Several ML Algorithms and Their Feature Vector Design for Gas Discrimination and Concentration Measurement with an Ultrasonically Catalyzed MOX Sensor

Linear Model for Concentration Measurement of Mixed Gases

Electronic noses have been widely used in industrial production, food preservation, agricultural product storage, environmental monitoring, and other fields. However, due to the cross-sensitivity of gas-sensing responses, accurately measuring the concentration of mixed gases remains challenging. To address this issue, this study attempts to determine the number of state variables that produce the cross-influence based on the experimental data, establish the state space model from the equivalent circuit model, and obtain model parameters through parameter correlation iterative algorithms and a Kalman filter. The sensor response model and the concentration measurement model of mixed gases are established accordingly. The simulation and experimental results show that these two models have high accuracy in predicting the sensor response and measuring the concentrations of mixed gases under the influence of mixed gases on the sensors.

Chemiresistive Gas Sensors Made with PtRu@SnO2 Nanoparticles for Machine Learning-Assisted Discrimination of Multiple Volatile Organic Compounds

Volatile organic compounds (VOCs) constitute key pollutants in the environment, and exposure to them is associated with negative health impacts. The vigilant monitoring of these pernicious VOCs is imperative for their timely detection and for curtailing the likelihood of both immediate and prolonged exposure, thus safeguarding against the deterioration of environmental quality. In this study, porous PtRu nanoalloys are successfully synthesized via a hydrothermal method and innovatively integrated with SnO2 nanoparticles to significantly enhance the performance of gas sensors. Density functional theory (DFT) calculations substantiated the pivotal role of PtRu nanoalloys in amplifying the sensitivity of SnO2 to acetone. A primary challenge in VOC surveillance is achieving the selectivity required for sensors to accurately identify specific compounds. By employing machine learning algorithms, with a particular emphasis on particle swarm optimization-support vector machine (PSO-SVM), we attained a classification accuracy of 100% in distinguishing between acetone, ethanol, methanol, and formaldehyde. This study demonstrates the potential for creating advanced sensors with selective detection of VOCs.

A Novel Calibration Scheme of Gas Sensor Array for a More Accurate Measurement Model of Mixed Gases

Gas sensor arrays (GSAs) usually encounter challenges due to the cross-contamination of mixed gases, leading to reduced accuracy in measuring gas mixtures. However, with the advent of artificial intelligence, there is a promising avenue for addressing this issue effectively. In pursuit of more accurate mixed gas measurements, we proposed a measurement model leveraging neural networks. Our approach involved employing the encoder of an autoencoder network (AEN) to extract features from experimental data, while fully connected layers were utilized for predicting concentrations of mixed gases. To refine the neural network parameters, we employed a variational autoencoder to generate additional data resembling the distribution of experimental data. Subsequently, we designed a domain difference maximum entropy technique to identify optimal concentration points for the calibration data. These calibration points were instrumental in training the fully connected layers, enhancing the model's accuracy. During practical usage, with the AEN configuration fixed, the model can be fine-tuned by using a small subset of test points across large-scale GSA deployments. Simulation and practical measurement results demonstrated the efficacy of our proposed measurement model, boasting high accuracy, with confidence intervals for relative errors of the four gas measurements below 3% at the 95% confidence level. Besides, the calibration scheme reduced the number of test points compared with traditional methods, reducing the cost of labor and equipment.

Selective Identification of Hazardous Gases Using Flexible, Room-Temperature Operable Sensor Array Based on Reduced Graphene Oxide and Metal Oxide Nanoparticles via Machine Learning

Selective detection and monitoring of hazardous gases with similar properties are highly desirable to ensure human safety. The development of flexible and room-temperature (RT) operable chemiresistive gas sensors provides an excellent opportunity to create wearable devices for detecting hazardous gases surrounding us. However, chemiresistive gas sensors typically suffer from poor selectivity and zero-cross selectivity toward similar types of gases. Herein, a flexible, RT operable chemiresistive gas sensors array is designed, featuring reduced graphene oxide (rGO) and rGO decorated with zinc oxide (ZnO), titanium dioxide (TiO2), and tin dioxide (SnO2) nanoparticles (NPs) on a flexible polyimide (PI) substrate. The sensor array consists of four different sensing layers capable of the selective identification of various hazardous gases such as NO2, NO, and SO2 using machine learning (ML). The gas sensor array exhibits a stable response even when mechanically deformed or exposed to high humidity (up to 60%). Each gas sensor, due to the different metal oxide NPs, shows unique responses in terms of sensitivity, responsiveness, response time, and recovery time to different gases. Consequently, the sensor array generates distinct response patterns that effectively differentiate between the target gases. By leveraging these distinctive recovery patterns and employing a data fusion approach in ML, specific concentrations of target gases can be distinguished. Using ML with fused array sensing data, the training and test accuracies achieved were 98.20 and 97.70%, respectively. This innovative combination of sensor arrays and ML offers significant potential for selective gas detection in environmental monitoring and personal safety applications.

Flicker Noise in Resistive Gas Sensors-Measurement Setups and Applications for Enhanced Gas Sensing

We discuss the implementation challenges of gas sensing systems based on low-frequency noise measurements on chemoresistive sensors. Resistance fluctuations in various gas sensing materials, in a frequency range typically up to a few kHz, can enhance gas sensing by considering its intensity and the slope of power spectral density. The issues of low-frequency noise measurements in resistive gas sensors, specifically in two-dimensional materials exhibiting gas-sensing properties, are considered. We present measurement setups and noise-processing methods for gas detection. The chemoresistive sensors show various DC resistances requiring different flicker noise measurement approaches. Separate noise measurement setups are used for resistances up to a few hundred kΩ and for resistances with much higher values. Noise measurements in highly resistive materials (e.g., MoS2, WS2, and ZrS3) are prone to external interferences but can be modulated using temperature or light irradiation for enhanced sensing. Therefore, such materials are of considerable interest for gas sensing.