The Classification of Aflatoxin Contamination Level in Cocoa Beans using Fluorescence Imaging and Deep learning
Abstract
Aflatoxin contamination in cacao is a significant problem in terms of trade losses and health effects. This calls for the need for a non-invasive, precise, and effective detection strategy. This research contribution is to determine the best deep-learning model to classify the aflatoxin contamination level in cocoa beans based on fluorescence images and deep learning to improve performance in the classification. The process involved inoculating and incubating Aspergillus flavus (6mL/100g) to obtain aflatoxin-contaminated cocoa beans for 7 days during the incubation period. Liquid Mass Chromatography (LCMS) was used to quantify the aflatoxin in order to categorize the images into different levels including “free of aflatoxin”, “contaminated below the limit”, and “contaminated above the limit”. 300 images were acquired through a mini studio equipped with UV lamps. The aflatoxin level was classified using several pre-trained CNN approaches which has high accuracy such as GoogLeNet, SqueezeNet, AlexNet, and ResNet50. The sensitivity analysis showed that the highest classification accuracy was found in the GoogLeNet model with optimizer: Adam and learning rate: 0.0001 by 96.42%. The model was tested using a testing dataset and obtain accuracy of 96% based on the confusion matrix. The findings indicate that combining CNN with fluorescence images improved the ability to classify the amount of aflatoxin contamination in cacao beans. This method has the potential to be more accurate and economical than the current approach, which could be adapted to reduce aflatoxin's negative effects on food safety and cacao trade losses.
Keywords
Full Text:
PDFReferences
M. Eskola, G. Kos, C. T. Elliott, J. Hajšlová, S. Mayar, and R. Krska, “Worldwide contamination of food-crops with mycotoxins: Validity of the widely cited ‘FAO estimate’ of 25%,” Crit. Rev. Food Sci. Nutr., vol. 60, no. 16, pp. 2773–2789, 2020, doi: 10.1080/10408398.2019.1658570.
P. Kumar, D. K. Mahato, M. Kamle, T. K. Mohanta, and S. G. Kang, “Aflatoxins: A global concern for food safety, human health and their management,” Front. Microbiol., vol. 7, pp. 1–10, 2017, doi: 10.3389/fmicb.2016.02170.
J. Boonen, S. V Malysheva, L. Taevernier, J. D. D. Mavungu, S. De Saeger, and B. D. Spiegeleer, “Human skin penetration of selected model mycotoxins.,” Toxicology, vol. 301, no. 1–3, pp. 21–32, 2012, doi: 10.1016/j.tox.2012.06.012.
S. Mohamed, Y. Sadam, R. Malaka, S. Baco, and J. Mustabi, “Aflatoxin M1 in Milk : Occurrence and Its Risk Association : A Review,” Hasanuddin Journal of Animal Science (HAJAS), vol. 4, no. 2, pp. 68–81, 2022, doi: 10.20956/hajas.v4i2.22097.
S. Marchese, A. Polo, A. Ariano, S. Velotto, S. Costantini, and L. Severino, “Aflatoxin B1 and M1: Biological Properties and Their Involvement in Cancer Development.,” Toxins, vol. 10, no. 6, 2018, doi: 10.3390/toxins10060214.
D. Githang’a, O. Anzala, C. Mutegi, and A. Agweyu, “The effects of exposures to mycotoxins on immunity in children: A systematic review,” Curr. Probl. Pediatr. Adolesc. Health Care, vol. 49, no. 5, pp. 109–116, 2019, doi: 10.1016/j.cppeds.2019.04.004.
M. Mahfuz et al., “Chronic Aflatoxin Exposure and Cognitive and Language Development in Young Children of Bangladesh: A Longitudinal Study,” Toxins, vol. 14, no. 12, 2022, doi: 10.3390/toxins14120855.
R. Daou et al., “Aflatoxin B1 Occurrence in Children under the Age of Five’s Food Products and Aflatoxin M1 Exposure Assessment and Risk Characterization of Arab Infants through Consumption of Infant Powdered Formula: A Lebanese Experience,” Toxins, vol. 14, no. 5, pp. 1–13, 2022, doi: 10.3390/toxins14050290.
J. Yu, “Current Understanding on Aflatoxin Biosynthesis and Future Perspective in Reducing Aflatoxin Contamination,” Toxins, vol. 4, no. 11, pp. 1024–1057, 2012, doi: 10.3390/toxins4111024.
P. N. A. Adriansyah, W. P. Rahayu, H. D. Kusumaningrum, and O. Kawamura, “Aflatoxin M1 reduction by microorganisms isolated from kefir grains,” Int. Food Res. J., vol. 29, no. 1, pp. 78–85, 2022, doi: 10.47836/ifrj.29.1.09.
O. Ketney, “Food Safety Legislation Regarding Of Aflatoxins Contamination,” ACTA Univ. Cibiniensis, vol. 67, no. 1, pp. 149–154, 2015, doi: 10.1515/aucts-2015-0081.
European Commission, “COMMISSION IMPLEMENTING REGULATION (EU) No 884/2014 of 13 August 2014 imposing special conditions governing the import of certain feed and food from certain third countries due to contamination risk by aflatoxins and repealing Regulation (EC) No 1152/2009,” Off. J. Eur. Union, vol. 242, no. 14, pp. 4-19, 2014.
P. Mounjouenpou, D. Gueule, A. Fontana-Tachon, B. Guyot, P. R. Tondje, and J. P. Guiraud, “Filamentous fungi producing ochratoxin a during cocoa processing in Cameroon,” Int. J. Food Microbiol., vol. 121, no. 2, pp. 234–241, 2008, doi: 10.1016/j.ijfoodmicro.2007.11.017.
V. Vivek, S. Bermúdez, and C. Larrea, “Global Market Report: Cocoa,” Exch. Organ. Behav. Teach. J., pp. 1–12, 2019.
P. N. Pires et al., “Aflatoxins and ochratoxin A: occurrence and contamination levels in cocoa beans from Brazil,” Food Addit. Contam. - Part A Chem. Anal. Control. Expo. Risk Assess., vol. 36, no. 5, pp. 815–824, 2019, doi: 10.1080/19440049.2019.1600749.
A. Hassoun and R. Karoui, "Quality evaluation of fish and other seafood by traditional and nondestructive instrumental methods: Advantages and limitations," Critical Reviews in Food Science and Nutrition, vol. 57, no. 9, pp. 1976-1998, 2017.
C. S. Alvarez et al., “Aflatoxin B 1 exposure and liver cirrhosis in Guatemala: A case-control study,” BMJ Open Gastroenterol., vol. 7, no. 1, pp. 1–7, 2020, doi: 10.1136/bmjgast-2020-000380.
T. M. Osaili et al., “Occurrence of aflatoxins in nuts and peanut butter imported to UAE,” Heliyon, vol. 9, no. 3, p. e14530, 2023, doi: 10.1016/j.heliyon.2023.e14530.
L. Fang et al., “Occurrence and exposure assessment of aflatoxins in Zhejiang province, China,” Environ. Toxicol. Pharmacol., vol. 92, p. 103847, 2022, doi: 10.1016/j.etap.2022.103847.
I. Polisenska, “Identification of Fusarium damaged wheat kernels using image analysis,” vol. 59, no. 5, pp. 125-130, 2011, doi: 10.11118/actaun201159050125.
C. A. Mallmann, A. O. Mallmann, and D. Tyska, “Survey of Mycotoxin in Brazilian Corn by NIR Spectroscopy-Year 2019,” Glob. J. Nutri. Food Sci, vol. 3, pp. 1–7, 2020, doi: 10.33552/GJNFS.2020.03.000552.
X. Tian, C. Zhang, J. Li, S. Fan, Y. Yang, and W. Huang, “Detection of early decay on citrus using LW-NIR hyperspectral reflectance imaging coupled with two-band ratio and improved watershed segmentation algorithm.,” Food Chem., vol. 360, p. 130077, 2021, doi: 10.1016/j.foodchem.2021.130077.
H. Kaya-celiker, P. K. Mallikarjunan, and A. Kaaya, “Mid-infrared spectroscopy for discrimination and classi fi cation of Aspergillus spp . contamination in peanuts,” Food Control, vol. 52, pp. 103–111, 2015, doi: 10.1016/j.foodcont.2014.12.013.
M. Sieger, G. Kos, M. Sulyok, M. Godejohann, R. Krska, and B. Mizaikoff, “Portable infrared laser spectroscopy for on-site mycotoxin analysis,” Sci. Rep., vol. 7, 2017, doi: 10.1038/srep44028.
S. Thiruppathi, D. S. Jayas, N. D. G. White, P. G. Fields, and T. Gräfenhan, “Near-Infrared (NIR) hyperspectral imaging : theory and applications to detect fungal infection and mycotoxin contamination in food products” Indian Journal of Entomology, vol. 78, pp. 91-99, 2016, doi: 10.5958/0974-8172.2016.00029.8.
J. Roberts, A. Power, J. Chapman, S. Chandra, and D. Cozzolino, “A short update on the advantages, applications and limitations of hyperspectral and chemical imaging in food authentication,” Appl. Sci., vol. 8, no. 4, 2018, doi: 10.3390/app8040505.
Z. Du, N. Ali, and B. Ashraf, “X ‐ ray computed tomography for quality inspection of agricultural products : A review,” Food science & nutrition, vol. 7, no. 10, pp. 3146–3160, 2019, doi: 10.1002/fsn3.1179.
J. G. Tallada, D. T. Wicklow, T. C. Pearson, and P. R. Armstrong, “Detection of Fungus-Infected Corn Kernels using Near-Infrared Reflectance Spectroscopy and Color Imaging,” Trans. ASABE, vol. 54, pp. 1151–1158, 2011.
X. Qi, J. Jiang, X. Cui, and D. Yuan, “Identification of fungi-contaminated peanuts using hyperspectral imaging technology and joint sparse representation model,” J. Food Sci. Technol., vol. 56, no. 7, pp. 3195–3204, 2019, doi: 10.1007/s13197-019-03745-2.
T. Manojlović, T. Tomanič, I. Štajduhar, and M. Milanič, “Rapid extraction of skin physiological parameters from hyperspectral images using machine learning,” Appl. Intell., vol. 53, no. 13, pp. 16519–16539, 2023, doi: 10.1007/s10489-022-04327-0.
P. Cozzini, G. Ingletto, R. Singh, and C. Dall’Asta, “Mycotoxin detection plays ‘cops and robbers’: Cyclodextrin chemosensors as specialized police?,” Int. J. Mol. Sci., vol. 9, no. 12, pp. 2474–2494, 2008, doi: 10.3390/ijms9122474.
A. Kamilaris and F. X. Prenafeta-Boldú, “A review of the use of convolutional neural networks in agriculture,” J. Agric. Sci., vol. 156, no. 3, pp. 312–322, 2018, doi: 10.1017/S0021859618000436.
Z. Hruska, H. Yao, R. Kincaid, R. L. Brown, D. Bhatnagar, and T. E. Cleveland, “Temporal effects on internal fluorescence emissions associated with aflatoxin contamination from corn kernel cross-sections inoculated with toxigenic and atoxigenic Aspergillus flavus,” Front. Microbiol., vol. 8, pp. 1–10, 2017, doi: 10.3389/fmicb.2017.01718.
V. Rotich, D. F. Al Riza, F. Giametta, T. Suzuki, Y. Ogawa, and N. Kondo, “Thermal oxidation assessment of Italian extra virgin olive oil using an UltraViolet (UV) induced fluorescence imaging system,” Spectrochim. Acta - Part A Mol. Biomol. Spectrosc., vol. 237, p. 118373, 2020, doi: 10.1016/j.saa.2020.118373.
A. Singla, L. Yuan, and T. Ebrahimi, “Food/non-food image classification and food categorization using pre-trained GoogLeNet model,” in Proceedings of the 2nd International Workshop on Multimedia Assisted Dietary Management, pp. 3–11, 2016, doi: 10.1145/2986035.2986039.
W. Rahman, M. G. G. Faruque, K. Roksana, A. H. M. S. Sadi, M. M. Rahman, and M. M. Azad, “Multiclass blood cancer classification using deep CNN with optimized features,” Array, vol. 18, p. 100292, 2023, doi: 10.1016/j.array.2023.100292.
T. Nishi, S. Kurogi, and K. Matsuo, “Grading fruits and vegetables using RGB-D images and convolutional neural network,” 2017 IEEE Symp. Ser. Comput. Intell. SSCI 2017 - Proc., vol. 2018 pp. 1–6, 2018, doi: 10.1109/SSCI.2017.8285278.
A. Sedik, A. Abohany, K. Sallam, K. Munasinghe, and T. Medhat, “Deep fake news detection system based on concatenated and recurrent modalities,” Expert Syst. Appl., vol. 208, p. 117953, 2022, doi: 10.1016/j.eswa.2022.117953.
Y. Hendrawan et al., “AlexNet convolutional neural network to classify the types of Indonesian coffee beans,” IOP Conf. Ser. Earth Environ. Sci., vol. 905, no. 1, 2021, doi: 10.1088/1755-1315/905/1/012059.
M. Momeny, A. A. Neshat, A. Jahanbakhshi, M. Mahmoudi, Y. Ampatzidis, and P. Radeva, “Grading and fraud detection of saffron via learning-to-augment incorporated Inception-v4 CNN,” Food Control, vol. 147, p. 109554, 2023, doi: 10.1016/j.foodcont.2022.109554.
K. Wei et al., “Classification of Tea Leaves Based on Fluorescence Imaging and Convolutional Neural Networks,” Sensors (Basel)., vol. 22, no. 20, 2022, doi: 10.3390/s22207764.
T. Tanaka et al., “An application of liquid chromatography and mass spectrometry for determination of aflatoxins,” Mycotoxins, vol. 52, no. 2, pp. 107–113, 2002, doi: 10.2520/myco.52.107.
J. Xie, N. He, L. Fang, and A. Plaza, “Scale-free convolutional neural network for remote sensing scene classification,” IEEE Trans. Geosci. Remote Sens., vol. 57, no. 9, pp. 6916–6928, 2019, doi: 10.1109/TGRS.2019.2909695.
V. Bhole and A. Kumar, “Analysis of Convolutional Neural Network Using Pre-Trained Squeezenet Model for Classification of Thermal Fruit Images,” ICT Compet. Strateg., pp. 759–768, 2020, doi: 10.1201/9781003052098-80.
N. Jamil, S. R. Roslan, R. Hamzah, and I. Ramli, “Food recognition of Malaysian meals for the management of Calorie intake,” Int. J. Adv. Trends Comput. Sci. Eng., vol. 8, pp. 355–360, 2019, doi: 10.30534/ijatcse/2019/5281.62019.
S. E. Abdallah, W. M. Elmessery, M. Y. Shams, N. S. A. Al-Sattary, A. A. Abohany, and M. Thabet, “Deep Learning Model Based on ResNet-50 for Beef Quality Classification,” Inf. Sci. Lett., vol. 12, no. 1, pp. 289–297, 2023, doi: 10.18576/isl/120124.
P. Rybacki, J. Niemann, K. Bahcevandziev, and K. Durczak, “Convolutional Neural Network Model for Variety Classification and Seed Quality Assessment of Winter Rapeseed,” Sensors, vol. 23, no. 5, 2023, doi: 10.3390/s23052486.
S. Jiang, K. Guo, J. Liao, and G. Zheng, “Solving Fourier ptychographic imaging problems via neural network modeling and TensorFlow,” Biomed. Opt. Express, vol. 9, no. 7, p. 3306, 2018, doi: 10.1364/boe.9.003306.
J. Jepkoech, D. M. Mugo, B. K. Kenduiywo, and E. C. Too, “The Effect of Adaptive Learning Rate on the Accuracy of Neural Networks,” Int. J. Adv. Comput. Sci. Appl., vol. 12, no. 8, pp. 736–751, 2021, doi: 10.14569/IJACSA.2021.0120885.
I. Kandel and M. Castelli, “The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset,” ICT Express, vol. 6, no. 4, pp. 312–315, 2020, doi: 10.1016/j.icte.2020.04.010.
S. Mezzah and A. Tari, “Practical hyperparameters tuning of convolutional neural networks for EEG emotional features classification,” Intell. Syst. with Appl., vol. 18, p. 200212, 2023, doi: 10.1016/j.iswa.2023.200212.
G. Habib and S. Qureshi, “Optimization and acceleration of convolutional neural networks: A survey,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 7, pp. 4244–4268, 2022, doi: 10.1016/j.jksuci.2020.10.004.
S. Sarraf and G. Tofighi, “Classification of Alzheimer’s Disease Structural MRI Data by Deep Learning Convolutional Neural Networks,” arXiv preprint arXiv:1607.06583, 2016.
X. Tang, H. Zhang, N. Zhang, H. Yan, F. Tang, and W. Zhang, “Dropout Rate Prediction of Massive Open Online Courses Based on Convolutional Neural Networks and Long Short-Term Memory Network,” Mob. Inf. Syst., vol. 2022, p. 8255965, 2022, doi: 10.1155/2022/8255965.
A. Lopez-del Rio, M. Martin, A. Perera-Lluna, and R. Saidi, “Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction,” Sci. Rep., vol. 10, no. 1, pp. 1–14, 2020, doi: 10.1038/s41598-020-71450-8.
Y. Q. Yang, P. S. Wang, and Y. Liu, “Interpolation-Aware Padding for 3D Sparse Convolutional Neural Networks,” Proc. IEEE Int. Conf. Comput. Vis., pp. 7447–7455, 2021, doi: 10.1109/ICCV48922.2021.00737.
K. Shaheed et al., “DS-CNN: A pre-trained Xception model based on depth-wise separable convolutional neural network for finger vein recognition,” Expert Syst. Appl., vol. 191, p. 116288, 2022, doi: https://doi.org/10.1016/j.eswa.2021.116288.
Q. Li, L. Li, W. Wang, Q. Li, and J. Zhong, “A comprehensive exploration of semantic relation extraction via pre-trained CNNs,” Knowledge-Based Syst., vol. 194, p. 105488, 2020, doi: https://doi.org/10.1016/j.knosys.2020.105488.
E. Priesterjahn, R. Geisen, and M. Schmidt-heydt, “Influence of Light and Water Activity on Growth and Mycotoxin Formation of Selected Isolates of Aspergillus flavus and Aspergillus parasiticus,” Microorganisms, vol. 8, no. 12, pp. 1–15, 2020.
R. Casquete, M. J. Benito, M. D. G. Córdoba, and S. Ruiz-moyano, “The growth and aflatoxin production of Aspergillus flavus strains on a cheese model system are influenced by physicochemical factors,” J. Dairy Sci., vol. 100, no. 9, pp. 6987–6996, 2017, doi: 10.3168/jds.2017-12865.
T. Furukawa and S. Sakuda, "Inhibition of aflatoxin production by paraquat and external superoxide dismutase in Aspergillus flavus," Toxins, vol. 11, no. 2, p. 107, doi: 10.3390/toxins11020107.
J. Liu et al., “Effects of Nutrients in Substrates of Different Grains on Aflatoxin B 1 Production by Aspergillus flavus,” BioMed Research International, vol. 2016, 2016.
P. Chang, S. S. T. Hua, S. B. L. Sarreal, and R. W. Li, “Suppression of Aflatoxin Biosynthesis in Aspergillus flavus by 2-Phenylethanol Is Associated with Stimulated Growth and Decreased Degradation of Branched-Chain Amino Acids,” Toxins, vol. 7, no. 10, pp. 3887–3902, 2015, doi: 10.3390/toxins7103887.
E. Tumukunde et al., “Osmotic-Adaptation Response of sakA/hogA Gene to Aflatoxin Biosynthesis, Morphology Development and Pathogenicity in Aspergillus flavus,” Toxins, vol. 11, no. 1, pp. 1–20, 2019, doi: 10.3390/toxins11010041.
Y. Wang, Y. Zhou, Y. Qin, and L. Wang, “Effect of environmental factors on the aflatoxin production by Aspergillus flavus during storage in upland rice seed using response surface methodology,” LWT, vol. 169, p. 113977, 2022, doi: 10.1016/j.lwt.2022.113977.
S. Biotrop, “The effect of temperature and relative humidity for Aspergillus flavus BIO 2237 growth and aflatoxin production on soybeans,” International Food Research Journal, vol. 22, no. 1, pp. 82–87, 2015.
A. Kumar, H. Pathak, and S. Bhadauria, “Aflatoxin contamination in food crops : causes, detection, and management : a review,” Food Production, Processing and Nutrition, vol. 3, pp. 1-9, 2021.
G. Winter, C. D. Todd, M. Trovato, G. Forlani, and D. Funck, "Physiological implications of arginine metabolism in plants," Frontiers in plant science, vol. 6, p. 534, 2015, doi: 10.3389/fpls.2015.00534.
B. Wang et al., “Effects of nitrogen metabolism on growth and aflatoxin biosynthesis in Aspergillus flavus,” J. Hazard. Mater., vol. 324, pp. 691–700, 2017, doi: 10.1016/j.jhazmat.2016.11.043.
M. Scarpari et al., “Lipids in Aspergillus flavus -maize interaction,” Frontiers in Microbiology, vol. 5, pp. 1–9, 2014, doi: 10.3389/fmicb.2014.00074.
I. K. Cigić and H. Prosen, “An overview of conventional and emerging analytical methods for the determination of mycotoxins,” Int. J. Mol. Sci., vol. 10, no. 1, pp. 62–115, 2009, doi: 10.3390/ijms10010062.
J. Pawliszyn. Comprehensive sampling and sample preparation: analytical techniques for scientists. Academic Press, 2012.
J. Gao, L. Zhao, J. Li, L. Deng, J. Ni, and Z. Han, “Aflatoxin rapid detection based on hyperspectral with 1D-convolution neural network in the pixel level,” Food Chem., vol. 360, p. 129968, 2021, doi: 10.1016/j.foodchem.2021.129968.
K. Liu, “Comparison of different Convolutional Neural Network models on Fruit 360 Dataset,” Highlights in Science, Engineering and Technology, vol. 34, pp. 85–94, 2023.
L. Migus, J. Salomon, and P. Gallinari, “Stability of implicit neural networks for long-term forecasting in dynamical systems,” arXiv preprint arXiv:2305.17155, 2023,
M. Reyad, A. M. Sarhan, and M. Arafa, "A modified Adam algorithm for deep neural network optimization," Neural Computing and Applications, pp. 1-18, 2023.
Y. Hendrawan et al., “Classification of soybean tempe quality using deep learning,” IOP Conf. Ser. Earth Environ. Sci., vol. 924, no. 1, 2021, doi: 10.1088/1755-1315/924/1/012022.
R. Abdulkadirov, P. Lyakhov, and N. Nagornov, “Survey of Optimization Algorithms in Modern Neural Networks,” Mathematics, vol. 11, no. 11, pp. 1–37, 2023, doi: 10.3390/math11112466.
D. Valero-Carreras, J. Alcaraz, and M. Landete, “Comparing two SVM models through different metrics based on the confusion matrix,” Comput. Oper. Res., vol. 152, p. 106131, 2023, doi: 10.1016/j.cor.2022.106131.
K. Albarrak, Y. Gulzar, Y. Hamid, A. Mehmood, and A. B. Soomro, “A Deep Learning-Based Model for Date Fruit Classification,” Sustain., vol. 14, no. 10, 2022, doi: 10.3390/su14106339.
DOI: https://doi.org/10.18196/jrc.v5i1.19081
Refbacks
- There are currently no refbacks.
Copyright (c) 2024 Muhammad Syukri Sadimantara, Bambang Dwi Argo, Sucipto Sucipto, Dimas Firmanda Al Riza, Yusuf Hendrawan
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Journal of Robotics and Control (JRC)
P-ISSN: 2715-5056 || E-ISSN: 2715-5072
Organized by Peneliti Teknologi Teknik Indonesia
Published by Universitas Muhammadiyah Yogyakarta in collaboration with Peneliti Teknologi Teknik Indonesia, Indonesia and the Department of Electrical Engineering
Website: http://journal.umy.ac.id/index.php/jrc
Email: jrcofumy@gmail.com