Co-training neural network-based infrared sensor array for natural gas monitoring

Wang, Jinlei; Lian, Sai; Lei, Bingjie; Li, Bing; Lei, Shaochong

doi:10.1016/j.sna.2022.113392

Cited by 10 publications

(7 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A multilayer perceptual neural network model was used for natural gas monitoring application by an array of infrared sensors earlier. 167 To monitor NO 2 in air, Laref et al 168 proposed an approach of calibration transfer to reduce the long-term drift of the sensors. Targeting continuous monitoring of ambient air quality, Bax et al 69 proposed an approach of removing all the uncorrelated features from the feature vector using orthogonal signal correction based method.…”

Section: Evolution Of Managerial Toolsmentioning

confidence: 99%

Review–Modern Data Analysis in Gas Sensors

Sagar

Allison

Jalajamony

et al. 2022

J. Electrochem. Soc.

View full text Add to dashboard Cite

Development in the field of gas sensors has witnessed exponential growth with a multitude of applications. The diversity of the applications has led to unexpected challenges. Recent advances in data science have addressed the challenges such as selectivity, drift, aging, limit of detection, and response time. The incorporation of modern data analysis including machine learning techniques have enabled a self-sustaining gas-sensing infrastructure without human intervention. This article provides a birds-eye view on data enabled technologies in the realm of gas sensors. While elaborating the prior developments in gas-sensing related data analysis, this article is intended as an entrant for enthusiasts in the domain of data science and gas sensors.

show abstract

Section: Evolution Of Managerial Toolsmentioning

confidence: 99%

Review–Modern Data Analysis in Gas Sensors

Sagar

Allison

Jalajamony

et al. 2022

J. Electrochem. Soc.

View full text Add to dashboard Cite

show abstract

“…Khan et al [26] built a gas sensor array to identify NO 2 , C 2 H 5 OH, SO 2 , and H 2 by using principal component analysis (PCA), support vector machines (SVMs), naive Bayes, and k-nearest neighbor (k-NN). Wang et al [27] used the multilayer perceptron neural network (MLPNN) as base learners via co-training to monitor natural gas.…”

Section: Introductionmentioning

confidence: 99%

E-Nose System Based on Fourier Series for Gases Identification and Concentration Estimation From Food Spoilage

Luo

Zhu

et al. 2023

IEEE Sensors J.

View full text Add to dashboard Cite

This work presents an electronic nose (EN)-based gas identification and concentration estimation method for the detection of food spoilage. The response data of sensors were acquired through a commercial gas sensor array and data acquisition circuit board and transformed into pictures with the form of the Fourier series. A convolutional neural network (CNN) model was used to identify the pictures from the conversion of sensor data, thus achieving the purpose of identifying the gases (C 2 H 5 OH, NH 3 , and H 2 S). In order to solve the problem of sample imbalance and to improve the generalization performance of classification models, the synthetic minority oversampling technique (SMOTE) and dropout technique were employed. Fivefold cross-validation was used to evaluate the performance of the model, of which the gas identification accuracy rate reached 96.67%. Moreover, a gas concentration regression model with the advantages of simplicity and strong interpretability was further proposed to estimate the concentrations of C 2 H 5 OH, NH 3 , and H 2 S. The mean absolute errors and coefficients of determination for the concentration estimation of C 2 H 5 OH, NH 3 , and H 2 S are (3.71 ppm, 0.968), (0.50 ppm, 0.968), and (0.13 ppm, 0.99), respectively. Furthermore, we used our model to evaluate the freshness of kiwifruit, pork, and beef, and it showed satisfactory predictive performance. The method proposed in this work realizes high-precision detection of gases from food spoilage and has a good application prospect in the rapid judgment of food freshness on the EN system.

show abstract

“…Several types of gas sensors with different sensing mechanisms, such as infrared, electrochemical, and semiconductor-based gas sensors, have been widely studied to identify NO via NN. − Chu et al reported a semiconductor-based sensor array combining four elements operating independently with a neural network to quantify a target gas . Wang et al reported a minor error of 7–19% with an infrared gas sensor array combined with co-training multi-layer perceptual NN . Although those gas sensors showed high accuracy via NN to NO gas, these studies addressed the reduction of power consumption by using nanostructures to detect a target gas at room temperature (RT), without considering the reliability in the accuracy through repetition or multi-sensing.…”

mentioning

confidence: 99%

mentioning

confidence: 99%

“…7 Wang et al reported a minor error of 7−19% with an infrared gas sensor array combined with co-training multi-layer perceptual NN. 8 Although those gas sensors showed high accuracy via NN to NO gas, these studies addressed the reduction of power consumption by using nanostructures to detect a target gas at room temperature (RT), without considering the reliability in the accuracy through repetition or multi-sensing. Note that in the case of NN, it is required to compile a host of response characteristics via multi-sensing in repetitive sensing of unit cell or arrays to increase accuracy; however, the two-dimensional (2D) structure restrains their ability for high-density arrays, resulting in an increased error rate.…”

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

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

Co-training neural network-based infrared sensor array for natural gas monitoring

Cited by 10 publications

References 33 publications

Review–Modern Data Analysis in Gas Sensors

Review–Modern Data Analysis in Gas Sensors

E-Nose System Based on Fourier Series for Gases Identification and Concentration Estimation From Food Spoilage

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

Contact Info

Product

Resources

About