Development of a partial least squares-artificial neural network (PLS-ANN) hybrid model for the prediction of consumer liking scores of ready-to-drink green tea beverages

Yu, Peigen; Low, Mei Yin; Zhou, Weibiao

doi:10.1016/j.foodres.2017.10.015

Cited by 38 publications

(18 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The result also indicated that the PLS model was found to have the lowest prediction performance while ANN and PLS-ANN hybrid models were found to have comparable qualities based on the values of and RMSEP. This result suggested that the linear PLS model cannot generalize nonlinearity of spectral data and these findings are in line with the results of the previous study [9]. While the characteristics of ANN modelling that can adapt and generalize data sets having non-linear relationships makes ANN achieve a better result in this research.…”

Section: Prediction Performancesupporting

confidence: 91%

“…For instance, auto regressive integrated moving average and ANN (ARIMA_ANN) are marginally showed better performance then hybrid ANN_ARIMA in Indian stock trend forecasting research [22]. Moreover, ANN showed a slightly higher performance in term of and lower RMSE compared to PLS-ANN in consumer liking scores of ready-todrink green tea beverages predictions [9]. Furthermore, the criteria of datasets with extrapolation samples may influenced the prediction performance of different predictive modelling.…”

Section: Hidden Neuronsmentioning

confidence: 99%

“…Genetic algorithm (GA) coupled with PLS showed the capability of retrieving components of interest from spectral data [8]. Furthermore, GA combined with ANN shows a reliable method in classifying an egg's freshness [9]. In addition, ANN hybrid with GA was established to predict travel agency air ticket sales revenue [10].…”

Section: Introductionmentioning

confidence: 99%

“…Next, the quality of different models of PLS, ANN, and PLS-ANN to predict consumer interest rating of ready to drink green tea beverages were investigated [9]. PLS-ANN showed a better quality compared to PLS in coefficient of determination and mean square error value.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Artificial neural network and partial least square in predicting blood hemoglobin using near-infrared spectrum

Idrus

Chia

2019

IJEECS

View full text Add to dashboard Cite

<p>Predictive models is crucial in near-infrared (NIR) spectroscopic analysis. Partial least square - artificial neural network (PLS-ANN) is a hybrid method that may improve the performance of prediction in NIR spectroscopic analysis. This study investigates the advantage of PLS-ANN over the well-known modelling in spectroscopy analysis that is partial least square (PLS) and artificial neural network (ANN). The results show that ANN that coupled with first order SG derivatives achieved the best prediction with root mean square error of prediction (RMSEP) of 0.3517 gd/L and coefficient of determination ( ) of 0.9849 followed by PLS-ANN with RMSEP of 0.4368 gd/L and of 0.9787, and PLS with RMSEP of 0.4669 gd/L and of 0.9727. This suggests that the spectrum information may unable to be totally represented by the first few latent variables of PLS and a nonlinear model is crucial to model these nonlinear information in NIR spectroscopic analysis.</p>

show abstract

Section: Prediction Performancesupporting

confidence: 91%

Section: Hidden Neuronsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Artificial neural network and partial least square in predicting blood hemoglobin using near-infrared spectrum

Idrus

Chia

2019

IJEECS

View full text Add to dashboard Cite

show abstract

“…Green tea is mainly produced in China, Japan and someeastern Asian countries, and usually consumed as tea beverages [1]. However, other hydrophobic active ingredients of green tea such as chlorophyll, insoluble protein and fiber, located inside the tea leaves, are hard to extract with water [2][3][4].…”

Section: Introductionmentioning

confidence: 99%

Water Cooking Stability of Dried Noodles Enriched with Different Particle Size and Concentration Green Tea Powders

Zhou

Zhu

et al. 2020

Foods

View full text Add to dashboard Cite

Incorporating green tea powder (GTP) into dried noodles enriched the functional characteristics of noodles. To achieve the maximum benefits from GTP, the water cooking stability of dried green tea noodles (DGTN) should be investigated. Indeed, antioxidant activities and phenolic compounds of DGTN after water cooking markedly decreased. The results showed that large GTP particles caused the increased cooking loss of DGTN, but the phenolic compound loss of DGTN prepared with them was low after cooking. Analysis of texture properties and microstructure showed that DGTN with a 2% concentration of large GTP particles formed some holes in the noodles’ network, and its breaking strength decreased. However, we observed that many GTP particles adhered to the surface of DGTN prepared with small GTP particles, and they were easier to lose after water cooking. Comprehensive analysis concluded that cooking loss, functional compounds retention and textural properties of DGTN were related to GTP particle size and concentration via the microstructure.

show abstract

Quality control of fresh strawberries by a random forest model

et al. 2021

View full text Add to dashboard Cite

BACKGROUND Strawberry quality is one of the most important factors that guarantees consistent commercialization of the fruit and ensures the consumer's satisfaction. This work makes innovative use of random forest (RF) to predict sensory measures of strawberries using physical and physical‐chemical variables. Furthermore, it also employs these same physical and physical‐chemical variables to classify strawberries in the classes "satisfied" or "not satisfied" and "would pay more" or "wouldn't pay more. The RF‐based model predicts the acceptance, expectation, ideal of sweetness, ideal of acidity, and the ideal of succulence based on the physical and physical‐chemical data. Then, the predicted parameters are used as input for the RF‐based classification model. RESULTS The RF achieved a coefficient of determination R2 > 0.72 and a root‐mean‐squared error (RMSE) smaller than 0.17 for the prediction task, which indicates that one can estimate the sensory measures of strawberries using physical and physical–chemical data. Furthermore, the RF was able to classify 87.95% of the strawberry samples correctly into the classes ‘satisfied’ and ‘not satisfied’ and 78.99% in the classes ‘would pay more’ or ‘would not pay more’. A two‐step RF model, which employed both physical and physical–chemical data to classify strawberry samples regarding the consumer's response also correctly classified 100% and 90.32% of the samples with respect to consumers’ satisfaction and their willingness to pay more, respectively. CONCLUSION The results indicate that the developed models can be used in the quality control of strawberries, supporting the establishment of quality standards that consider the consumer's response. The proposed methodology can be extended to control the sensory quality of other fruits. © 2021 Society of Chemical Industry

show abstract

Development of a partial least squares-artificial neural network (PLS-ANN) hybrid model for the prediction of consumer liking scores of ready-to-drink green tea beverages

Cited by 38 publications

References 25 publications

Artificial neural network and partial least square in predicting blood hemoglobin using near-infrared spectrum

Artificial neural network and partial least square in predicting blood hemoglobin using near-infrared spectrum

Water Cooking Stability of Dried Noodles Enriched with Different Particle Size and Concentration Green Tea Powders

Quality control of fresh strawberries by a random forest model

Contact Info

Product

Resources

About