Type discrimination and concentration prediction towards ethanol using a machine learning-enhanced gas sensor array with different morphology-tuning characteristics

Smart Gas Sensors: Recent Developments and Future Prospective

Gas sensor is an indispensable part of modern society with wide applications in environmental monitoring, healthcare, food industry, public safety, etc. With the development of sensor technology, wireless communication, smart monitoring terminal, cloud storage/computing technology, and artificial intelligence, smart gas sensors represent the future of gas sensing due to their merits of real-time multifunctional monitoring, early warning function, and intelligent and automated feature. Various electronic and optoelectronic gas sensors have been developed for high-performance smart gas analysis. With the development of smart terminals and the maturity of integrated technology, flexible and wearable gas sensors play an increasing role in gas analysis. This review highlights recent advances of smart gas sensors in diverse applications. The structural components and fundamental principles of electronic and optoelectronic gas sensors are described, and flexible and wearable gas sensor devices are highlighted. Moreover, sensor array with artificial intelligence algorithms and smart gas sensors in "Internet of Things" paradigm are introduced. Finally, the challenges and perspectives of smart gas sensors are discussed regarding the future need of gas sensors for smart city and healthy living.

Overcoming the Limits of Cross-Sensitivity: Pattern Recognition Methods for Chemiresistive Gas Sensor Array

As information acquisition terminals for artificial olfaction, chemiresistive gas sensors are often troubled by their cross-sensitivity, and reducing their cross-response to ambient gases has always been a difficult and important point in the gas sensing area. Pattern recognition based on sensor array is the most conspicuous way to overcome the cross-sensitivity of gas sensors. It is crucial to choose an appropriate pattern recognition method for enhancing data analysis, reducing errors and improving system reliability, obtaining better classification or gas concentration prediction results. In this review, we analyze the sensing mechanism of cross-sensitivity for chemiresistive gas sensors. We further examine the types, working principles, characteristics, and applicable gas detection range of pattern recognition algorithms utilized in gas-sensing arrays. Additionally, we report, summarize, and evaluate the outstanding and novel advancements in pattern recognition methods for gas identification. At the same time, this work showcases the recent advancements in utilizing these methods for gas identification, particularly within three crucial domains: ensuring food safety, monitoring the environment, and aiding in medical diagnosis. In conclusion, this study anticipates future research prospects by considering the existing landscape and challenges. It is hoped that this work will make a positive contribution towards mitigating cross-sensitivity in gas-sensitive devices and offer valuable insights for algorithm selection in gas recognition applications.

Ultra-Low-Power E-Nose System Based on Multi-Micro-LED-Integrated, Nanostructured Gas Sensors and Deep Learning

As interests in air quality monitoring related to environmental pollution and industrial safety increase, demands for gas sensors are rapidly increasing. Among various gas sensor types, the semiconductor metal oxide (SMO)-type sensor has advantages of high sensitivity, low cost, mass production, and small size but suffers from poor selectivity. To solve this problem, electronic nose (e-nose) systems using a gas sensor array and pattern recognition are widely used. However, as the number of sensors in the e-nose system increases, total power consumption also increases. In this study, an ultra-low-power e-nose system was developed using ultraviolet (UV) micro-LED (μLED) gas sensors and a convolutional neural network (CNN). A monolithic photoactivated gas sensor was developed by depositing a nanocolumnar In₂O₃ film coated with plasmonic metal nanoparticles (NPs) directly on the μLED. The e-nose system consists of two different μLED sensors with silver and gold NP coating, and the total power consumption was measured as 0.38 mW, which is one-hundredth of the conventional heater-based e-nose system. Responses to various target gases measured by multi-μLED gas sensors were analyzed by pattern recognition and used as the training data for the CNN algorithm. As a result, a real-time, highly selective e-nose system with a gas classification accuracy of 99.32% and a gas concentration regression error (mean absolute) of 13.82% for five different gases (air, ethanol, NO₂, acetone, methanol) was developed. The μLED-based e-nose system can be stably battery-driven for a long period and is expected to be widely used in environmental internet of things (IoT) applications.

Nanosheet-type tin oxide gas sensor array for mental stress monitoring

Mental stress management has become significantly important because excessive and sustained mental stress can damage human health. In recent years, various biomarkers associated with mental stress have been identified. One such biomarker is allyl mercaptan. A nanosheet-type tin oxide exhibited high gas selectivity for allyl mercaptan; thus, in this study, a sensor array comprising nanosheet-type tin oxide gas sensors was fabricated to detecting allyl mercaptan. Supervised learning algorithms were use to build gas classification models based on the principal component analysis of the sensor signal responses from the sensor array. The comprehensive data provided by the classification models can be used to forecast allyl mercaptan with high accuracy.

Gas Identification by Simultaneous Permeation through Parallel Membranes: Proof of Concept

This paper describes an experimental system for simultaneous permeation of a pressurized test gas through different gas permeable membranes and provides a proof of concept for a novel approach for gas identification/fingerprinting for potential construction of electronic noses. The design, construction, and use of a six-channel system which allows simultaneous gas permeation from a single pressurized gas compartment through six different parallel membranes are presented. The permeated gas is accumulated in confined spaces behind the respective membranes. The rate of gas pressure accumulation behind each membrane is recorded and used as a measure of the gas permeation rate through the membrane. The utilized gas permeable membranes include Teflon AF, silicone rubber, track-etch hydrophilic polycarbonate, track-etch hydrophobic polycarbonate, track-etch polyimide, nanoporous anodic aluminum oxide, zeolite ZSM-5, and zeolite NaY. An analogy between the rate of pressure accumulation of the permeating gas behind the membrane and the charging of an electric capacitor in a single series RC circuit is proposed and thoroughly validated. The simultaneous permeation rates through different membranes demonstrated a very promising potential as characteristic fingerprints for 10 test gases, that is, helium, neon, argon, hydrogen, nitrogen, carbon dioxide, methane, ethane, propane, and ethylene, which are selected as representative examples of mono-, di-, tri-, and polyatomic gases and to include some homologous series as well as to allow testing the potential of the proposed system to discriminate between closely related gases such as ethane and ethylene or carbon dioxide and propane which have almost identical molecular masses. Finally, a preliminary investigation of the possibility of applying the developed gas permeation system for semiquantitative analysis of the CO₂-N₂ binary mixture is also presented.