Predicting Oil Content of Fresh Palm Fruit Using Transmission-Mode Ultrasonic Technique

In this paper, an ultrasonic technique is proposed to predict oil content in a fresh palm fruit. This is accomplished by measuring the attenuation based on ultrasonic transmission mode. Several palm fruit samples with known oil content by Soxhlet extraction (ISO9001:2008) were tested with our ultrasonic measurement. Amplitude attenuation data results for all palm samples were collected. The Feedforward Neural Networks (FNNs) are applied to predict the oil content for the samples. The Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of the FNN model for predicting oil content percentage are 7.6186 and 5.2287 with the correlation coefficient (R) of 0.9193.

Authors:

• Sutthawee Suwannarat
• Thanate Khaorapapong
• Mitchai Chongcheawchamnan

Keywords:

• Non-destructive
• ultrasonic testing
• oil content
• fresh palm fruit
• neural network.

References:

[1] R. Sambantamurthi, K. Sundram, Y.-A. Tan, "Chemistry and
biochemistry of palm oil," Progress in Lipid Research, vol. 39, pp. 507-
558, 2000.
[2] Office of Agricultural Economics, Situation and trends in key
agricultural year 2554, Ministry of Agriculture, Thailand, 2011.
[3] P. Butz, C. Hofmann, B. Tauscher, "Recent developments in
noninvasive techniques for fresh fruit and vegetable internal quality
analysis," J. FoodSci, vol. 70, no. 9, pp. 131-R141, November 2005.
[4] A. Mizrach, "Ultrasonic technology for quality evaluation of fresh fruit
and vegetables in pre- and postharvest processes," Postharvest Biology
and Technology, vol. 48, pp. 315-330, 2008.
[5] A. Mizrach, U. Flitsanov, "Nondestructive ultrasonic determination of
avocado softening process," Journal of Food Engineering, vol. 40, pp.
139-144, 1999.
[6] J. Krautkramer, H. Krautkramer, Ultrasonic testing of materials.,
Springer-Verlag, Heidelberg, Germany, 1990.