PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY

 

e-ISSN 2231-8526
ISSN 0128-7680

Home / Regular Issue / JST Vol. 33 (1) Jan. 2025 / JST-5259-2024

 

Machine Learning Precision for Mangosteen Maturity: A Comparative Analysis of Conventional Classifiers

Ram Kumar Thirumugam, Yasmin Mohd Yacob, Wan Mahfuzah Wan Ibrahim, Salina Mohd Asi and Suhizaz Sudin

Pertanika Journal of Science & Technology, Volume 33, Issue 1, January 2025

DOI: https://doi.org/10.47836/pjst.33.1.13

Keywords: Conventional machine learners, decision tree, fruit maturity, K-Nearest Neighbour, random forest, support vector machine

Published on: 23 January 2025

Identifying mangosteen maturity stages pre-harvest is crucial for postharvest quality, as fruit disease and pest infestation often occur at specific stages. Deep learning, while popular for classification, struggles with false negatives. Conversely, conventional machine learning methods now effectively handle false negative issues. The main goal of this research is to determine the significant comparison between different conventional classifiers, namely Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM) and K-Nearest Neighbour (K-NN), in terms of their accuracy, validity, and False Negative Rate (FNR) in predicting six distinct classes. Image samples of 253 mangosteens across six maturity stages were used, with 20 regions of interest (ROIs) each. 112 Gray-level Co-Occurrence Matrix (GLCM) and colour features were extracted to train models using texture, colour, and combined features. The evaluation metrics used for assessing the validity of predictions included precision, recall, F1-score, accuracy, and Cohen’s Kappa. The RF classifier achieved high validation scores, with an accuracy of 0.76 and Cohen’s Kappa of 0.70 for combined features, 0.75 and 0.69 for coloured features, and 0.46 and 0.33 for texture features. The Friedman test on false positive rates (FNR) across the four models shows significant differences (p < 0.05) for colour, texture, and their combination, with p-values of 0.00134, 0.00572, and 0.00071, respectively. RF is the best method, with the lowest mean FNR scores: 1.16 for texture, 1.16 for colour, and 1.00 for combined features. In conclusion, the RF classifier outperforms other classifiers in accuracy, validity, and mean FNR across six classes with three category features, achieving statistical significance in the Friedman Test.

  • Afandi, M. I., Kurniawan, E., & Wijaya, S. K. (2021). Rapid grading of mangosteen peel defect using Extreme Learning Machine. In Proceedings of the 2021 International Conference on Computer, Control, Informatics and Its Applications (pp. 60-65). ACM Publishing. https://doi.org/10.1145/3489088.3489110

    Al-Mashhadani, Z., & Chandrasekaran, B. (2021). Ros-based robotic system for tomato disease and ripeness classification using convolutional neural networks. In 2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) (pp. 0420-0427). IEEE Publishing. https://doi.org/10.1109/iemcon53756.2021.9623183

    Ashtiani, S. M., Javanmardi, S., Jahanbanifard, M., Martynenko, A. I., & Verbeek, F. (2021). Detection of mulberry ripeness stages using deep learning models. IEEE Access, 9, 100380-100394. https://doi.org/10.1109/access.2021.3096550

    Azizah, L. M. R., Umayah, S. F., Riyadi, S., Damarjati, C., & Utama, N. A. (2017). Deep learning implementation using convolutional neural network in mangosteen surface defect detection. In 2017 7th IEEE international conference on control system, computing and engineering (ICCSCE) (pp. 242-246). IEEE Publishing. https://doi.org/10.1109/iccsce41414.2017

    Bashir, R. N., Khan, F. A., Khan, A. A., Tausif, M., Abbas, M. Z., Shahid, M. M. A. & Khan N. (2023). Intelligent optimization of Reference Evapotranspiration (ETo) for precision irrigation. Journal of Computational Science, 69, Article 102025. https://doi.org/10.1016/j.jocs.2023.102025.

    Benmouna, B., García-Mateos, G., Sabzi, S., Fernández-Beltran, R., Parras-Burgos, D., & Molina-Martínez, J. M. (2022). Convolutional neural networks for estimating the ripening state of Fuji Apples using visible and near-infrared spectroscopy. Food and Bioprocess Technology, 15, 2226-2236.

    Boateng, E. Y., Otoo, J., & Abaye, D. (2020). Basic tenets of classification Algorithms K-Nearest-Neighbor, support vector machine, random forest and neural network: A review. Journal of Data Analysis and Information Processing, 8, 341-357. https://doi.org/10.4236/jdaip.2020.84020

    Damarjati, C., Riyadi, S., Triyani, W. I., Azizah, L. M., & Hariadi, T. K. (2017). Statistical features extraction of discrete curvelet transform for surface quality evaluation of mangosteen. In 2017 7th IEEE International Conference on Control System, Computing and Engineering (ICCSCE) (pp. 236-241). IEEE Publishing. https://doi.org/10.1109/iccsce.2017.8284411

    Gao, Z., Shao, Y., Xuan, G., Wang, Y., Liu, Y., & Han, X. (2020). Real-time hyperspectral imaging for the in-field estimation of strawberry ripeness with deep learning, Artificial Intelligence in Agriculture, 4, 31-38. https://doi.org/10.1016/j.aiia.2020.04.003

    Giuntini, R., Holik, F. Park, D. K., Freytes, H., Blank, C., & Sergioli, G. (2023). Quantum-inspired algorithm for direct multiclass classification. Applied Soft Computing, 134, Article 109956. https://doi.org/10.1016/j.asoc.2022.109956.

    Goel, E., & Abhilasha, E. (2017). Random forest: A review. International Journal of Advanced Research in Random Forest, 7(1), 251–257. https://doi.org/10.23956/ijarcsse/v7I1/01113

    Haralick, R. M., Shanmugam, K., & Dinstein, I. (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, 3, 610–621.

    IndexBox. (2024). Malaysia: Mango and Mangosteen Market 2024. https://www.indexbox.io/store/malaysia-mangoes-mangosteens-and-guavas-market-report-analysis-and-forecast-to-2020/

    Joshua, S. V., Priyadharson, A. S. M., Kannadasan, R., Khan, A. A., Worawat, L., Khan, F. A., Rehman, A. U., & Ali, M. J. (2022). Crop yield prediction using machine learning approaches on a wide spectrum. Computers, Materials & Continua, 72(3), 5663-5679. https://doi.org/10.32604/cmc.2022.027178

    Khan A. A., Nauman, M. A., Bashir, R. N., Jahangir, R., Alroobaea, R., Binmahfoudh, A., Alsafyani, M., & Wechtaisong, C. (2022). Context aware evapotranspiration (ETs) for saline soils reclamation. IEEE Access, 10, 110050-110063. https://doi.org/10.1109/ACCESS.2022.3206009.

    Khan, A. A., Faheem, M., Bashir, R. N., Wechtaisong, C., & Abbas, M. Z. (2022). Internet of Things (IoT) assisted context aware fertilizer recommendation. IEEE Access, 10, 129505–129519. https://doi.org/10.1109/ACCESS.2022.3228160

    Khojastehnazhand, M., Mahmoud, O., & Tabatabaeefar, A. (2010). Development of a lemon sorting system based on colour and size. African Journal of Plant Science, 4, 122-127.

    Kim, T., Lee, D. H., Kim, K. C., Choi, T., & Yu, J. M. (2023). Tomato maturity estimation using deep neural network. Applied Sciences, 13(1), Article 412. https://doi.org/10.3390/app13010412

    Leemans, V., Destain, M., & Magein, H. (2002). On-line fruit grading according to their external quality using machine vision. Biosystems Engineering, 88(4), 397-404.

    Liakos, K. G., Busato, P., Moshou, D., Pearson, S., & Bochtis, D. (2018). Machine learning in agriculture: A review. Sensors, 18(8), Article 2674. https://doi.org/10.3390/s18082674

    Liming, X., & Yanchao, Z. (2010). Automated strawberry grading system based on image processing. Computers and Electronics in Agriculture, 71(1), 32–39. https://doi.org/10.1016/j.compag.2009.09.013

    Mohtar, I. A., Ramli, N. S. S., & Ahmad, Z. (2019). Automatic classification of mangosteen ripening stages using deep learning. In 2019 1st International Conference on Artificial Intelligence and Data Sciences (AiDAS) (pp. 44-47). IEEE Publishing. https://doi.org/10.1109/aidas47888.2019.8970933

    Muñoz, P. B. C., Sorogastua, E. M. F., & Gardini, S. R. P. (2022). Detection and classification of ventura-blueberries in five levels of ripeness from images taken during pre-harvest stage using deep learning techniques. In 2022 IEEE ANDESCON (pp. 1-6). IEEE Publishing. https://doi.org/10.1109/andescon56260.2022.9989578

    Orchi, H., Sadik, M., Khaldoun, M., & Sabir, E. (2023). Automation of crop disease detection through conventional machine learning and deep transfer learning approaches. Agriculture, 13, Article 352. https://doi.org/10.3390/agriculture13020352

    Pandey, R., Naik, S., & Marfatia, R. (2013). Image processing and machine learning for automated fruit grading system: A technical review. International Journal of Computer Applications, 81(16), 29-39. https://doi.org/10.5120/14209-2455

    Parashar, N., & Johri, P. (2024). Enhancing apple leaf disease detection: A CNN-based model integrated with image segmentation techniques for precision agriculture. International Journal of Mathematical, Engineering and Management Sciences, 9(4), 943-964. https://doi.org/10.33889/IJMEMS.2024.9.4.050

    Phothisonothai, M., & Tantisatirapong, S. (2019). Fractal dimension based color texture analysis for mangosteen ripeness grading. In 2019 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS) (pp. 1-2). IEEE Publishing. https://doi.org/10.1109/ispacs48206.2019.8986398

    Powers, D. M. W. (2020). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness & correlation. Journal of Machine Learning Technologies, 2(1), 37–63. https://doi.org/10.48550/arXiv.2010.16061

    Rainio, O., Teuho, J., & Klén, R. (2024). Evaluation metrics and statistical tests for machine learning. Scientific Reports, 14, Article 6086. https://doi.org/10.1038/s41598-024-56706-x

    Riyadi, S., Azizah, L. M. R., Damarjati, C., & Hariadi, T. K. (2018). Evaluation of mangosteen surface quality using discrete curvelet transform. In 2018 International Conference on Information and Communication Technology Convergence (ICTC) (pp. 475-479). IEEE Publishing. https:// 10.1109/ictc.2018.8539577

    Riyadi, S., Ratiwi, A. M. A., Damarjati, C., Hariadi, T. K., Prabasari, I., & Utama, N. A. (2020). Classification of mangosteen surface quality using principal component analysis. Emerging Information Science and Technology, 1(1), 33-43. https://doi.org/10.18196/eist.115

    Rushing, B. (2022). No free theory choice from machine learning. Synthese, 200, Article 414. https://doi.org/10.1007/s11229-022-03901-w

    Sudana, O., Bayupati, I. P. A. & Yudiana, D. G. (2020). Classification of maturity level of the mangosteen using the convolutional neural network (CNN) method. International Journal of Advanced Science and Technology (IJAST), 135(2020), 37-48. https://doi.org/10.33832/ijast.2020.135.04

    Tan, W. K., Husin, Z., & Ismail, M. A. H. (2020). Feasibility study of beef quality assessment using computer vision and Deep Neural Network (DNN) algorithm. In 2020 8th International Conference on Information Technology and Multimedia (ICIMU) (pp. 243-246). IEEE Publishing. https://doi.org/10.1109/icimu49871.2020

    Thammastitkul, A., & Klayjumlang, T. (2021). Mangosteen quality grading for export markets using digital image processing techniques. International Journal on Advanced Science Engineering Information Technology, 11(6), 2452–2458. https://doi.org/10.18517/ijaseit.11.6.14003

    Whidhiasih, R. N., Guritman, S., & Supriyo, P. T. (2012). Identification of mangosteen stage maturity on colour based using fuzzy neural network. Jurnal Teknologi Industri Pertanian, 22(2), 82-91.

ISSN 0128-7680

e-ISSN 2231-8526

Article ID

JST-5259-2024

Download Full Article PDF

Share this article

Related Articles