfying. However, if gas or gas condition is unknown, only CM with SVDA showed best performance.