Intelligent Classification Of Charleston Gray Watermelon Variety Based On Fruit Ripeness Using Acoustic Signal Processing

Document Type : Research Paper


1 Ph.D. Student, Department of Biosystems Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran

2 Associate Professor, Department of Biosystems Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran

3 Assistant Professor, Department of Biosystems Engineering, Faculty of Agriculture, University of Tabriz, Tabriz, Iran


According to the water crisis in the country and watermelon traditional irrigation process, it is possible to reduce planting and consequently increase the price of this product in the coming years, which highlights the necessity of indices for choosing high-quality watermelons. The purpose of this study is classification of the Charleston Gray watermelon variety into unripe, ripe and overripe classes, in this regard acoustic signals processing, data mining algorithms, and artificial intelligence techniques have been used for this purpose. After preparing the samples, firs through a capacitive microphone, signals acquired from different positions of watermelon using a solenoid and then, samples classes were determined by performing sensory evaluations. Signal processing techniques in time, frequency, processing domains and wavelet transformation were used for extraction of important features from acoustic signals of the watermelons, then some of the features that were significant in classification were selected using the t-test. Support Vector Machines and K Nearest Neighbor algorithms were used for sample classification. Totally 52% of the samples were classified correctly by experts. For metal ball, SVM algorithm with cubic kernel function resulted 78% correctly classification for acoustic signals obtained from middle position and Gaussian kernel function resulted 75% correctly classification for signals obtained from stem side position. K Nearest Neighbor algorithm equipped with the cosine distance resulted highest samples classification with a precision of 79% for the metal ball and the position of the stem side.


Main Subjects

Abbaszadeh, R., Rajabipour, A., Ahmadi, H., Mahjoob, M. J. and Delshad, M. (2010). Nondestructive evaluation of watermelon ripeness using LDV. Proceedings of the 6th National Congress of Agricultural Machinery Engineering and Mechanization. Karaj. Iran. Sep15-16. (in Farsi)
 Abbaszadeh, R., Rajabipour, A., Labbafi, R. and Ahmadi, H. (2012). Prediction of watermelon customer-friendly based on sensory evaluation data using expert fuzzy model. Proceedings of the 7th National Congress of Agricultural Engineering (Biosystems Mechanics) and Mechanization. Sep 4-6.  Shiraz. Iran. (in Farsi)
Ahmadi, K. (2015). Agricultural statistics first volume crops. Ministry of Agriculture, Department of Planning and Economy. (in Farsi)
Anon. (2013). FAO Food and Nutrition Series. Statistical database http://faostat.
Armstrong, P., Zapp, H., Brown, G. (1989). Impulsive excitation of acoustic vibrations in apples for firmness determination. American Society of Agricultural Engineers.
Bourne, M. (2002). Food texture and viscosity: concept and measurement. Academic press.
Coifman, R.R., M.V. Wickerhauser. (1992). Entropy-based Algorithms for best basis selection. IEEE Trans. on Inf. Theory. 38(2). 713–718.
Diezma-Iglesias, B., Ruiz-Altisent, M., & Barreiro, P. (2004). Detection of Internal Quality in Seedless Watermelon by Acoustic Impulse Response. Biosystems Engineering. 88(2). 221-230.
Farabee, M. L., & Stone, M. L. (1991). Determination of watermelon maturity with sonic impulse testing. American Society of Agricultural Engineers.
Han, J., Pei, J., & Kamber, M. (2011). Data mining: concepts and techniques. Elsevier.
Karmollachaab, H. (2012). Nondestructive internal quality analysis of watermelons by acoustic technique and artificial neural networks. M. Sc. Thesis. Faculty of Agriculture. Tabriz University. Tabriz. Iran. (in Farsi)
Marple, S. Lawrence. (1987). Digital Spectral Analysis. Chapter 7. Englewood Cliffs, NJ: Prentice Hall.
Muramatsu, N., Tanaka, K., Asakura, T., Ishikawa-Takano, Y., Sakurai, N., Wada, N., Nevins, D. J. (1997). Critical comparison of an accelerometer and a laser Doppler vibrometer for measuring fruit firmness. HortTechnology. 7(4). 434-438.
Nourain, J., Ying, Y. B., Wang, J., & Rao, X. (2004). Determination of acoustic vibration in watermelon by finite element modeling. Paper presented at the Optics East.
Omid, M., A. Mahmoudi, M. H. Omid. (2009). An intelligent system for sorting pistachio nut varieties. Expert Systems with Applications. 36(9): 11528-11535.
Proakis, John G., Dimitris G. Manolakis. (1996). Digital Signal Processing: Principles, Algorithms, and Applications. Englewood, Prentice Hall. Section 12.3.3
Saadatiniya, M., Emadi, B. (2011). Determination of ripeness of watermelon fruit based on acoustic methods. 1st National Congress of Mechanisation and Modern Technologies in Agricultural. Ahvaz. Iran. Fep16-18. (in Farsi)
Stone, M., Armstrong, P., Zhang, X., Brusewitz, G., & Chen, D. (1996). Watermelon maturity determination in the field using acoustic impulse impedance techniques. Transactions of the ASAE. 39(6). 2325-2330.
Strang, G. (1989). Wavelets and Dilation Equations: A Brief Introduction. SIAM Review. Society for Industrial and Applied Mathematics. 31(4). 614-627.
Taniwaki, M., Hanada, T., & Sakurai, N. (2009). Postharvest quality evaluation of “Fuyu” and “Taishuu” persimmons using a nondestructive vibrational method and an acoustic vibration technique. Postharvest Biology and Technology. 51(1). 80-85.
Zeng, W., X. Huang, S. Müller Arisona., I. V. McLoughlin (2013). Classifying watermelon ripeness by analysing acoustic signals using mobile devices. Personal and Ubiquitous Computing. 18(7): 1753-1762.