Determination of Odor Intensity of Binary Gas Mixtures Using Perceptual Models and an Electronic Nose Combined with Fuzzy Logic

Szulczyński, Bartosz; Gębicki, Jacek

doi:10.3390/s19163473

Cited by 17 publications

(9 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sensors 2020, 20, x FOR PEER REVIEW 3 of 12 procedure and environmental requirements were described in these references. In this study, the collected dataset contains 31 samples of binary mixture EA+BA, 21…”

Section: Support Vector Regression Methodologymentioning

confidence: 99%

“…The influences of assessor quantity, age, gender, and testing environments could be avoided [36]. On the other hand, it has been reported that the e-nose can directly perform odor intensity evaluation [21,37]. However, it directly correlates the sensor signal and odor intensity, and does not fully consider the gas mixture's composition.…”

Section: Odor Intensity Predictive Performance Of the Svr Modelmentioning

confidence: 99%

“…Machine learning methods have also attracted the attention of odor researchers and have been applied in various forms [20]. Szulczynski et al proposed an electronic nose and the odor intensity was directly linked to the results of analytical air monitoring with a fuzzy logic algorithm [21]. Zhu et al made an accurate prediction of soil organic matter contents by employing back-propagation neural network, support vector regression, and partial least squares regression methods [22].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Visual Analysis of Odor Interaction Based on Support Vector Regression Method

Yan

Liu

2020

Sensors

View full text Add to dashboard Cite

The complex odor interaction between odorants makes it difficult to predict the odor intensity of their mixtures. The analysis method is currently one of the factors limiting our understanding of the odor interaction laws. We used a support vector regression algorithm to establish odor intensity prediction models for binary esters, aldehydes, and aromatic hydrocarbon mixtures, respectively. The prediction accuracy to both training samples and test samples demonstrated the high prediction capacity of the support vector regression model. Then the optimized model was used to generate extra odor data by predicting the odor intensity of more simulated samples with various mixing ratios and concentration levels. Based on these olfactory measured and model predicted data, the odor interaction was analyzed in the form of contour maps. This intuitive method showed more details about the odor interaction pattern in the binary mixture. We found that that the antagonism effect was commonly observed in these binary mixtures and the interaction degree was more intense when the components' mixing ratio was close. Meanwhile, the odor intensity level of the odor mixture barely influenced the interaction degree. The machine learning algorithms were considered promising tools in odor researches.3 of 12 standard in odor intensity evaluation [26]. More details about the testing procedure and environmental requirements were described in these references. In this study, the collected dataset contains 31 samples of binary mixture EA+BA, 21 samples of EA+EB, 22 samples of BA+EB, 24 samples of PA+VA, 24 samples of PA+HEP, 24 samples of VA+HEP, 34 samples of B+T, 31 samples of B+E, and 24 samples of T+E.

show abstract

Section: Support Vector Regression Methodologymentioning

confidence: 99%

Section: Odor Intensity Predictive Performance Of the Svr Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Visual Analysis of Odor Interaction Based on Support Vector Regression Method

Yan

Liu

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The resulting estimate from the vector model is a profile of OI values, which represent the combination and relative strengths of ODs imparted by the mixture. The odour vector model has been successfully applied to binary [ 26 – 29 ], ternary [ 30 ], quaternary [ 31 , 32 ], and quinary mixtures [ 24 ]. However, noting that natural product odours—such as those from flowers or fruits—are mixtures of larger numbers of volatile compounds, there is an interest in expanding this modelling process to assess its utility within the context of representative profile complexity.…”

Section: Introductionmentioning

confidence: 99%

Utilisation of QSPR ODT modelling and odour vector modelling to predict Cannabis sativa odour

et al. 2023

View full text Add to dashboard Cite

Cannabis flower odour is an important aspect of product quality as it impacts the sensory experience when administered, which can affect therapeutic outcomes in paediatric patient populations who may reject unpalatable products. However, the cannabis industry has a reputation for having products with inconsistent odour descriptions and misattributed strain names due to the costly and laborious nature of sensory testing. Herein, we evaluate the potential of using odour vector modelling for predicting the odour intensity of cannabis products. Odour vector modelling is proposed as a process for transforming routinely produced volatile profiles into odour intensity (OI) profiles which are hypothesised to be more informative to the overall product odour (sensory descriptor; SD). However, the calculation of OI requires compound odour detection thresholds (ODT), which are not available for many of the compounds present in natural volatile profiles. Accordingly, to apply the odour vector modelling process to cannabis, a QSPR statistical model was first produced to predict ODT from physicochemical properties. The model presented herein was produced by polynomial regression with 10-fold cross-validation from 1,274 median ODT values to produce a model with R2 = 0.6892 and a 10-fold R2 = 0.6484. This model was then applied to terpenes which lacked experimentally determined ODT values to facilitate vector modelling of cannabis OI profiles. Logistic regression and k-means unsupervised cluster analysis was applied to both the raw terpene data and the transformed OI profiles to predict the SD of 265 cannabis samples and the accuracy of the predictions across the two datasets was compared. Out of the 13 SD categories modelled, OI profiles performed equally well or better than the volatile profiles for 11 of the SD, and across all SD the OI data was on average 21.9% more accurate (p = 0.031). The work herein is the first example of the application of odour vector modelling to complex volatile profiles of natural products and demonstrates the utility of OI profiles for the prediction of cannabis odour. These findings advance both the understanding of the odour modelling process which has previously only been applied to simple mixtures, and the cannabis industry which can utilise this process for more accurate prediction of cannabis odour and thereby reduce unpleasant patient experiences.

show abstract

“…In 2019, Szulczy ński et al proposed a fuzzy logic algorithm for the determination of the odor intensity of the binary mixtures of eight odorants: n-Hexane, cyclohexane, toluene, o-xylene, trimethylamine, triethylamine, α-pinene, and β-pinene. In this research, a prototype of an e-nose equipped with eight gas chemical sensors (one photoionization, two electrochemical, and five metal oxide semiconductor sensors) was used [26]. In 2021, Zhou et al evaluated the floral volatile profile of six Hedychium accessions using HS-SPME-GC-MS and e-nose technology.…”

Section: Introductionmentioning

confidence: 99%

Volatile Organic Compound Monitoring during Extreme Wildfires: Assessing the Potential of Sensors Based on LbL and Sputtering Films

Magro

Gonçalves

Morais

et al. 2022

Sensors

View full text Add to dashboard Cite

A new theory suggests that flammable gases generated by heated vegetation, in particular the volatile organic compounds (VOC) common to Mediterranean plants, may, under certain topographic and wind conditions, accumulate in locations where, after the arrival of the ignition source, they rapidly burst into flames as explosions. Hence, there is a need for the development of a system that can monitor the development of these compounds. In this work, a sensor’s array is proposed as a method for monitoring the amount of eucalyptol and α-pinene, the major VOC compounds of the Eucalyptus and Pine trees. The detection of the target compounds was assessed using the impedance spectroscopy response of thin films. Combinations of layers of polyelectrolytes, such as poly(allylamine hydrochloride) (PAH), polyethyleneimine (PEI), poly(sodium 4-sytrenesulfonate) (PSS) graphene oxide (GO), and non/functionalized multiwall nanotubes (MWCNT-COOH or MWCNT), namely, PAH/GO, PEI/PSS, PEI/GO, PAH/MWCNT, PAH/MWCNT-COOH, films, and TiO2 and ZnO sputtered films, were deposited onto ceramic supports coated with gold interdigitated electrodes. The results showed that concentrations of the target VOCs, within the range of 68 to 999 ppmv, can be easily distinguished by analyzing the impedance spectra, particularly in the case of the ZnO- and PAH/GO-film-based sensors, which showed the best results in the detection of the target compounds. Through principal component analysis (PCA), the best set of features attained for the ZnO and PAH/GO based sensor devices revealed a linear trend of the PCA’s first principal component with the concentration within the range 109 and 807 ppmv. Thus, the values of sensitivity to eucalyptol and α-pinene concentrations, which were (2.2 ± 0.3) × 10−4 and (5.0 ± 0.7) × 10−5 per decade, respectively, as well as resolutions of 118 and 136 ppbv, respectively, were identified.

show abstract

Determination of Odor Intensity of Binary Gas Mixtures Using Perceptual Models and an Electronic Nose Combined with Fuzzy Logic

Cited by 17 publications

References 42 publications

Visual Analysis of Odor Interaction Based on Support Vector Regression Method

Visual Analysis of Odor Interaction Based on Support Vector Regression Method

Utilisation of QSPR ODT modelling and odour vector modelling to predict Cannabis sativa odour

Volatile Organic Compound Monitoring during Extreme Wildfires: Assessing the Potential of Sensors Based on LbL and Sputtering Films

Contact Info

Product

Resources

About