A New Classification Method for Stored Grain Insect Infestation Using KIII and SVM Based Electronic Nose

Abstract:

Insect infestation is a common problem for stored grain. In this paper, a novel pattern recognition approach combining an olfactory neural network entitled KIII with support vector machine (SVM) is proposed and used in conjunction with an electronic nose to generate recognition models. Using this approach, feature vectors are firstly processed by KIII model which stimulates information processing function of olfactory bulb, and then classified by SVM. Through optimization of SVM model parameters, the data are mapped into high dimension space and the stored wheat samples with different degrees of insect damage are distinguished successfully. The experimental results demonstrate that the proposed method can achieve up to 100% classification rate and significantly outperforms the conventional KIII-Minimum Euclidean Distance Classifier.

• Periodical: Advanced Materials Research (Volumes 1006-1007)
• Pages: 870-873
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1006-1007.870
• Online since: August 2014
• Authors: Jie Li, Dong Lai Xu
• Keywords: Olfactory Neural Network, Pattern Recognition, Stored-Grain Insect, Support Vector Machine (SVM)

References

[1] Neethirajan, S., Karunakaran, C., Jayas, D.S., White, N.D.G.: Food Control Vol. 18(2007), pp.157-162.

[2] Milner M.A.X., Lee M.R., Katz R.: Journal of Economic Entomology Vol. 43(1950), pp.933-935.

[3] Karunakaran C., Jayas D.S., White N.D.G.: Cereal Chemistry Vol. 80 (2003), pp.553-557.

[4] Karunakaran C., Jayas D.S., White N.D.G.: Journal of Stored Products Research Vol. 40 (2004), pp.507-516.

[5] Rajendran S., Steve L. T.: Advances in Food and Nutrition Research Vol. 49 (2005), pp.163-232.

[6] Fornal J., Jelinski T., Sadowska J., Grundas S., Nawrot J., Niewiada A., Warchalewski J.R., Blaszczak W.: Journal of Stored Products Research Vol. 43 (2007), pp.142-148.

DOI: 10.1016/j.jspr.2006.02.003

[7] Haff R., Toyofuku N.: Sensing and Instrumentation for Food Quality and Safety Vol. 2 (2008), pp.262-273.

[8] Persaud K.C., Dodd G.:. Nature Vol. 299 (1982), pp.352-355.

[9] Martí M.P., Busto O., Guasch J., Boqué R.: TrAC Trends in Analytical Chemistry Vol. 24 (2005), pp.57-66.

DOI: 10.1016/j.trac.2004.09.006

[10] Rock F., Barsan N., Weimar U.: Chemical Reviews Vol. 108 (2008), pp.705-725.

[11] Stetter J.R., Findlay Jr M.W., Schroeder K.M., Yue C., Penrose W.R.: Analytica Chimica Acta Vol. 284 (1993), pp.1-11.

DOI: 10.1016/0003-2670(93)80001-2

[12] Hu, J.: International Conference on Information Acquisition. Shandong, P.R. China (2006).

[13] Zhang H., Wang J.: Journal of Stored Products Research Vol. 43 (2007), pp.489-495.

[14] Chang H.J., Freeman W.J.: Int J of Bifurcation and Chaos Vol. 2 (1998), p.321–345.

[15] Chang H.J., Freeman, W.J.: Int. J. Bifurcation and Chaos Vol. 11 (1998), p.2107–2123.

[16] Freeman W.J.: Int J of Bifurcation and Chaos Vol. 10 (2001), p.2307–2322.

[17] R. Kozma, W.J. Freeman: Int J Bifurcation Chaos Vol. 6 (2001), pp.1607-1629.

[18] V. Vapnik: The Nature of Statistical Learning Theory (New York, Springer-Verlag, 1995).