Detection of Pistachio Aflatoxin Using Raman Spectroscopy and Artificial Neural Networks

Document Type : Research Article

Authors

• R. Mohammadigol ¹
• M. H. Khoshtaghaza ²
• R. Malekfar ²
• M. Mirabolfathi ³
• A. M. Nikbakht ⁴

¹ Arak University

² Tarbiat Modares University

³ Iranian Research Institute of Plant Protection

⁴ Urmia University

https://doi.org/10.22067/jam.v5i1.28122

Abstract

Pistachio contamination to aflatoxin has been known as a serious problem for pistachio exportation. With regards to the increasing demand for Raman spectroscopy to detect and classify different materials and also the current experimental and technical problems for measuring toxin (such as being expensive and time-consuming), the main objective of this study was to detect aflatoxin contamination in pistachio by using Raman spectroscopy technique and artificial neural networks. Three sets of samples were prepared: non-contaminated (healthy) and contaminated samples with 20 and 100 ppb of the total aflatoxins (B1+B2+G1+G2). After spectral acquisition, considering to the results, spectral data were normalized and then principal components (PCs) were extracted to reduce the data dimensions. For classification of the samples spectra, an artificial neural network was used with a feed forward back propagation algorithm for 4 inputs and 3 neurons in hidden layer. Mean overall accuracy was achieved to be 98 percent; therefore, non-liner Raman spectra data modeling by ANN for samples classification was successful.

Keywords

• Aflatoxin
• ANN
• PCA
• Pistachio
• Raman Spectroscopy

20.1001.1.22286829.1394.5.1.1.2

References

Anon. 2012. Mycotoxins Legislation Worldwide European Mycotoxins Awareness Network.

Arrus, K., G. Blank, D. Abramson, R. Clear and R. Holley. 2005. Aflatoxin production by Aspergillus flavus in Brazil nuts. Journal of Stored Products Research 41: 513-527.

Boutrif, E. 1998. Prevention of aflatoxin in pistachios. Report no

.

Dennis, A. 2013a. Photo-Bleaching and Automatic Baseline Correction for Raman Spectroscopy.

Dennis, A. 2013b. Automatic Baseline Correction PerkinElmer company.

Dragacci, S. and F. Grosso and J. Gilbert. 2001. Immunoaffinity column cleanup with liquid chromatography for determination of aflatoxin M1 in liquid milk: collaborative study. Journal of AOAC International 84: 437-443.

Feng, S., R. Chen, J. Lin, J. Pan, G. Chen, Y. Li, M. Cheng, Z. Huang, J. Chen and H. Zeng. 2010. Nasopharyngeal cancer detection based on blood plasma surface-enhanced Raman spectroscopy and multivariate analysis. Biosensors and Bioelectronics 25: 2414-2419.

Gordon, S. H., B. C. Wheeler, R. B. Schudy, D. T. Wicklow and R. V. Greene. 1998. Neural network pattern recognition of photoacoustic FTIR spectra and knowledge-based techniques for detection of mycotoxigenic fungi in food grains. Journal of Food Protection® 61: 221-230.

Hagan, M. T. and H. B. Demuth and M. H. Beale. 1996. Neural network design. Pws Pub. Boston.

Huang, Z., S. K. Teh, W. Zheng, K. Lin, K. Y. Ho, M. Teh and K. G. Yeoh. 2010. In vivo detection of epithelial neoplasia in the stomach using image-guided Raman endoscopy. Biosensors and Bioelectronics 26: 383-389.

Ishikawa, S. and V. Gulick. 2013. An automated mineral classifier using Raman spectra. Computers & Geosciences 54: 259-268.

Jamshidi, B. 2012. Non-destractive taste characterization and classification of oranges using Vis/NIR spectroscopy. TMU(in Farsi).

Moallem, P. and A. Monajemi. 2007. A Heuristic Criterion for Goodness of Multi Layer Perceptron as a Classifier. in IDMC'07. Tehran, Iran.(in Farsi(

Moghadam, M. M. 2007. Study of pistachio contamination in processing terminals of Semnan province and evaluation of resistance of pistachio cultivars to Aspergillus flavus and aflatoxin B1 .IPRI, AREO(in Farsi(

Næs, T., K. Kvaal, T. Isaksson and C. Miller. 1993. Artificial neural networks in multivariate calibration. Journal of Near Infrared Spectroscopy 1: 1.

Nicolai, B. M., K. Beullens, E. Bobelyn, A. Peirs, W. Saeys, K. I. Theron and J. Lammertyn. 2007. Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: A review. Postharvest Biology and Technology 46: 99-118.

Parnis, J. M. and K. B. Oldham. 2013. Beyond the Beer–Lambert law: The dependence of absorbance on time in photochemistry. Journal of Photochemistry and Photobiology A: Chemistry 267: 6-10.

Pearson, S., A. Candlish, K. Aidoo and J. Smith. 1999. Determination of aflatoxin levels in pistachio and cashew nuts using immunoaffinity column clean-up with HPLC and fluorescence detection. Biotechnology techniques 13: 97-99.

Sherafati, A. 2008. Pistachio application (challenges and solutions). Sarva Publication(in Farsi(

Sigurdsson, S., P. A. Philipsen, L. K. Hansen, J. Larsen, M. Gniadecka and H.-C. Wulf. 2004. Detection of skin cancer by classification of Raman spectra. Biomedical Engineering, IEEE Transactions on 51: 1784-1793.

Sinha, K. K. 1999. Testing methods for aflatoxins in foods. Food & Nutrition Bulletin 20: 458-464.

Stroka, J., E. Anklam, U. Jorissen and J. Gilbert. 2000. Immunoaffinity column cleanup with liquid chromatography using post-column bromination for determination of aflatoxins in peanut butter, pistachio paste, fig paste, and paprika powder: collaborative study. Journal of AOAC International 83: 320-340.

Tajabadipour, A. 2008. Evaluation of the effectiveness of different devices in the process of separation phase in the garden of nuts to aflatoxin contamination suspected: .IPRI, AREO(in Farsi(

Teh, S. K., W. Zheng, K. Y. Ho, M. Teh, K. G. Yeoh and Z. Huang. 2008. Diagnosis of gastric cancer using near-infrared Raman spectroscopy and classification and regression tree techniques. Journal of biomedical optics 13: 034013-034013-034018.

Teh, S. K., W. Zheng, K. Y. Ho, M. Teh, K. G. Yeoh and Z. Huang. 2010. Near‐infrared Raman spectroscopy for optical diagnosis in the stomach: Identification of Helicobacter‐pylori infection and intestinal metaplasia. International Journal of Cancer 126: 1920-1927.

Wu, D. and S. Feng and Y. He. 2007. Infrared spectroscopy technique for the nondestructive measurement of fat content in milk powder. Journal of dairy science 90: 3613-3619.