QCM Sensor-Based Alcohol Classification Using Ensembled Stacking Model

Alcohol consumption is the global yoke of injury and disease attributable as per the early study. The excessive intake of alcohol is coupled with unconstructive consequences and jeopardizing future prospects. This paper presents an ensemble model made of an array of five chemical compounds of quartz crystal microbalance (QCM) sensors to find the corresponding compositions of a gas mixture. This study makes use of QCM sensor responses to determine the gas compositions. These physical device sensors are used to sense the resonance frequency change of gas sensors by classifying the chemical compounds and recognizing their harmful effects. The main focus of the study is to determine the reaction of QCM sensors to five different alcohols, such as 1-octanol, 1-propanol, 2-butanol, 2-propanol, and 1-isobutanol, and to determine the effective sensor type in the classification of these compounds. The experiment is conducted to classify and identify the constituent component amount through an ensemble classifier to progress the efficiency of the QCM sensors. The results of 125 different scenarios illustrated that various alcohols could be classified effectively using a stacking classifier from the QCM sensor data.