Improved Classification of Intact Ripe Mango Sweetness using Fusion Deep Learning and Enhanced Near-Infrared Spectroscopy
|© 2022 by IJETT Journal|
|Year of Publication : 2022|
|Authors : Sumitra Nuanmeesri, Lap Poomhiran
|DOI : 10.14445/22315381/IJETT-V70I7P207|
How to Cite?
Sumitra Nuanmeesri, Lap Poomhiran, "Improved Classification of Intact Ripe Mango Sweetness using Fusion Deep Learning and Enhanced Near-Infrared Spectroscopy" International Journal of Engineering Trends and Technology, vol. 70, no. 7, pp. 60-67, 2022. Crossref, https://doi.org/10.14445/22315381/IJETT-V70I7P207
This research aims to develop models for classifying the sweetness of intact ripe mangoes using image-based deep learning fused with near-infrared spectral data. Each mango was measured for near-infrared spectral data at all 12 locations distributed across the fruit. These spectral data were enhanced by Baseline Linear Correction, Multiplicative Scatter Correction, Standard Normal Variate, and mixed methods. Next, the mango images are processed using the GrabCut method to eliminate background information and then adjusted with the Adaptive Mean-C Thresholding method. Finally, the mango fruit image was processed, and the enhanced spectral data were taken through feature extraction using a Convolutional Neural Network-based early fusion technique. The results showed that the model using the enhanced spectral data that applied the Multiplicative Scatter Correction combined with the Standard Normal Variate method provided the highest model efficiency. The training accuracy was 99.66%, and this model's validation accuracy was 94.20%. Therefore, enhanced nearinfrared spectroscopy, combined with image processing and model development deep learning-based, can improve the classification of the sweetness of ripe mangoes.
Classification, Deep Learning, Mango Sweetness, Near-Infrared, Neural Network.
 P. Pinsirodom, R. Taprap, and T. Parinyapatthanaboot, “Antioxidant Activity and Phenolic Acid Composition in Different Parts of Selected Cultivars of Mangoes in Thailand,” International Food Research Journal, vol. 25, no. 4, pp. 1435-1443, 2018.
 Kusumiyat, A.A. Munawar, and D. Suhandy, “Fast and Contactless Assessment of Intact Mango Fruit Quality Attributes Using Near Infrared Spectroscopy (NIRS),” IOP Conference Series: Earth and Environmental Science, Banda Aceh, Indonesia: IOPScience, vol. 644, pp. 012028, 2021.
 Y. Papanikolaou and V.L. Fulgoni III, “Mango Consumption is Associated with Improved Nutrient Intakes, Diet Quality, and WeightRelated Health Outcomes, Nutrients,” vol. 14, no. 1, pp. 59, 2022.
 Md.K. Islam, M.Z.H. Khan, M.A.R. Sarkar, N. Absar, and S.K. Sarkar, “Changes in Acidity, TSS, and Sugar Content at Different Storage Periods of the Postharvest Mango (Mangifera Indica L.) Influenced by Bavistin DF,” International Journal of Food Science, vol. 2013, pp. 939385, 2013.
 A.A. Munawar, Kusumiyati, and D. Wahyuni, “Near Infrared Spectroscopic Data for Rapid and Simultaneous Prediction of Quality Attributes in Intact Mango Fruits,” Data in Brief, vol. 27, pp. 104789, 2019.
 A. Raghavendra, D.S. Guru, and M.K. Rao, “Mango Internal Defect Detection Based on Optimal Wavelength Selection Method Using NIR Spectroscopy,” Artificial Intelligence in Agriculture, vol. 5, pp. 43-51, 2021.
 A.A. Munawar, D.v. Hörsten, D. Mörlein, E. Pawelzik, and J.K. Wegener, “Rapid and Non-Destructive Prediction of Mango Sweetness and Acidity Using Near Infrared Spectroscopy,” in Proc. Mass Data Management in the Agricultural and Food Industry - Collection - Processing - Use, pp. 219-222, 2013.
 M.S. Amirul, R. Endut, C.B.M. Rashidi, S.A. Aljunid, N. Ali, M.H. Laili, A.R. Laili, and M.N.M. Ismail, “Estimation of Harumanis (Mangifera indica L.) sweetness using Near-Infrared (NIR) Spectroscopy,” IOP Conference Series: Materials Science and Engineering, vol. 767, no. 1, pp. 012070, 2020.
 C.-N. Nguyen, Q.-T. Phan, N.-T. Tran, M. Fukuzawa, P.-L. Nguyen, and C.N. Nguyen, “Precise Sweetness Grading of Mangoes (Mangifera Indica L.) Based on Random Forest Technique with Low-Cost Multispectral Sensors,” IEEE Access, vol. 8, pp. 212371- 212382, 2020.
 Y.T. Chang, M.C. Hsueh, S.P. Hung, J.M. Lu, J.H. Peng, and S.F. Chen, “Prediction of Specialty Coffee Flavors Based on NearInfrared Spectra Using Machine and Deep-Learning Methods,” Journal of the Science of Food and Agriculture, vol. 101, pp. 4705- 4714, 2021.
 D. Rong, H. Wang, Y. Ying, Z. Zhang, and Y. Zhang, “Peach Variety Detection Using VIS-NIR Spectroscopy and Deep Learning,” Computers and Electronics in Agriculture, vol. 175, pp. 105553, 2020.
 S.K. Bejo and S. Kamaruddin, “Determination of Chokanan Mango Sweetness (Mangifera Indica) Using Non-Destructive Image Processing Technique,” Australian Journal of Crop Science, vol. 8, no. 4, pp. 457-480, 2014.
 M.F. Mavi, Z. Husin, B.A., Y.M. Yacob, R.S.M. Farook, W.K. Tan, Mango ripeness classification system using hybrid technique, Indonesian Journal of Electrical Engineering and Computer Science. 14(2) (2019) 859-868.
 K. Ratprakhon, W.C. Neubauer, K. Riehn, J. Fritsche, and S. Rohn, Developing an Automatic Color Determination Procedure for the Quality Assessment of Mangos (Mangifera Indica) Using a CCD Camera and Color Standards,” Foods, vol. 9, 2020.
 K. Simonyan and A. Zisserman, “Very Deep Convolutional Networks for Large-Scale Image Recongnition,” arXiv preprint, arXiv:1409.1556, 2015.
 G. Rother, V. Kolmogorov, and A. Blake, “GrabCut: Interactive Foreground Extraction Using Iterated Graph Cuts,” in Proc. ACM Transactions on Graphics, vol. 23, no. 3, pp. 309-314, 2004.
 R. Hayati, A.A. Munawar, and F. Fachruddin, “Enhanced Near Infrared Spectral Data to Improve Prediction Accuracy in Determining Quality Parameters of Intact Mango,” Data in Brief, vol. 30, pp. 105571, 2020.
 F. Zhang, X. Tang, A. Tong, B. Wang, and J. Wang, “An Automatic Baseline Correction Method Based on the Penalized Least Squares Method,” Sensors, vol. 20, pp.2015, 2020.
 A.A. Munawar, Y. Yunus, Devianti, and P. Satriyo, “Calibration Models Database of Near Infrared Spectroscopy to Predict Agricultural Soil Fertility Properties,” Data in Brief, vol. 30, pp. 105469, 2020.
 G. Ren, Y. Sun, M. Li, J. Ning, and Z. Zhang, “Cognitive Spectroscopy for Evaluating Chinese Black Tea Grades (Camellia Sinensis): Near-Infrared Spectroscopy and Evolutionary Algorithms,” Journal of the Science of Food and Agriculture, vol. 100, pp. 3950-3959, 2020.
 H.U. Rehman et al., “Preclassification of broadband and sparse infrared data by multiplicative signal correction approach, Molecules,” vol. 27, pp. 2298, 2022.
 P. Mishra and S. Lohumi, “Improved Prediction of Protein Content in Wheat Kernels with a Fusion of Scatter Correction Methods in NIR Data Modelling, Biosystems Engineering,” vol. 203, pp. 93-97, 2021.
 H. Jonsson and J. Gabrielsson, “Comprehensive Chemometrics: 2.11 - Evaluation of Preprocessing Methods,” S.D. Brown, R. Tauler, and B. Walczak, Eds.Elsevier, pp. 199-206, 2009.
 S. Nuanmeesri, “Mobile Application for the Purpose of Marketing, Product Distribution and Location-Based Logistics for Elderly Farmers,”Applied Computing and Informatics, 2020.
 S. Nuanmeesri, L. Poomhiran, and K. Ploydanai, “Improving the Prediction of Rotten Fruit Using Convolutional Neural Network,” International Journal of Engineering Trends and Technology, vol. 69, no. 7, pp. 51-55, 2021.
 S. Nuanmeesri, S. Chopvitayakun, P. Kadmateekarun, and L. Poomhiran, “Marigold Flower Disease Prediction Through Deep Neural Network with Multimodal Image,” International Journal of Engineering Trends and Technology, vol. 69, no. 7, pp. 174-180, 2021.