Gas identification with drift counteraction for electronic noses using augmented convolutional neural network

Feng, Lijie; Dai, Haihang; Song, Xiang; Liu, Jiaming; Mei, Xue

doi:10.1016/j.snb.2021.130986

Cited by 28 publications

(14 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An upgraded convolutional neural network was used to provide a new technique for gas identification with drift counteraction for electronic noses. (L. Feng et al, 2022).…”

Section: : Algorithms For Discriminationmentioning

confidence: 99%

Review on Discrimination of Hazardous Gases by Smart Sensing Technology

Bandewad

Datta

Gawali

et al. 2023

AIA

View full text Add to dashboard Cite

Real-time detection of hazardous gases in the ambient and indoors has become the prime motive for curbing the problem of air pollution. Keeping the concentration of hazardous gases in control is the main task before human society so as to keep environmental balance. Smart sensors are attracting researchers to focus on fabricating devices that could detect and predict the presence of gas in real-time, give accurate results about the gas concentration, detection of a target gas from the mixture of gases. This smart gas sensor system can have applications in the field of military, space, underwater, indoor, outdoors, factories, vehicles, and wearable smart devices. This study reviews recent advances in smart sensor technology with respect to the material structure, sensing technique, and discrimination algorithm. Focus is given on reducing the power consumption and area of a sensor circuitry with the help of different techniques.

show abstract

“…An upgraded convolutional neural network was used to provide a new technique for gas identification with drift counteraction for electronic noses. (L. Feng et al, 2022).…”

Section: : Algorithms For Discriminationmentioning

confidence: 99%

Review on Discrimination of Hazardous Gases by Smart Sensing Technology

Bandewad

Datta

Gawali

et al. 2023

AIA

View full text Add to dashboard Cite

show abstract

“…It is anticipated that stability control techniques such as sensor drift-compensation methods will be employed to complement the conventional ones. 255,256 On the other hand, SMO-based gas sensors operating at low or room temperatures are appealing as they reduce the operating cost due to very low power consumption. Fundamental research studies highlighting nanostructured SMO-based room-temperature gas sensors have been published elsewhere.…”

Section: Perspective and Conclusionmentioning

confidence: 99%

“…Nevertheless, there is no single technique for controlling the stability of SMO-based gas sensors. It is anticipated that stability control techniques such as sensor drift-compensation methods will be employed to complement the conventional ones. , On the other hand, SMO-based gas sensors operating at low or room temperatures are appealing as they reduce the operating cost due to very low power consumption. Fundamental research studies highlighting nanostructured SMO-based room-temperature gas sensors have been published elsewhere. ,, Techniques, such as the fabrication of heterojunction nanostructures, , functionalizations with metal promoters (such as Pt) , and doping, have been applied to achieve low-temperature-based gas sensors.…”

Section: Perspective and Conclusionmentioning

confidence: 99%

Review on Porosity Control in Nanostructured Semiconducting Metal Oxides and Its Influence on Chemiresistive Gas Sensing

Bulemo

Cheong

2023

ACS Appl. Nano Mater.

View full text Add to dashboard Cite

Nanostructured semiconducting metal oxides (SMOs) hold the potential for playing a critical role in gas-sensing applications due to their interconnected nanograins, large surface area, and shorter diffusion length. The rational introduction of ubiquitous porosity in SMOs can enhance gas/air diffusion as well as the accessibility of nanograins and reactive sites. Although much work has been researched for adopting highly porous nanostructured SMOs to enhance gas sensing, no comprehensive review on porosity control has yet been presented. In this review, the latest porosity control methods for SMOs, structural properties, and their gas-sensing results are reported. Finally, perspective on porosity control methods and future directions are provided for further development and research of porous SMO-based gas-sensing nanomaterials.

show abstract

“…Another method by which to correct for drift is by identifying components unrelated to classification, including proposed methods such as Orthogonical Signal Correction (OSC), Linear Discriminant Correction (LDA) and Partial Least Squares (PLS) [ 18 , 19 , 20 , 21 ]. A third way to correct for sensor drift is more universally applicable and involves machine learning such as Kernel Transformation (DCKT), Self-Organizing Maps (SOMs), Adaptive Resonance Theory (ART), and Deep-learning Neural Networks [ 9 , 11 , 22 , 23 , 24 , 25 , 26 , 27 ]. The choice of the optimal fitting correction method is dependent on both the characteristics of the data and the type of sensors used.…”

Section: Introductionmentioning

confidence: 99%

Electronic Nose Sensor Drift Affects Diagnostic Reliability and Accuracy of Disease-Specific Algorithms

Bosch

Menezes

Pees

et al. 2022

Sensors

View full text Add to dashboard Cite

Sensor drift is a well-known disadvantage of electronic nose (eNose) technology and may affect the accuracy of diagnostic algorithms. Correction for this phenomenon is not routinely performed. The aim of this study was to investigate the influence of eNose sensor drift on the development of a disease-specific algorithm in a real-life cohort of inflammatory bowel disease patients (IBD). In this multi-center cohort, patients undergoing colonoscopy collected a fecal sample prior to bowel lavage. Mucosal disease activity was assessed based on endoscopy. Controls underwent colonoscopy for various reasons and had no endoscopic abnormalities. Fecal eNose profiles were measured using Cyranose 320®. Fecal samples of 63 IBD patients and 63 controls were measured on four subsequent days. Sensor data displayed associations with date of measurement, which was reproducible across all samples irrespective of disease state, disease activity state, disease localization and diet of participants. Based on logistic regression, corrections for sensor drift improved accuracy to differentiate between IBD patients and controls based on the significant differences of six sensors (p = 0.004; p < 0.001; p = 0.001; p = 0.028; p < 0.001 and p = 0.005) with an accuracy of 0.68. In this clinical study, short-term sensor drift affected fecal eNose profiles more profoundly than clinical features. These outcomes emphasize the importance of sensor drift correction to improve reliability and repeatability, both within and across eNose studies.

show abstract

Gas identification with drift counteraction for electronic noses using augmented convolutional neural network

Cited by 28 publications

References 40 publications

Review on Discrimination of Hazardous Gases by Smart Sensing Technology

Review on Discrimination of Hazardous Gases by Smart Sensing Technology

Review on Porosity Control in Nanostructured Semiconducting Metal Oxides and Its Influence on Chemiresistive Gas Sensing

Electronic Nose Sensor Drift Affects Diagnostic Reliability and Accuracy of Disease-Specific Algorithms

Contact Info

Product

Resources

About