Mass modeling of cantaloupe based on geometric attributes: A case study for Tile Magasi and Tile Shahri

Seyedabadi, Esmaeel; Khojastehpour, Mehdi; Sadrnia, Hassan; Saiedirad, Mohammad-Hosaien

doi:10.1016/j.scienta.2011.06.003

Cited by 18 publications

(18 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, for the best feedforward ANN, correlation coefficient (R 2 test ), and test root mean square error (RMSE test ) were 0.66 and 0.992 cm 3 , respectively. [8] To model the mass of cantaloupe varieties based on geometric properties, Seyedabadi et al [9] first measured fruit sizes. Then, they designed a regression model for cantaloupe mass and utilized a water displacement method to measure its actual volume.…”

Section: Introductionmentioning

confidence: 99%

Modeling of volume and surface area of apple from their geometric characteristics and artificial neural network

Ziaratban

Azadbakht

Ghasemnezhad

2016

International Journal of Food Properties

View full text Add to dashboard Cite

Geometric parameters and physical properties of agricultural products are widely used in designing and manufacturing of harvesting devices. These features are highly useful for drying and sorting processes. This can lead to determine the major and minor diameters in this regard. As such, the current study applied machine vision, and image processing technology to identify the major and minor diameters of the Golden Delicious apple. Through applying apple diameters, the actual surface area and real volume of apples were measured by peeling method and water displacement method, respectively. Finally, mathematical modeling, and feed-forward artificial neural network allowed for estimation of the surface area and volume of Golden Delicious apple. The results revealed that the correlation coefficient (R 2) of the mathematical model, for the volume and surface area were 0.9394 and 0.9291, respectively. In the neural network, R 2-values for the volume and surface area in the most appropriate topology were 0.99991 and 0.99995, respectively. Moreover, study findings indicate that predicting the volume and surface area of fruit can be determined better using artificial neural network than using mathematical model. The proposed artificial neural network procedure applied in this study even minimized the complex calculations for estimating volume and surface area of fruit.

show abstract

Section: Introductionmentioning

confidence: 99%

Modeling of volume and surface area of apple from their geometric characteristics and artificial neural network

Ziaratban

Azadbakht

Ghasemnezhad

2016

International Journal of Food Properties

View full text Add to dashboard Cite

show abstract

“…To date, most researchers relied on micrometer or caliper measurements or digital image analysis to determine seed parameters (Ercisli et al, 2012;Seyedabadia et al, 2011;Shahin et al, 2006). The physical attributes of small objects, such as seeds of selected plant species, were not investigated based on 3D scans.…”

Section: Resultsmentioning

confidence: 99%

Numerical modelling of agricultural products on the example of bean and yellow lupine seeds

Anders¹,

Kaliniewicz²,

Markowski³

2015

International Agrophysics

View full text Add to dashboard Cite

A b s t r a c t. Numerical models of bean seeds cv. Złota Saxa and yellow lupine seeds cv. Juno were generated with the use of a 3D scanner, the geometric parameters of seeds were determined based on the models developed, and compared with the results of digital image analysis and micrometer measurements. Measurements of seed length, width and thickness performed with the use of a micrometer, 3D scanner and digital image analysis produced similar results that did not differ significantly at a = 0.05. The micrometer delivered the simplest and fastest measurements. The mean surface area of bean seeds cv. Złota Saxa and yellow lupine seeds cv. Juno, calculated with the use of mathematical formulas based on the results of micrometer measurements and digital image analysis, differed significantly from the mean surface area determined with a 3D scanner. No significant differences in seed volume were observed when this parameter was measured with a 3D scanner and determined with the use of mathematical formulas based on the results of digital image analysis and micrometer measurements. The only differences were noted when the volume of yellow lupine seeds cv. Juno was measured in a 25 ml liquid pycnometer.

show abstract

“…Lorestani and Tabatabaeefar (2006) recommended a power function to estimate the kiwi fruit mass by third projected area. Seyedabadi et al (2011) also suggested a power regression equation to estimate the mass of cantaloupes based on the third projected area.…”

Section: Resultsmentioning

confidence: 99%

“…In the case of mass modeling, Naderi-Boldaji et al (2008) determined models for predicting mass of Iranian grown apricot from its dimensions, projected areas and volumes; they found a nonlinear equation between mass and its minor diameter. Also, Hassan-Beygi et al (2010) and Seyedabadi et al (2011) used this method for predicting the mass of saffron and cantaloupe, respectively. The physical properties of different seeds and fruits have been determined by the other researchers; Zerun wheat (Işıklı et al 2012), rice (Mohapatra and Bal 2011), berberis fruit (Işıklı and Yılmaz 2011), mahua (Patel et al 2011), millet (Balasubramanian and Viswanathan 2010), olive fruit (Kılıçkan and Güner 2008), tangerine (Khanali et al 2007), pear (Wang 2004), sunflower seeds (Gupta and Das 1997) and soybean (Kulkarni et al 1993).…”

Section: Introductionmentioning

confidence: 99%

Models for predicting the mass of lime fruits by some engineering properties

et al. 2012

View full text Add to dashboard Cite

Grading fruits based on mass is important in packaging and reduces the waste, also increases the marketing value of agricultural produce. The aim of this study was mass modeling of two major cultivars of Iranian limes based on engineering attributes. Models were classified into three: 1-Single and multiple variable regressions of lime mass and dimensional characteristics. 2-Single and multiple variable regressions of lime mass and projected areas. 3-Single regression of lime mass based on its actual volume and calculated volume assumed as ellipsoid and prolate spheroid shapes. All properties considered in the current study were found to be statistically significant (ρ < 0.01). The results indicated that mass modeling of lime based on minor diameter and first projected area are the most appropriate models in the first and the second classifications, respectively. In third classification, the best model was obtained on the basis of the prolate spheroid volume. It was finally concluded that the suitable grading system of lime mass is based on prolate spheroid volume.

show abstract

Mass modeling of cantaloupe based on geometric attributes: A case study for Tile Magasi and Tile Shahri

Cited by 18 publications

References 15 publications

Modeling of volume and surface area of apple from their geometric characteristics and artificial neural network

Modeling of volume and surface area of apple from their geometric characteristics and artificial neural network

Numerical modelling of agricultural products on the example of bean and yellow lupine seeds

Models for predicting the mass of lime fruits by some engineering properties

Contact Info

Product

Resources

About