Rapid measurement of fatty acid content during flour storage using a color-sensitive gas sensor array: Comparing the effects of swarm intelligence optimization algorithms on sensor features

Jiang, Hui; Liu, Tong; He, Peihuan; Ding, Yuhan; Chen, Quansheng

doi:10.1016/j.foodchem.2020.127828

Cited by 29 publications

(11 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Jiang coworkers used a genetic algorithm, ant colony algorithm and PSO to optimize a BP neural network in the study of predicting fatty acid content in the flour storage process, and the results showed that the PSO-BP neural network model had the highest coefficient of determination and the best optimization effect. 27 Moreover, the research results of this paper were also consistent with Liu coworkers's conclusion about using the PSO-BP neural network to predict wind turbine blades, that is, the PSO-BP neural network has small error and higher fitting ability. 28 Through the comparison of root mean square error and the coefficient of determination, it can be concluded that the PSO-BP has better nonlinear fitting ability.…”

Section: Construction and Comparison Of Neural Network Modelssupporting

confidence: 88%

Application of back propagation neural network model optimized by particle swarm algorithm in predicting the risk of hypertension

Yan

Chen

Yang

et al. 2022

J of Clinical Hypertension

View full text Add to dashboard Cite

The structure of a back propagation neural network was optimized by a particle swarm optimization (PSO) algorithm, and a back propagation neural network model based on a PSO algorithm was constructed. By comparison with a general back propagation neural network and logistic regression, the fitting performance and prediction performance of the PSO algorithm is discussed. Furthermore, based on the back propagation neural network optimized by the PSO algorithm, the risk factors related to hypertension were further explored through the mean influence value algorithm to construct a risk prediction model. In the evaluation of the fitting effect, the root mean square error and coefficient of determination of the back propagation neural network based on the PSO algorithm were 0.09 and 0.29, respectively. In the comparison of prediction performance, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve of the back propagation neural network based on PSO algorithm were 85.38%, 43.90%, 96.66%, and 0.86, respectively. The results showed that the backpropagation neural network optimized by PSO had the best fitting effect and prediction performance. Meanwhile, the mean impact value algorithm could screen out the risk factors related to hypertension and build a disease prediction model, Yan Yan and Rong Chen contributed equally to this study.

show abstract

Section: Construction and Comparison Of Neural Network Modelssupporting

confidence: 88%

Application of back propagation neural network model optimized by particle swarm algorithm in predicting the risk of hypertension

Yan

Chen

Yang

et al. 2022

J of Clinical Hypertension

View full text Add to dashboard Cite

show abstract

“…Figure 4a was the cumulative frequency of all wavelengths in the sensor array that were selected after running the GA 100 times. The cumulative frequency is the number of times that a wavelength is selected as the optimal solution during the running of the GA. [ 45 ] This indicates that the wavelength with a higher cumulative frequency can better reflect the change in absorbance values of different phenolic substances in the reaction process, and contribute more to the qualitative discrimination model of phenolic substances. It can be seen from Figure 4a that after optimization algorithms were run 100 times, the cumulative frequencies of all of the wavelengths were different.…”

Section: Resultsmentioning

confidence: 99%

“…Genetic algorithm (GA) [ 45 ] is an efficient and intelligent global optimization algorithm based on Darwin's theory of ‘survival of the fittest’. In short, GA iteratively cultivates the population through mutation, exchange, and selection.…”

Section: Methodsmentioning

confidence: 99%

An efficient differential sensing strategy for phenolic pollutants based on a nanozyme with polyphenol oxidase activity

et al. 2022

View full text Add to dashboard Cite

To realize the efficient differential sensing of phenolic pollutants in sewage, a novel sensing strategy was successfully developed based on a nanozyme (GMP‐Cu) with polyphenol oxidase activity. Phenolic pollutants can be oxidized using GMP‐Cu, and the oxidation products reacts subsequently with 4‐aminoantipyrine to produce a quinone‐imine compound. The absorption spectra of final quinone‐imine products that resulted from different phenolic pollutants showed obvious differences, which were due to the interaction difference between GMP‐Cu and phenolic pollutants, as well as the different molecular structures of the quinone‐imine products from different phenolic pollutants. Based on the difference in the absorption spectra, a novel differential sensing strategy was developed. A genetic algorithm was used to select the characteristic wavelengths at different enzymatic reaction times. Hierarchical cluster analysis and PLS‐DA algorithms were utilized for the discriminant sensing of seven representative phenolic pollutants, including hydroquinone, resorcinol, catechol, resorcinol, phenol, p‐chlorophenol, and 2,4‐dichlorophenol. A scientific wavelength selection algorithm and a recognition algorithm resulted in the successful identification of phenolic pollutants in sewage with a discriminant accuracy of 100%, and differentiation of the phenolic pollutants regardless of their concentration. These results indicated that a sensing strategy can be used as an effective tool for the efficient identification and differentiation of phenolic pollutants in sewage.

show abstract

“…However, the decrease did not significantly differ compared to the values recorded before the storage (Table 1), whereas significant interactive effects of both ripening stage and storage duration were observed on all the color characteristics targeted (Table 1). The varying behavior observed in the color characteristics during storage is certainly due mainly to the chemical reactions that occurred in the flours, especially by the oxidation and hydrolysis reactions of fatty acid (Jiang et al, 2021), and also the Maillard reaction (Karathanos et al, 2006).…”

Section: Effects Of Packaging On Color and Dry Matter Of Flours Durin...mentioning

confidence: 99%

Effects of packaging and ripeness on plantain flour characteristics during storage

Honfo

Togbé

Dekker

et al. 2022

Food Science & Nutrition

View full text Add to dashboard Cite

Plantain is an important food crop in tropical and subtropical regions worldwide. In sub-Saharan Africa, banana and plantain provide more than 25% of the energy needs of 70 million people (Daniells et al., 2011;FAOSTAT, 2019). Pulp from mature green plantain is rich in sugar (2%-31%), micronutrients, viz. potassium (440 mg/100 g), phosphorus (32 mg/100 g), and magnesium (32 mg/100 g), vitamin C (20 mg/100 g), and vitamin B (Kouadio, 2015;Robinson & Galan Sauco, 2010).In plantain production areas, plantain pulps are consumed between the green and the yellow stages of ripening, after being boiled, pounded, fried, or roasted. Plantain pulp is also processed into flour for bakery and pastry. Besides, semiripe or ripe plantain can be used in infant food formulations as well as food for invalids who may have challenges in digesting carbohydrates (Yomeni et al., 2004). Ripening in plantain occurs once the fruit matures. During ripening, chlorophyll is degraded by the chlorophyllase enzyme to a colorless product (Fatemeh et al., 2012). In addition, carbohydrates are converted into simple sugars through α-and β-amylases activity (Okezie et al., 2003).As such, semiripe or ripe plantain flour can be incorporated into food products requiring solubility, sweetness, and a small quantity of sugar.However, the ripening stages of fruits and vegetables are determinants in the technical aspects of their processing. For example,

show abstract

Rapid measurement of fatty acid content during flour storage using a color-sensitive gas sensor array: Comparing the effects of swarm intelligence optimization algorithms on sensor features

Cited by 29 publications

References 35 publications

Application of back propagation neural network model optimized by particle swarm algorithm in predicting the risk of hypertension

Application of back propagation neural network model optimized by particle swarm algorithm in predicting the risk of hypertension

An efficient differential sensing strategy for phenolic pollutants based on a nanozyme with polyphenol oxidase activity

Effects of packaging and ripeness on plantain flour characteristics during storage

Contact Info

Product

Resources

About