Rapid Detection of Fraudulent Rice Using Low-Cost Digital Sensing Devices and Machine Learning
Abstract
:1. Introduction
2. Materials and Methods
2.1. Samples Description
2.2. Near-Infrared Measurement
2.3. Electronic Nose Measurement
2.4. Statistical Analysis and Machine Learning Modelling
3. Results and Discussion
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Viinikainen, T. Food frauds—Intention, detection and management. In Food Safety Technical Toolkit for Asia and the Pacific; Markus, L., Cornelia, B., Isabella, A., Dharmapuri, S., Eds.; FAO: Bangkok, Thailand, 2021. [Google Scholar]
- Macready, A.L.; Hieke, S.; Klimczuk-Kochańska, M.; Szumiał, S.; Vranken, L.; Grunert, K.G. Consumer trust in the food value chain and its impact on consumer confidence: A model for assessing consumer trust and evidence from a 5-country study in Europe. Food Policy 2020, 92, 101880. [Google Scholar] [CrossRef]
- Śliwińska-Bartel, M.; Burns, D.T.; Elliott, C. Rice fraud a global problem: A review of analytical tools to detect species, country of origin and adulterations. Trends Food Sci. Technol. 2021, 116, 36–46. [Google Scholar] [CrossRef]
- Vaishna, R.L.; Satyavathi, V.V.; Anupama, K. Single grain analysis of the complex Basmati rice samples to determine the nature of admixtures and accurate adulteration quantification. J. Food Sci. Technol. 2022, 59, 1658–1663. [Google Scholar] [CrossRef]
- Peijin, T.; Kevin, L.J.; Tingting, W.; Elejalde, U.; Hongchao, Z.; Yuanrong, J.; Wenming, C. Rapid identification of the variety and geographical origin of Wuyou No.4 rice by fourier transform near-infrared spectroscopy coupled with chemometrics. J. Cereal Sci. 2021, 102, 103322. [Google Scholar] [CrossRef]
- Liu, W.; Xu, X.; Liu, C.; Zheng, L. Nondestructive Detection of Authenticity of Thai Jasmine Rice Using Multispectral Imaging. J. Food Qual. 2021, 2021, 6642220. [Google Scholar] [CrossRef]
- Yusoff, M.R.; Harun, A.R.; Ahmad, F. Current Applicable DNA Markers for Marker Assisted Breeding in Rice (Oryza sativa L.). In Recent Advances in Rice Research; IntechOpen: London, UK, 2020. [Google Scholar]
- Jamal Gilani, S.; Zzafar, A.; Imam, S.S.; Ahmad, J. Application of fingerprinting techniques in authentication and traceability of fruits and vegetables. In Fingerprinting Techniques in Food Authentication and Traceability, 1st ed.; Siddiqi, K.S., Nollet, L.M.L., Eds.; CRC Press: Boca Raton, FL, USA, 2018; p. 448. [Google Scholar]
- Wongsaipun, S.; Theanjumpol, P.; Kittiwachana, S. Development of a Universal Calibration Model for Quantification of Adulteration in Thai Jasmine Rice Using Near-infrared Spectroscopy. Food Anal. Methods 2021, 14, 997–1010. [Google Scholar] [CrossRef]
- Li, C.; Li, B.; Ye, D. Analysis and Identification of Rice Adulteration Using Terahertz Spectroscopy and Pattern Recognition Algorithms. IEEE Access 2020, 8, 26839–26850. [Google Scholar] [CrossRef]
- Aznan, A.; Viejo, C.G.; Pang, A.; Fuentes, S. Rapid Assessment of Rice Quality Traits Using Low-Cost Digital Technologies. Foods 2022, 11, 1181. [Google Scholar] [CrossRef]
- Erlangga, F.; Wijaya, D.R.; Wikusna, W. Electronic Nose Dataset for Classifying Rice Quality using Neural Network. In Proceedings of the 2021 9th International Conference on Information and Communication Technology (ICoICT), Yogyakarta, Indonesia, 3–5 August 2021; pp. 462–466. [Google Scholar]
- Neamsorn, N.; Changrue, V.; Chanbang, Y.; Kunasakdakul, K.; Theanjumpol, P.; Kantakaew, P. Electronic nose system for rancidity and insect monitoring of brown rice. E3S Web Conf. 2020, 187, 04015. [Google Scholar] [CrossRef]
- Jiarpinijnun, A.; Osako, K.; Siripatrawan, U. Visualization of volatomic profiles for early detection of fungal infection on storage Jasmine brown rice using electronic nose coupled with chemometrics. Measurement 2020, 157, 107561. [Google Scholar] [CrossRef]
- Zhang, J.; Zhang, B.; Dong, J.; Tian, Y.; Lin, Y.; Fang, G.; Wang, S. Identification of mouldy rice using an electronic nose combined with SPME-GC/MS. J. Stored Prod. Res. 2022, 95, 101921. [Google Scholar] [CrossRef]
- Udomkun, P.; Innawong, B.; Niruntasuk, K. The feasibility of using an electronic nose to identify adulteration of Pathumthani 1 in Khaw Dok Mali 105 rice during storage. J. Food Meas. Charact. 2018, 12, 2515–2523. [Google Scholar] [CrossRef]
- Viejo, C.G.; Fuentes, S.; Hernandez-Brenes, C. Smart Detection of Faults in Beers Using Near-Infrared Spectroscopy, a Low-Cost Electronic Nose and Artificial Intelligence. Fermentation 2021, 7, 117. [Google Scholar] [CrossRef]
- Pu, Y.; Pérez-Marín, D.; O’Shea, N.; Garrido-Varo, A. Recent Advances in Portable and Handheld NIR Spectrometers and Applications in Milk, Cheese and Dairy Powders. Foods 2021, 10, 2377. [Google Scholar] [CrossRef]
- Pasquini, C. Near infrared spectroscopy: A mature analytical technique with new perspectives—A review. Anal. Chim. Acta 2018, 1026, 8–36. [Google Scholar] [CrossRef]
- Tantalaki, N.; Souravlas, S.; Roumeliotis, M. Data-Driven Decision Making in Precision Agriculture: The Rise of Big Data in Agricultural Systems. J. Agric. Food Inf. 2019, 20, 344–380. [Google Scholar] [CrossRef]
- Raj, G.V.S.B.; Dash, K.K. Comprehensive study on applications of artificial neural network in food process modeling. Crit. Rev. Food Sci. Nutr. 2020, 62, 2756–2783. [Google Scholar] [CrossRef]
- Gonzalez Viejo, C.; Fuentes, S.; Godbole, A.; Widdicombe, B.; Unnithan, R.R. Development of a low-cost e-nose to assess aroma profiles: An artificial intelligence application to assess beer quality. Sens. Actuators B Chem. 2020, 308, 127688. [Google Scholar] [CrossRef]
- Viejo, C.G.; Tongson, E.; Fuentes, S. Integrating a Low-Cost Electronic Nose and Machine Learning Modelling to Assess Coffee Aroma Profile and Intensity. Sensors 2021, 21, 2016. [Google Scholar] [CrossRef]
- Gonzalez Viejo, C.; Torrico, D.D.; Dunshea, F.R.; Fuentes, S. Development of Artificial Neural Network Models to Assess Beer Acceptability Based on Sensory Properties Using a Robotic Pourer: A Comparative Model Approach to Achieve an Artificial Intelligence System. Beverages 2019, 5, 33. [Google Scholar] [CrossRef]
- Burden, F.; Winkler, D. Bayesian Regularization of Neural Networks. In Artificial Neural Networks: Methods and Applications; Livingstone, D.J., Ed.; Humana Press: Totowa, NJ, USA, 2009; pp. 23–42. [Google Scholar]
- Kayri, M. Predictive Abilities of Bayesian Regularization and Levenberg–Marquardt Algorithms in Artificial Neural Networks: A Comparative Empirical Study on Social Data. Math. Comput. Appl. 2016, 21, 20. [Google Scholar] [CrossRef] [Green Version]
- Sariev, E.; Germano, G. Bayesian regularized artificial neural networks for the estimation of the probability of default. Quant. Financ. 2019, 20, 311–328. [Google Scholar] [CrossRef]
- Oppong, D.; Panpipat, W.; Chaijan, M. Chemical, physical, and functional properties of Thai indigenous brown rice flours. PLoS ONE 2021, 16, e0255694. [Google Scholar] [CrossRef] [PubMed]
- Saleh, A.S.; Wang, P.; Wang, N.; Yang, L.; Xiao, Z. Brown Rice Versus White Rice: Nutritional Quality, Potential Health Benefits, Development of Food Products, and Preservation Technologies. Compr. Rev. Food Sci. Food Saf. 2019, 18, 1070–1096. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Ciurczak, E.W.; Igne, B.; Workman, J., Jr.; Burns, D.A. Handbook of Near-Infrared Analysis; CRC Press: Boca Raton, FL, USA, 2021. [Google Scholar]
- Zhao, Q.; Yousaf, L.; Xue, Y.; Shen, Q. Changes in flavor of fragrant rice during storage under different conditions. J. Sci. Food Agric. 2020, 100, 3435–3444. [Google Scholar] [CrossRef]
- The Good Scents Company Information System. Available online: https://www.thegoodscentscompany.com/ (accessed on 13 October 2022).
- Power, A.C.; Jones, J.; NiNeil, C.; Geoghegan, S.; Warren, S.; Currivan, S.; Cozzolino, D. What’s in this drink? Classification and adulterant detection in Irish Whiskey samples using near infrared spectroscopy combined with chemometrics. J. Sci. Food Agric. 2021, 101, 5256–5263. [Google Scholar] [CrossRef]
- Chen, Y.; Bin, J.; Zou, C.; Ding, M. Discrimination of Fresh Tobacco Leaves with Different Maturity Levels by Near-Infrared (NIR) Spectroscopy and Deep Learning. J. Anal. Methods Chem. 2021, 2021, 9912589. [Google Scholar] [CrossRef]
- Santos, I.A.; Conceição, D.G.; Viana, M.B.; Silva, G.D.J.; Santos, L.S.; Ferrão, S.P.B. NIR and MIR spectroscopy for quick detection of the adulteration of cocoa content in chocolates. Food Chem. 2021, 349, 129095. [Google Scholar] [CrossRef]
- Teye, E.; Amuah, C.L.; McGrath, T.; Elliott, C. Innovative and rapid analysis for rice authenticity using hand-held NIR spectrometry and chemometrics. Spectrochim. Acta Part A Mol. Biomol. Spectrosc. 2019, 217, 147–154. [Google Scholar] [CrossRef]
- Centonze, V.; Lippolis, V.; Cervellieri, S.; Damascelli, A.; Casiello, G.; Pascale, M.; Logrieco, A.F.; Longobardi, F. Discrimination of geographical origin of oranges (Citrus sinensis L. Osbeck) by mass spectrometry-based electronic nose and characterization of volatile compounds. Food Chem. 2018, 277, 25–30. [Google Scholar] [CrossRef]
- De Araújo, T.K.L.; Nóbrega, R.O.; Fernandes, D.D.D.S.; de Araújo, M.C.U.; Diniz, P.H.G.D.; da Silva, E.C. Non-destructive authentication of Gourmet ground roasted coffees using NIR spectroscopy and digital images. Food Chem. 2021, 364, 130452. [Google Scholar] [CrossRef] [PubMed]
- Wilde, A.S.; Haughey, S.A.; Galvin-King, P.; Elliott, C.T. The feasibility of applying NIR and FT-IR fingerprinting to detect adulteration in black pepper. Food Control 2019, 100, 1–7. [Google Scholar] [CrossRef] [Green Version]
- Peng, Q.; Chen, J.; Meng, K.; Zheng, H.; Chen, G.; Xu, X.; Lin, Z.; Xie, G. Rapid detection of adulteration of glutinous rice as raw material of Shaoxing Huangjiu (Chinese Rice Wine) by near infrared spectroscopy combined with chemometrics. J. Food Compos. Anal. 2022, 111, 104563. [Google Scholar] [CrossRef]
- Xiao, R.; Liu, L.; Zhang, D.; Ma, Y.; Ngadi, M.O. Discrimination of organic and conventional rice by chemometric analysis of NIR spectra: A pilot study. J. Food Meas. Charact. 2018, 13, 238–249. [Google Scholar] [CrossRef]
- Arslan, M.; Zareef, M.; Tahir, H.E.; Zhang, J.; Ahmad, W.; Rakha, A.; Shi, J.; Xiaobo, Z.; Khan, M.R. Discrimination of basmati rice adulteration using colorimetric sensor array system. Food Control 2021, 132, 108513. [Google Scholar] [CrossRef]
- Srinuttrakul, W.; Mihailova, A.; Islam, M.D.; Liebisch, B.; Maxwell, F.; Kelly, S.D.; Cannavan, A. Geographical Differentiation of Hom Mali Rice Cultivated in Different Regions of Thailand Using FTIR-ATR and NIR Spectroscopy. Foods 2021, 10, 1951. [Google Scholar] [CrossRef] [PubMed]
Product Category | Rice Types | Brand | Abbreviation | |
---|---|---|---|---|
Adulterated Rice 1 | Basmati | Grown in Pakistan | Riviana | BSR |
Basmati 1 | Grown in India | Woolworths | BAW | |
Adulterated Rice 2 | Sushi rice | Grown in Australia | SunRice | SRS |
Sushi rice 1 | Grown in the USA | Pandaroo | PDR | |
Adulterated Rice 3 | Basmati | Aromatic | Riviana | BSR |
Long-grain 1 | Non-aromatic | Woolworths | LGW | |
Adulterated Rice 4 | Jasmine | Aromatic | Coles | JAS |
Long-grain 1 | Non-aromatic | Woolworths | LGW | |
Adulterated Rice 5 | Khoshihikari | Premium | Sunrice | KHO |
Sushi rice 1 | Regular | Sunrice | SRS | |
Adulterated Rice 6 | Medium-grain | Organic | Macro | MOR |
Medium-grain 1 | Non-organic | Sunrice | MGB |
Algorithm | Stages | Samples (n) | Observations (Samples × Target) | R | Slope | Performance (MSE) |
---|---|---|---|---|---|---|
Model 1: Adulterated Rice 1 | ||||||
BR | Training | 230 | 230 | 0.97 | 0.95 | 0.46 × 102 |
Testing | 100 | 100 | 0.95 | 0.89 | 1.10 × 102 | |
Overall | 330 | 330 | 0.97 | 0.93 | - | |
Model 2: Adulterated Rice 2 | ||||||
BR | Training | 230 | 230 | 0.95 | 0.89 | 1.03 × 102 |
Testing | 100 | 100 | 0.90 | 0.87 | 1.71 × 102 | |
Overall | 330 | 330 | 0.94 | 0.88 | - | |
Model 3: Adulterated Rice 3 | ||||||
LM | Training | 230 | 230 | 0.96 | 0.90 | 0.84 × 102 |
Validation | 50 | 50 | 0.95 | 0.90 | 1.03 × 102 | |
Testing | 50 | 50 | 0.93 | 0.86 | 1.09 × 102 | |
Overall | 330 | 330 | 0.95 | 0.90 | - | |
Model 4: Adulterated Rice 4 | ||||||
BR | Training | 230 | 230 | 0.97 | 0.95 | 0.51 × 102 |
Testing | 100 | 100 | 0.95 | 0.90 | 0.96 × 102 | |
Overall | 330 | 330 | 0.97 | 0.93 | - | |
Model 5: Adulterated Rice 5 | ||||||
BR | Training | 230 | 230 | 0.99 | 0.99 | 0.11 × 102 |
Testing | 100 | 100 | 0.96 | 0.91 | 0.69 × 102 | |
Overall | 330 | 330 | 0.98 | 0.97 | - | |
Model 6: Adulterated Rice 6 | ||||||
BR | Training | 230 | 230 | 0.96 | 0.92 | 0.64 × 102 |
Testing | 100 | 100 | 0.90 | 0.84 | 2.10 × 102 | |
Overall | 330 | 330 | 0.94 | 0.89 | - |
Algorithm | Stages | Samples (n) | Observations (Samples × Targets) | R | Slope | Performance (MSE) |
---|---|---|---|---|---|---|
Model 7: Adulterated Rice 1 | ||||||
LM | Training | 230 | 230 | 0.98 | 0.93 | 0.43 × 102 |
Validation | 50 | 50 | 0.93 | 0.84 | 1.47 × 102 | |
Testing | 50 | 50 | 0.93 | 0.91 | 1.53 × 102 | |
Overall | 330 | 330 | 0.96 | 0.92 | - | |
Model 8: Adulterated Rice 2 | ||||||
LM | Training | 230 | 230 | 0.98 | 0.96 | 0.44 × 102 |
Validation | 50 | 50 | 0.97 | 0.94 | 0.48 × 102 | |
Testing | 50 | 50 | 0.97 | 0.96 | 0.48 × 102 | |
Overall | 330 | 330 | 0.98 | 0.95 | - | |
Model 9: Adulterated Rice 3 | ||||||
LM | Training | 230 | 230 | 0.98 | 0.95 | 0.42 × 102 |
Validation | 50 | 50 | 0.95 | 0.87 | 0.96 × 102 | |
Testing | 50 | 50 | 0.94 | 0.87 | 1.07 × 102 | |
Overall | 330 | 330 | 0.97 | 0.93 | - | |
Model 10: Adulterated Rice 4 | ||||||
BR | Training | 230 | 230 | 0.97 | 0.92 | 0.53 × 102 |
Testing | 100 | 100 | 0.88 | 0.91 | 2.36 × 102 | |
Overall | 330 | 330 | 0.95 | 0.92 | - | |
Model 11: Adulterated Rice 5 | ||||||
LM | Training | 230 | 230 | 0.99 | 0.98 | 0.24 × 102 |
Validation | 50 | 50 | 0.93 | 0.97 | 0.90 × 102 | |
Testing | 50 | 50 | 0.95 | 0.97 | 1.09 × 102 | |
Overall | 330 | 330 | 0.98 | 0.97 | - | |
Model 12: Adulterated Rice 6 | ||||||
BR | Training | 230 | 230 | 0.98 | 0.96 | 0.28 × 102 |
Testing | 100 | 100 | 0.91 | 0.87 | 1.88 × 102 | |
Overall | 330 | 330 | 0.96 | 0.93 | - |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Aznan, A.; Gonzalez Viejo, C.; Pang, A.; Fuentes, S. Rapid Detection of Fraudulent Rice Using Low-Cost Digital Sensing Devices and Machine Learning. Sensors 2022, 22, 8655. https://doi.org/10.3390/s22228655
Aznan A, Gonzalez Viejo C, Pang A, Fuentes S. Rapid Detection of Fraudulent Rice Using Low-Cost Digital Sensing Devices and Machine Learning. Sensors. 2022; 22(22):8655. https://doi.org/10.3390/s22228655
Chicago/Turabian StyleAznan, Aimi, Claudia Gonzalez Viejo, Alexis Pang, and Sigfredo Fuentes. 2022. "Rapid Detection of Fraudulent Rice Using Low-Cost Digital Sensing Devices and Machine Learning" Sensors 22, no. 22: 8655. https://doi.org/10.3390/s22228655