Hanyang University Reports Findings in Engineering (Classification and concentration estimation of CO and NO2 mixtures under humidity using neural network-assisted pattern recognition analysis)

摘要

By a News Reporter-Staff News Editor at Network Daily News - New researchon Engineering is the subject of a report. According to news originating from Seoul, South Korea, byNewsRx correspondents, research stated, “This study addresses the concerns regarding the cross-sensitivityof metal oxide sensors by building an array of sensors and subsequently utilizing machine earning techniquesto analyze the data from the sensor arrays. Sensors were built using InO Au-ZnO, Au-SnO, and Pt-SnOand they were operated simultaneously in the presence of 25 different concentrations of nitrogen dioxide(NO), carbon monoxide (CO), and their mixtures.”Our news journalists obtained a quote from the research from Hanyang University, “To investigate theeffects of humidity, experiments were conducted to detect 13 distinct CO and NO gas combinations inatmospheres with 40 and 90 relative humidity. Principal component analysis was performed for thenormalized resistance variation collected for a particular gas atmosphere over a certain period, and theresults were used to train deep neural network-based models. The dynamic curves produced by the sensorarray were treated as pixelated images and a convolutional neural network was adopted for classification.An accuracy of 100 was achieved using both models during cross-validation and testing.”According to the news editors, the research concluded: “The results indicate that this novel approachcan eliminate the time-consuming feature extraction process.”