Intraclass Classification of Volatile Amines Using Impedance Spectroscopy Platform

Amines are ubiquitous, yet polymer‐based DC resistive gas sensors often lack the selectivity required for intragroup discrimination. Moreover, concentration‐dependent classification of intraclass amines using a single sensor platform has not been previously reported to the best of our knowledge. This work presents a machine‐learning‐enabled impedance spectroscopy approach that uses a tin oxide–polypyrrole composite sensor to form a virtual sensor array for intraclass amine classification. The sensor's impedance response to four representative amines, ammonia, dimethylamine, triethylamine, and trimethylamine, was investigated and classified over a wide frequency range (100 Hz to 8 MHz). The sensor exhibited frequency‐dependent impedance behavior in response to different amines, enabling concentration‐dependent classification using unique set of frequencies as features. PCA was employed to visualize 20 distinct classes of the four different amines at five concentrations each (4 × 5 matrix). A SVM classifier was trained and tested on the obtained dataset using a 60%:40% train–test split. The tested data were classified with a maximum accuracy of 93% across all 20 classes, followed by a wrapper‐based feature selection approach to enhance model efficiency and reduce computational complexity. This work presents a powerful strategy for selectively classifying amines and highlights its real‐time prediction ability.