Accurate detection and discrimination of pollutant gases using a temperature modulated MOX sensor combined with feature extraction and support vector classification

Gas detection and discrimination have been, until recently, sensors-specific, with different sensors and techniques used for each of the gases. In this work, we describe a novel approach relying on a single physical sensor in conjunction with data-driven algorithms for detecting the presence of one of the three dangerous gases: CO, NO2, and O3 individually or in mixtures. The approach uses a single Metal Oxide (MOX) sensor coupled with two heaters in its hardware part. Then, its software part uses a supervised machine learning model. The sensor is exposed to the different gases and their mixtures and would react accordingly with a change in its electric signals. These raw signals, along with the readings from the heaters, constitute the primary dataset for the discrimination. To further enhance the classification results, the raw dataset is augmented by calculating several time-domain features of each of the measurements. Then, the features are ranked, and the ones with the best results to solve the classification problem are selected. Once the pretreatment of the data is finished, the selected features are used to train and validate a multi-Support Vector Machine model. Finally, the results showcased in this paper highlight the effectiveness of the proposed approach.

Automated summary

The approach described in this work utilizes a single physical sensor and data-driven algorithms to detect the presence of the dangerous gases CO, NO2, and O3 individually or in mixtures. By ranking and selecting the best features, a multi-Support Vector Machine model is trained and validated to further enhance classification results, showcasing the effectiveness of the proposed approach in gas detection and discrimination.