Study on prediction model of grain post-harvest loss

Yu, Hanxiao; Li, Bingchan; Shen, Dongqin; Cao, Jie; Mao, Bo

doi:10.1016/j.procs.2017.11.350

Cited by 11 publications

(13 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predictive modeling is a statistical technique that has been achieving noteworthy results in the context of postharvest grain management as an innovative way of data analysis (Liakos, Busato, Moshou, Pearson, & Bochtis, 2018;Liu, Li, Shen, Cao, & Mao, 2017;Martinez-Feria et al, 2019;Romero et al, 2013;Yu, Li, Shen, Cao, & Mao, 2017). In short, a predictive model consists one or more mathematical functions applied to a set of observed data that, with the help of statistical inference, is capable of generating predictions for what might happen to response variable(s) of interest as inputs change.…”

Section: Introductionmentioning

confidence: 99%

Machine learning algorithms to predict the dry matter loss of stored soybean grains (Glycine max L.)

Zeymer

Guzzo

Araújo

et al. 2021

J Food Process Engineering

View full text Add to dashboard Cite

Predictive modeling is useful to estimate future events based on collected data and discipline-specific knowledge to guide decision making. Machine learning is one of the most frequently used methods to develop predictive models. There is limited literature in which machine learning techniques have been applied to soybeans' behavior during storage, and thus, the goal of this study was to test different model frameworks that estimate dry matter loss of soybeans utilizing data acquired from a dynamic grain respiration system with different levels of moisture content (12, 14, 18, and 22%, wet basisw.b.) and temperature (25, 30, and 35 C). Five different models were trained and tested with a 2,625 point data set, which was partitioned into a training set (90%) and a testing set (10%). In the training step, 10-fold cross-validation was used to choose the best hyperparameters for each of the models. All fitted models were evaluated using standard metrics of Root Mean Square Error (RMSE), coefficient of determination (R 2 ), dispersion of residual values, and a coefficient of performance. The Random Forest model performed best in terms of the distance between predicted and observed values, with three predicting variables. The use of predictive modeling in the recent Agriculture 4.0 scenario is a promising development for risk management and decision making in the context of grain and oilseed storage. Practical ApplicationsSoy is one of the most important crops in the world. The dry matter loss through respiration is a major problem during storage. The results of this study can aid researchers and the soybean industry in managing storage as a risk management and decision-making tool.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine learning algorithms to predict the dry matter loss of stored soybean grains (Glycine max L.)

Zeymer

Guzzo

Araújo

et al. 2021

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…Different investigations have been devoted to the modeling of postharvest processes, which tries to simulate the experimental conditions in order to set an appropriate relationship between dependent and independent parameters (Aldars‐García, Ramos, Sanchis, & Marín, ; Gardas, Raut, & Narkhede, ; Raut, Gardas, Kharat, & Narkhede, ; Song, Kim, Waldman, & Lee, ; Yu, Li, Shen, Cao, & Mao, ). Mathematical modeling of the physical phenomena helps to reduce the experimental costs of production (Cuesta & Alvarez, ; Hong, Liu, Glover, Wu, & Yan, ).…”

Section: Introductionmentioning

confidence: 99%

Development and validation of mathematical modeling for terminal velocity of cantaloupe

Moradi

Khaneghah

Parvaresh

et al. 2019

J Food Process Engineering

View full text Add to dashboard Cite

Terminal velocity is an important factor, which is useful for designing different unit operations such as hydro transport and sorting of fruits. The current investigation is aimed to propose a new dimensionless model for terminal velocity of cantaloupe fruit. For this purpose, 30 fruits from three different varieties commonly known as Jana, Gerdabadi, and Shahabadi randomly were collected and, then, the physical properties, which may affect terminal velocity, were determined. On the basis of Buckingham theorem, six dimensionless groups were recognized and established to be used for dimensionless modeling of terminal velocity of cantaloupe fruit. Dependent pi‐term versus each independent pi‐term was drawn, and regression analysis was applied to draw the curves to produce linear equations, which can be used in the construction of the dimensionless model. In order to evaluate the obtained model, terminal velocity of six randomly selected fruits from each cantaloupe variety were measured and compared with the predicted terminal velocity values. A good agreement was achieved between the experimental and the predicted terminal velocities. Also, the coefficient of determination, mean bias error, and mean relative deviation of the comparison were calculated as 0.90, 7.9, and 10.35%, respectively. In this context, the obtained model can be used as an appropriate procedure for the prediction of terminal velocity of cantaloupe fruit as well as other similar fruits with good accuracy. Practical applications Development of a generalized dimensionless model describing terminal velocity of cantaloupe fruit as a function of various physical characteristics can be used in different units of food industries such as fruit compote preparation and juicer industries. It may also be used for the designation of sorting units and hydro transport of different fruits. In other words, the obtained model could be used to sketch unit operations, which involve some postharvesting activities for cantaloupe fruits.

show abstract

“…Experiments using an irradiation dosage of 0.051 Gy as recommended by NAFDAC and USFD, demonstrated that the approach prolonged the fresh Okra shelf-life from 3 days to 14 days. Yu, Li, Shen, Cao and Mao [13], employed the use of Bias classifier, decision tree and SVM techniques to classify and compare their results to determine the most efficient algorithm in the prediction of grain data. Experiments showed that the SVM algorithm outperformed the other algorithms.…”

Section: Related Workmentioning

confidence: 99%

Application of Machine Learning Techniques for Okra Shelf Life Prediction

Iorliam¹,

Ikyo²,

Iorliam³

et al. 2021

JDAIP

View full text Add to dashboard Cite

The ability of machine learning techniques to make accurate predications is increasing. The aim of this work is to apply machine learning techniques such as Support Vector Machine, Naïve Bayes, Decision Tree, Logistic Regression, and K-Nearest Neighbour algorithms to predict the shelf life of Okra. Predicting the shelf life of Okra is important because Okra becomes harmful for human consumption if consumed after its shelf life. Okra parameters such as weight loss, firmness, Titrable Acid, Total Soluble Solids, Vitamin C/Ascorbic acid content, and PH were used as inputs into these machine learning techniques. Support Vector Machine, Naïve Bayes and Decision Tree each accurately predicted the shelf life of Okra with accuracies of 100%. However, the Logistic Regression and K-Nearest Neighbour achieved 88.89% and 88.33% accuracies, respectively. These results showed that machine learning techniques especially Support Vector Machine, Naïve Bayes and Decision Tree can be effectively applied for the prediction of Okra shelf life.

show abstract

Study on prediction model of grain post-harvest loss

Cited by 11 publications

References 7 publications

Machine learning algorithms to predict the dry matter loss of stored soybean grains (Glycine max L.)

Machine learning algorithms to predict the dry matter loss of stored soybean grains (Glycine max L.)

Development and validation of mathematical modeling for terminal velocity of cantaloupe

Application of Machine Learning Techniques for Okra Shelf Life Prediction

Contact Info

Product

Resources

About