Effects of Harvest Maturity and Storage Time on Storage Quality of Korla Fragrant Pear Based on GRNN and ANFIS Models: Part I Firmness Study

Hao, Ning; Liu, Yang; Wang, Zhentao; Zhai, Hong; Zhang, Yongcheng; Lan, Haipeng

doi:10.3136/fstr.26.363

Cited by 11 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This network helps to reduce the influence of artificial factors and makes the evaluation results more in line with the objective reality so that the neural network can make up for the defects existing in the above methods (Ali, Abbas, Perla, & Mahshad, 2019). In recent years, Back Propagation Neural Network (BPNN), General Regression Neural Network (GRNN), and Adaptive Network-based Fuzzy Inference System (ANFIS) have been extensively used in the prediction of fruits and vegetables, food rheology, food processing industry, fruit bruise prediction, fruit yield, and other aspects (Cheng et al, 2017;Farhad, Abdollah, Gholamhossein, & Ebrahim, 2020;Niu et al, 2020). It provides a feasible reference for solving the problem of predicting the shelf life of fragrant pears.…”

mentioning

confidence: 95%

“…Xu et al (2016) observed that the BPNN neural network can effectively predict the maximum storage time of litchi in cold storage and controlled atmosphere environment. Niu et al (2020) predicted the relationship between fruit hardness, harvest maturity, and storage time of Korla fragrant pears through the GRNN and ANFIS models. Razavi, Golmohammadi, Sedghi, and Asghari (2020) predicted the volume propagation of pear damage during storage by way of the ANFIS model.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Prediction method of shelf life of damaged Korla fragrant pears

Lan

et al. 2021

J Food Process Engineering

Self Cite

View full text Add to dashboard Cite

To scientifically and effectively predict the shelf life of damaged Korla fragrant pears, this paper explores the effects of maturity, storage temperature, and damage degree on their shelf life, which was furthermore predicted employing three neural network modeling methods: Back Propagation Neural Network, General Regression Neural Network (GRNN), and Adaptive Network-based Fuzzy Inference System (ANFIS). A prediction model was then built to achieve the optimal prediction of the shelf life of damaged Korla fragrant pears. The results suggest that maturity, storage temperature, and damage degree exert a significant effect on the shelf life of fragrant pears, and are inversely proportional to the shelf life length; the damaged fragrant pears still have storage value, which can be stored at low temperature according to different damage degree to prolong the shelf life of damaged fragrant pears; the prediction model of maturity, storage temperature, and damage degree on the shelf life of fragrant pears is built based on well-trained neural networks using the GRNN and ANFIS model, and the ANFIS model with gaussmf input membership function yields the best performance in predicting the shelf life of damaged fragrant pears (root mean square error = 3.5190; R 2 = 0.9881). The results offer theoretical guidance for the selection of optimal storage conditions and the effective prediction of the shelf life of fruits and vegetables. Practical applicationsBefore the Korla fragrant pears are stored in the warehouse, the practitioners will directly discard damaged fruits, causing a lot of waste and economic losses. The damaged fragrant pears can be temporarily stored and preserved, and they can be processed and sold in time before the end of the critical shelf life, thereby increasing the economic income of practitioners. Therefore, three neural networks-Back Propagation Neural Network, General Regression Neural Network, and Adaptive Network-based Fuzzy Inference System-are evaluated for their ability to predict the shelf life of damaged fragrant pears.A shelf life model of damaged fragrant pears is then constructed and screened out, and employed to realize the prediction of the shelf life of damaged fragrant pears. This method is also suitable for predicting the shelf life of other damaged fruits. | INTRODUCTIONKorla fragrant pears are considered a Xinjiang pear species, which are deeply favored by a vast number of consumers thanks to their sweet and smooth taste, thin skin, fine meat, and abundant nutrition (Wang, Su, Chen, Mao, & Jiang, 2021). In 2019, the gross output of Xinjiang Korla fragrant pears has been more than 1 million tons, and, after the harvest, more than 85% of the fragrant pears await to be put into cold

show abstract

mentioning

confidence: 95%

mentioning

confidence: 99%

Prediction method of shelf life of damaged Korla fragrant pears

Lan

et al. 2021

J Food Process Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…In general, substances that dissolve in water are referred to as soluble solids, and they are made up of sugar, acid, vitamins and minerals. SSC is a major indicator for measuring the maturity of Korla fragrant pear ( Niu et al., 2020 ). Among the four groups, the SSC of SA was significantly higher than that of the other three groups ( P <0.05) ( Table 3 ).…”

Section: Results and Analysismentioning

confidence: 99%

Effects of green manure planting mode on the quality of Korla fragrant pears (Pyrus sinkiangensis Yu)

et al. 2022

Self Cite

View full text Add to dashboard Cite

In this study, a three-year experiment on the fragrant pear orchard was conducted to investigate the effects of different varieties of green manure on the Korla fragrant pear fruit quality, with a view to finding a suitable green manure planting mode for Korla fragrant pear orchard. Green manures were planted in spaces among rows of pear trees, and then smashed and pressed into the soil as fertilisers by the agricultural machinery equipment in their full bloom period. In the experiment, four planting modes of green manure had been set for comparison: SA: Leguminosae green manures alfalfa (Medicago sativa L.), SP: Poaceae green manures oats (Avena sativa L.), ST: Cruciferae green manures oilseed rape (Brassica napus L.), and S: orchard authigenic green manures (Chenopodium album L., Mulgedium tataricum (L) DC., and Phragmites australis (Cav.) Trin. ex Steud.). Apart from that, eleven fruit quality indicators were analyzed to evaluating the effects of different green manure planting mode on the quality of fragrant pear. According to analysis of variance (ANOVA) results, there were significant differences among four planting modes in terms of nine fruit quality indicators (P<0.05). In addition, the correlation analysis (CA) results revealed that there were different degrees of correlations among quality indicators. On this basis, repeated information among indicators was eliminated by principal component analysis (PCA), thus simplifying and recombining the three principal components. All in all, these three principal components reflect appearance traits, internal nutritive value and taste of fruits, respectively. Specifically, SA significantly improved the internal quality and nutritive value of fruits, SP improved the physical traits of fruits, and ST significantly improved the taste of fruits. Based on the PCA results, a comprehensive evaluation model of fruit quality was constructed. The are comprehensive fruit quality scores:SA>SP>ST>S.

show abstract

“…Fruit firmness is the most significant quality attribute of Korla fragrant pear that is of primary concern to consumers. It is also an important parameter in assessing the maturity, postharvest quality, and shelf life of fragrant pears [4][5][6] . At present, fruit firmness is commonly measured by using the fruit firmness tester, which can achieve precise measurement but is destructive.…”

Section: Introduction mentioning

confidence: 99%

Non-destructive detection of the fruit firmness of Korla fragrant pear based on electrical properties

Liu¹,

Tang²,

Lan³

et al. 2022

International Journal of Agricultural and Biological Engineering

View full text Add to dashboard Cite

In order to achieve the non-destructive detection of the firmness of Korla fragrant pear during the ripening period, the characteristic variables integrating the parallel equivalent inductance (Lp), quality factor (Q), parallel equivalent capacitance (Cp), dissipation factor (D), parallel equivalent resistance (Rp) and impedance (Z) were formulated through principal component analysis (PCA). Further, based on the characteristic variables, the models were established for predicting the firmness of Korla fragrant pear by using the generalized regression neural network (GRNN) and back-propagation neural network (BPNN). The results showed that firmness has significant correlations with the six electrical parameters. The first two principal components (PCs) were selected as the characteristic variables of the electrical parameters. GRNN exhibited the best performance in predicting firmness (R 2 =0.9628, RMSE=0.383). The results could provide important references for non-destructive detection of the quality of Korla fragrant pear.

show abstract

Effects of Harvest Maturity and Storage Time on Storage Quality of Korla Fragrant Pear Based on GRNN and ANFIS Models: Part I Firmness Study

Cited by 11 publications

References 29 publications

Prediction method of shelf life of damaged Korla fragrant pears

Prediction method of shelf life of damaged Korla fragrant pears

Effects of green manure planting mode on the quality of Korla fragrant pears (Pyrus sinkiangensis Yu)

Non-destructive detection of the fruit firmness of Korla fragrant pear based on electrical properties

Contact Info

Product

Resources

About