Classification and Identification of Industrial Gases Based on Electronic Nose Technology

Development of a Smartwatch with Gas and Environmental Sensors for Air Quality Monitoring

In recent years, there has been a growing interest in developing portable and personal devices for measuring air quality and surrounding pollutants, partly due to the need for ventilation in the aftermath of COVID-19 situation. Moreover, the monitoring of hazardous chemical agents is a focus for ensuring compliance with safety standards and is an indispensable component in safeguarding human welfare. Air quality measurement is conducted by public institutions with high precision but costly equipment, which requires constant calibration and maintenance by highly qualified personnel for its proper operation. Such devices, used as reference stations, have a low spatial resolution since, due to their high cost, they are usually located in a few fixed places in the city or region to be studied. However, they also have a low temporal resolution, providing few samples per hour. To overcome these drawbacks and to provide people with personalized and up-to-date air quality information, a personal device (smartwatch) based on MEMS gas sensors has been developed. The methodology followed to validate the performance of the prototype was as follows: firstly, the detection capability was tested by measuring carbon dioxide and methane at different concentrations, resulting in low detection limits; secondly, several experiments were performed to test the discrimination capability against gases such as toluene, xylene, and ethylbenzene. principal component analysis of the data showed good separation and discrimination between the gases measured.

Chemical VOC sensing mechanism of sol-gel ZnO pellets and linear discriminant analysis for instantaneous selectivity

This work reports on the integration of ZnO pellets for use as a virtual sensor array (VSA) of volatile organic compounds (VOCs). ZnO pellets consist of nano-powder prepared using a sol-gel technique. The microstructure of the obtained samples was characterized by XRD and TEM methods. The response to VOCs at different concentrations was measured over a range of operating temperatures (250-450 °C) using DC electrical characterization. The ZnO based sensor showed a good response towards ethanol, methanol, isopropanol, acetone and toluene vapors. We note that the highest sensitivity (0.26 ppm^-1) is obtained with ethanol while the lowest one (0.041 ppm^-1) corresponds to methanol. Consequently, the limit of detection (LOD) estimated analytically reached 0.3 ppm for ethanol and 2.0 ppm for methanol at an operating temperature of 450 °C. The sensing mechanism of the ZnO semiconductor was developed on the basis of the reaction between the reducing VOCs with the chemisorbed oxygen. We verify through the Barsan model that mainly O^- ions in the layer react with VOC vapor. Furthermore, dynamic response was investigated to construct mathematical features with distinctly different values for each vapor. Basic linear discrimination analysis (LDA) shows a good job of separating two groups by combining features. In the same way we have shown an original reason embodying the distinction between more than two volatile compounds. With relevant features and VSA formalism, the sensor is clearly selective towards individual VOCs.

An Odor Labeling Convolutional Encoder-Decoder for Odor Sensing in Machine Olfaction

Deep learning methods have been widely applied to visual and acoustic technology. In this paper, we propose an odor labeling convolutional encoder–decoder (OLCE) for odor identification in machine olfaction. OLCE composes a convolutional neural network encoder and decoder where the encoder output is constrained to odor labels. An electronic nose was used for the data collection of gas responses followed by a normative experimental procedure. Several evaluation indexes were calculated to evaluate the algorithm effectiveness: accuracy 92.57%, precision 92.29%, recall rate 92.06%, F1-Score 91.96%, and Kappa coefficient 90.76%. We also compared the model with some algorithms used in machine olfaction. The comparison result demonstrated that OLCE had the best performance among these algorithms.

Development of Electronic Nose for Qualitative and Quantitative Monitoring of Volatile Flammable Liquids

A real-time electric nose (E-nose) with a metal oxide sensor (MOS) array was developed to monitor 5 highly flammable liquids (ethanol, tetrahydrofuran, turpentine, lacquer thinner, and gasoline) in this work. We found that temperature had a significant impact on the test results and temperature control could efficiently improve the performance of our E-nose. The results of our qualitative analysis showed that principal component analysis (PCA) could not efficiently distinguish these samples compared to a back-propagation artificial neural network (BP-ANN) which had a 100% accuracy rate on the test samples. Quantitative analysis was performed by regression analysis and the average errors were 9.1%–18.4%. In addition, through anti-interference training, the E-nose could filter out the potential false alarm caused by mosquito repellent, perfume and hair jelly.