Prediction of lateral surface, volume and sphericity of pomegranate using MLP artificial neural network

Document Type : Research Article

Authors

• A. Rohani ¹
• S. I. Saedi ²
• H. Gerailue ³
• M. H. Aghkhani ¹

¹ Department of Biosystems Engineering, College of Agriculture, Ferdowsi University of Mashhad, Mashhad, Iran

² Department of Agricultural Machinery, Faculty of Agricultural Engineering and Technology,University College of Agriculture and Natural Resources, University of Tehran, Tehran, Iran

³ Department of Electrical and Robotics Engineering, Faculty of Electronics, University of Shahrood, Shahrood, Iran

https://doi.org/10.22067/jam.v5i2.28130

Abstract

Introduction: Fast and accurate determination of geometrical properties of agricultural products has many applications in agricultural operations like planting, cultivating, harvesting and post-harvesting. Calculations related to storing, shipping and storage-coating materials as well as peeling time and surface-microbial concentrations are some applications of estimating product volume and surface area. Sphericity is also a parameter by which the shape differences between fruits, vegetables, grains and seeds can be quantified. This parameter is important in grading systems and inspecting rolling capability of agricultural products. Bayram presented a new dimensional method and equation to calculate the sphericity of certain shapesand some granular food materials (Bayram, 2005). Kumar and Mathew proposed atheoretically soundmethod for estimating the surface area of ellipsoidal food materials (Kumar and Mathew, 2003). Clayton et al. used non-linear regression models for calculation of apple surface area using the fruit mass or volume (Clayton et al., 1995). Humeida and Hobani predicted surface area and volume of pomegranates based on the weight and geometrical diametermean (Humeida and Hobani, 1993). Wang and Nguang designeda low cost sensor system to automatically compute the volume and surface area of axi-symmetricagricultural products such as eggs, lemons, limes and tamarillos (Wang and Nguang, 2007). The main objective of this study was to investigate the potential of Artificial Neural Network (ANN) technique as an alternative method to predict the volume, surface area and sphericity of pomegranates.
Materials and methods: The water displacement method (WDM) was used for measuring the actual volume of pomegranates. Also, the sphericity and surface area are computed by using analytical methods. In this study, the neural MLP models were designed based upon the three nominal diameters of pomegranatesas variable inputs, while the output model consisted of each of the three parameters including the volume, sphericity and surface area. Priorto any ANN training process, the data normalized over the range of [0, 1]. Fig. 1 shows a MLP with one hidden layer. In this study, back-propagation with declininglearning-rate factor (BDLRF) training algorithm was employed. The mean absolute percentage error (MAPE) and the coefficient of determinationof the linear regression line between the predicted values fromthe MLP model and the actual output were used to evaluate the performance of the model.
Results and Discussion: The number of neurons in the hidden layerand also theoptimal values for the learning parameters η and αwere selected bytrial and error method. The bestresult was achieved with five neurons in the hidden layer. The results showed thatthe optimum modelof performance was obtained at constant momentum termequal to 0.8 and learning rate equal to 0.9. In this study, 300 epochs were selected as the starting points of the BDLRF. Some statistical characteristics of the actual values of volume were estimated by WDM, surface area was computed by equation (3) and sphericity of pomegranates was computed by equation (1) and the predicted values of them using the neural network method were shown in Table 1. The obtained results verified that the differences between theactual values and the estimated ones can be ignored. But, the predicted values of the volume using the MLP model in comparison with equation (2) are much closer to the actual values. Statistical comparisons of desired and predicted data and the corresponding p values are given in Table 2. The results showed that P-value was greater than 0.08 in all cases. Therefore, there was no significant difference between the statistical parameters. However, the P-value for equation 2 is much less than that of the MLP model. The results shown in Figures 2, 3 and 4 show that the coefficients of determination between actual and predicted data were greater than 0.9. Considering all the results in our study, the MLP model is more accurate than the WDM and analytical methods.
Conclusions: In this paper, we first measure the actual volume of the pomegranate using WDM and equation (2). Also, assuming an elliptical fruit, the sphericity and surface area are computed analytically based on the three nominal diameters of a pomegranate. Finally, the results of achievements of the MLP designed revealed that the MLP model could be successfully applied to the prediction of thesphericity and surface area. Therefore, the MLP model can be a viable alternative to the analytical methods. However, this is possible only if there is a precise way to compute the three nominal diameters of pomegranates. In addition, according to the MAPE, the accuracy of the MLP model in prediction of volume of pomegranates was twicethe analytical method.

Keywords

• Neural Network
• Pomegranate
• Sphericity
• Surface area
• Volume

References

1. Banks, N. H. 1985. Surface area estimation of potato tubers. Potato Research 28: 487-495.

2. Baten, W. D., and R. E. Marshall. 1943. Some methods of approximate prediction of surface area of fruits. Journal of Agricultural Research 66: 357-373.

3. Bayram, M. 2005. Determination of the sphericity of granular food materials. Journal of Food Engineering 68 (3): 385-390.

4. Clayton, M., N. D. Amos., N. H. Banks., and R. H. Morton. 1995. Estimation of apple fruit surface area. New Zealand Journal of Crop and Horticulture Science 23: 345-349.

5. Du, C. J., and D. W. Sun. 2006. Estimating the surface area and volume of ellipsoidal ham using computer vision. Journal of Food Engineering 73 (3): 260-268.

6. Eifert, J. D., G. C. Sanglay, D. Lee, S. S. Summer, and M. D. Pierson. 2006. Prediction of raw produce surface area from weight measurement. Journal of Food Engineering 74 (4): 552-556.

7. Frechette, R. J., and J. W. Zahradnik. 1966. Surface area–weight relationships for Macintosh apples. Transactions of the American Society of Agricultural Engineers 9: 526-527.

8. Haykin, S. 1994. Neural networks: A comprehensive foundation. McMillan College Publishing Company, New York.

9. Hershko, V., D. Weisman, and A. Nussinovitch. 1998. Method for studying surface topography and roughness of onion and garlic skins for coating purposes. Journal of Food Science 63 (2): 317-321.

10. Humeida, M. A., and A. I. Hobani. 1993. Physical properties of pomegranate fruits. Journal of King Saud University Agricultural Science 5 (2): 165-175.

11. Igathinathane, C., and P. K. Chattopadhyay. 2000. Surface area of general ellipsoid shaped food materials by simplified regression equation method. Journal of Food Engineering 46 (4): 257-266.

12. Igathinathane, C., J. D. Davis., J. L. Purswell., and E. P. Columbus. 2010. Application of 3D scanned imaging methodology for volume, surface area, and envelope density evaluation of densified biomass. Bioresource Technology 101 (11): 4220-4227.

13. Jain, R. K., and S. Bal. 1997. Properties of pearl millet. Journal of Agricultural Engineering Research 66 (2): 85-91.

14. Kerdpiboon, S., W. L. Kerr, and S. Devahastin. 2006. Neural network prediction of physical property changes of dried carrot as a function of fractal dimension and moisture content. Food Research International 39 (10): 1110-1118.

15. Khojastehnazhand, M., M. Omid, and A. Tabatabaeefar. 2009. Determination of orange volume and surface area using image processing technique. Int. Agrophys. 23: 237-242.

16. Kumar, V. A., and S. Mathew. 2003. A Method for estimating the surface area of ellipsoidal food materials. Biosystems Engineering 85 (1): 1-5.

17. Makarian, H., and A. Rohani. 2011. Prediction of spatial distribution patterns of Hordeum glaucum steud. Population using neural network model. Journal of Plant Protection 24 (4): 471-480.(in Farsi).

18. Maw, B. W., Y. C. Hung, E. W. Tollner, D. A. Smittle, and B. G. Mullinix. 1996. Physical and mechanical properties of fresh and stored sweet onions. Transactions of the American Society of Agricultural Engineers 39 (2): 633-637.

19. Mohsenin, N. N. 1978. Physical properties of plant and animal materials. Gordon and Breach Science Publishers, New York.

20. Ranjbar, I., M. H. Abbaspour-Fard., Y. Ajabshirchi, and A. Rohani. 2010. Prediction of John Deere tractor repair and maintenance costs by using two different structures of MLP artificial neural network. Agriculture Economics & Development 22 (2): 87-96. (In Farsi).

21. Razmi-Rad, E., B. Ghanbarzadeh, S. M. Mosavi, Z. Emam-Djomeh, and J. Khazaei. 2007. Prediction of rheological properties of Iranian bread dough from chemical composition of wheat flour by using artificial neural networks. Journal of Food Engineering 81 (4): 728-734.

22. Rohani, A., M. H. Abbaspour-Fard, and S. Abdolahpour. 2011. Prediction of tractor repair and maintenance costs using artificial neural network. Expert Sys. Applications 38: 8999-9007.

23. Rohani, A., and H. Makarian. 2011. Making weed management maps by artificial neural networks for using in precision agriculture. Journal of Agricultural Machinery Engineering 1 (2): 74-83. (In Farsi).

24. Sabilov, C. M., D. Boldor, K. M. Keener, and B. E. Farkas. 2002. Image processing method to determine surface area and volume of axisymmetric agricultural products. International Journal of Food Properties 5 (3): 641-653.

25. Therdthai, N., and W. Zhou. 2001. Artificial neural network modelling of the electrical conductivity property of recombined milk. Journal of Food Engineering 50 (2): 107-111.

26. Turrell, F. M., J. P. Carlson, and L. J. Klotz. 1946. Tables of coefficients for estimating oblate and prolate spheriodal surfaces and volumes from spherical surfaces and volumes. Proceedings of American Society for Horticultural Science 48: 326.

27. Vakil-Baghmisheh, M. T., and N. Pavešic. 2001. Back-propagation with declining learning rate. Proceeding of the 10th Electrotechnical and Computer Science Conference, Portorož, Slovenia B: 297-300.

28. Wang, T. Y., and S. K. Nguang. 2007. Low cost sensor for volume and surface area computation of axi-symmetric agricultural products. Journal of Food Engineering 79 (3): 870-877.

29. Zarifneshat, S., A. Rohani, H. R. Ghassemzadeh, M. Sadeghi, A. Ebrahim, and M. Zarifneshat. 2012. Predictions of apple bruise volume using artificial neural network. Computers and Electronics in Agriculture 82: 75-86.