Machine learning-based discrimination of indoor pollutants using an oxide gas sensor array: High endurance against ambient humidity and temperature

Oh, Jungkeun; Kim, Sang Hun; Lee, Myeong-Jin; Hwang, Heesu; Ku, Wonseok; Lim, John; Hwang, In‐Sung; Lee, Jong Heun; Hwang, Jin‐Ha

doi:10.1016/j.snb.2022.131894

Cited by 26 publications

(17 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where SS error is the summation of (actual value − predicted value), 2 and SS total is the summation of (actual value − average value). 2 When using the Tanh and sigmoid functions as the activation function, the prediction model mimics the sensing tendency, which results in an excellent prediction close to the experimental results. This is because Tanh and sigmoid have a slight gradient, which are advantageous for learning complex nonlinear data or outputs limited to two specific values.…”

Section: ■ Results and Discussionmentioning

confidence: 99%

Section: ■ Results and Discussionmentioning

confidence: 99%

“…Gas sensors employing the neural networks (NN) analysis have been widely studied and developed recently for the quantification of a target gas in automobile applications, medical applications, human security, and environmental monitoring due to their high accuracy and prediction characteristics (Figure a). , For instance, the Pardo group conducted the analysis with multilayer perceptron and response characteristics of a sensor array for monitoring applications . Then, Spinelle et al applied the NN in order to evaluate the correlation between estimated and reference responses for air quality monitoring applications .…”

mentioning

confidence: 99%

See 2 more Smart Citations

Correlation between Sensing Accuracy and Read Margin of a Memristor-Based NO Gas Sensor Array Estimated by Neural Network Analysis

et al. 2023

View full text Add to dashboard Cite

Memristor-based gas sensors (gasistors) have been considered as the most promising candidate for detecting NO gas suitable for neural network (NN) analysis. In this work, in order to solve an overfitting issue arising from the training data when using a single gasistor, which degrades the accuracy of NN, we here propose a metal−insulatorsilicon (MIS)-structured Zr 3 N 4 -based gasistor array that results in an improvement in both the accuracy of the NN analysis and the efficiency of the operating power. As a result, the proposed gasistor array showed a decrease of epoch and a 2.5% improvement of prediction accuracy at room temperature compared to single cells with metal/insulator/metal (MIM) and MIS structures. These results imply that an array structure based on MIS can efficiently solve the overfitting issue by receiving multiple responses at once, compared to a single gas sensor that obtains one response per sensing.

show abstract

Section: ■ Results and Discussionmentioning

confidence: 99%

Section: ■ Results and Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Correlation between Sensing Accuracy and Read Margin of a Memristor-Based NO Gas Sensor Array Estimated by Neural Network Analysis

et al. 2023

View full text Add to dashboard Cite

show abstract

“…However, this temperature variability is not linear, and once the temperature threshold is exceeded, the gas-sensitive properties of the material on the sensor drop sharply, probably due to the temperature-dependent effect of the kinetic energy required for gas–surface interactions [ 46 ]. Likewise, this effect can be caused by changes in ambient temperature on the surface of the gas sensor, but either way, it can affect the gas sensor [ 47 ]. Each material has its optimum temperature range, called the operating temperature.…”

Section: Introductionmentioning

confidence: 99%

“…The important parameters for judging the performance of gas-sensitive sensors include response value and response recovery time; the response value (S) for an n-type semiconductor can be expressed by Equation (5) [ 47 ], in which

is the resistance value measured by the device in the air environment and

is the resistance value measured by the device in the monitored gas environment, and the response/recovery time can be calculated using Equation (6) [ 51 ]:

…”

Section: Introductionmentioning

confidence: 99%

TiO2 Gas Sensors Combining Experimental and DFT Calculations: A Review

et al. 2022

View full text Add to dashboard Cite

Gas sensors play an irreplaceable role in industry and life. Different types of gas sensors, including metal-oxide sensors, are developed for different scenarios. Titanium dioxide is widely used in dyes, photocatalysis, and other fields by virtue of its nontoxic and nonhazardous properties, and excellent performance. Additionally, researchers are continuously exploring applications in other fields, such as gas sensors and batteries. The preparation methods include deposition, magnetron sputtering, and electrostatic spinning. As researchers continue to study sensors with the help of modern computers, microcosm simulations have been implemented, opening up new possibilities for research. The combination of simulation and calculation will help us to better grasp the reaction mechanisms, improve the design of gas sensor materials, and better respond to different gas environments. In this paper, the experimental and computational aspects of are reviewed, and the future research directions are described.

show abstract

Machine Learning‐Assisted Research and Development of Chemiresistive Gas Sensors

Yuan,

Luo,

Meng

2024

Adv Eng Mater

View full text Add to dashboard Cite

The traditional trial‐and‐error testing to develop high‐performance chemiresistive gas sensors is inefficient and fails to meet the high demand for sensors in various industries. Machine learning can address the limitations of trial‐and‐error testing and can be effectively utilized for enhancing, developing, and designing sensors. This review first discusses the prediction of critical mechanism parameters of gas‐sensitive materials by machine learning, including adsorption energy, band gap, thermal conductivity, and dielectric constant. Secondly, it proposes that machine learning can improve five performance indexes: selectivity, response/recovery time, stability, sensitivity, and accuracy. Machine learning also facilitates the development and structural design of gas‐sensitive new materials. In addition, the potential of machine learning to optimize the sensor arrays is investigated, including reducing the number of sensors, identifying the best array combination, and improving recognition and detection capabilities. Finally, this paper discusses the challenges and limitations of machine‐learning assisted chemiresistive gas sensors in practical applications and envisions their future development.This article is protected by copyright. All rights reserved.

show abstract

Machine learning-based discrimination of indoor pollutants using an oxide gas sensor array: High endurance against ambient humidity and temperature

Cited by 26 publications

References 59 publications

Correlation between Sensing Accuracy and Read Margin of a Memristor-Based NO Gas Sensor Array Estimated by Neural Network Analysis

Correlation between Sensing Accuracy and Read Margin of a Memristor-Based NO Gas Sensor Array Estimated by Neural Network Analysis

TiO2 Gas Sensors Combining Experimental and DFT Calculations: A Review

Machine Learning‐Assisted Research and Development of Chemiresistive Gas Sensors

Contact Info

Product

Resources

About