Selective discrimination and accurate quantification of five target vapors among multiple vapors using 2D CuO and Co₃O₄ sensors

Selective and sensitive detection of volatile organic compounds (VOCs) are critically needed for various applications like environmental sustainability, industrial safety, healthcare, etc Metal oxides are one of the most explored chemiresistive sensing materials because of their high sensitivity, but they lack selectivity. This work reports synthesis of two metal oxides - CuO and Co₃O₄ using surfactant assisted hydrothermal method. The 2D morphologies of both the metal oxides were ensured through fielded emission scanning electron microscope. The polycrystalline nature of the materials was studied using X-ray diffractometer and bandgaps were found to be 1.72 eV (CuO) and 1.9 and 2.89 eV (Co₃O₄) through the Kubelka Munk plot. The two metal oxides were employed to detect four different concentrations (6-50 ppm) of five targeted VOCs (lung cancer biomarkers) - acetone, acetonitrile, isopropanol, methanol, and toluene. In addition, response of the sensors for 6-50 ppm of ethyl acetate, hexanal, ammonia, and NO₂ were also recorded as these VOCs are naturally produced in the body as a result of metabolic processes. The responses were recorded for 10 min for all the gases with CuO and Co₃O₄. Despite the intrinsic metal oxides lacking selectivity towards a specific VOC, careful feature selection achieved a classification accuracy of 95% using random forest (RF) algorithm. Subsequent application of RF model on validation dataset yielded a 91% accuracy in identifying target VOCs. Multilinear regression (MLR) algorithm was then employed to quantify the concentrations of the VOCs and low mean absolute error (MAE) values were obtained.