CLASSIFICATION OF DRIED MORINGA LEAF QUALITY USING THE NAIVE BAYES METHOD

Gede Pratama; Putu Sugiartawan; Kompiang Martina Dinata Putri

Authors

Gede Pratama INSTIKI
Putu Sugiartawan Institut Bisnis dan Teknologi Indonesia (INSTIKI)
Kompiang Martina Dinata Putri

Keywords:

Moringa leaves, Dried Moringa, Quality classification, Machine learning, Image classification

Abstract

This study aims to classify the quality of dried Moringa leaves (Moringa oleifera) using the Naive Bayes classification method. Moringa leaves are known for their nutritional and medicinal benefits, and their quality significantly affects their value. The classification process focuses on categorizing dried Moringa leaves into different quality grades based on attributes such as color, texture, and overall appearance. Data were collected from samples of dried Moringa leaves, and feature extraction was performed to quantify these attributes. The Naive Bayes classifier, a probabilistic model based on Bayes' Theorem, was used to classify the quality of the samples into predefined categories. The performance of the classifier was evaluated using standard metrics, including accuracy, precision, recall, and F1-score. Results indicated that the Naive Bayes method is effective in classifying the quality of dried Moringa leaves, achieving high accuracy and reliability. This research demonstrates the potential of machine learning techniques, particularly Naive Bayes, for automating quality assessment in the agricultural and herbal product industries, which can improve efficiency and standardization in product grading.

References

Bishop, C. M. (2006). Pattern Recognition and Machine Learning, Springer, [online], (https://link.springer.com/book/9780387310732, accsed November 20, 2024).

Kumar, A., Singh, M., Gupta, M., & Tiwari, A. (2019). Feature extraction and classification of images using local binary pattern and histogram of oriented gradients. Journal of Image Processing, 12(4), 23-30, [online]. (https://journals.sagepub.com/doi/full/10.1177/1010732318817660, accessed November 20, 2024).

Mitchell, T. M. (1997). Machine learning. McGraw Hill. Machine Learning, Amazon [online],(https://www.amazon.com/Machine-Learning-Tom Mitchell/dp/0070428077, accessed November 18, 2024).

Powers, D. M. W. (2011). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies, 2(1), 37-63. [online]

(https://www.researchgate.net/publication/228899057_DETECTION_AND_CLASSIFICATION_OF_PLANT_SPECIES_THROUGH_SPECTIR_AIRBORNE_HYPERSPECTRAL_IMAGERY_IN_CLARK_COUNTY_NEVADA , accessed November 17,2024).

Rahman, A., & Setiawan, M. I. (2021). Image feature extraction techniques for classification purposes. Procedia Computer Science, 188, 1015-1021. [online],(https://www.sciencedirect.com/science/article/pii/S1877050921001253, accessed November 15,2024).

Tanaka, H., & Yamada, T. (2020). Quality assessment of agricultural products using machine learning. Agricultural Science and Technology Journal, 10(2), 55-61, [online],

(https://www.sciencedirect.com/science/article/abs/pii/S0167947307004118, accessed November 21, 2024).

Zhang, H., & Ling, C. (2018). A tutorial on Naive Bayes classification. Computational Statistics & Data Analysis, 52(5), 414-426, [online], (https://www.sciencedirect.com/science/article/pii/S0167947317304548, accessed November 20,2024).

Liu, W., & Li, S. (2013). Feature selection and classifier development in machine learning: Applications in classification of agricultural products. International Journal of Agricultural Informatics, 4(2), 32-41, [online],(https://scholar.google.com/scholar/FeatureSelectionandClassifierDevelopmentinMachineLearningforAgriculturalProducts, accessed June 11,2024).

Zhang, H. (2004). The optimality of naive Bayes, FLAIRS 2004, [online], (https://aaai.org/papers/flairs-2004-097/, accessed November 20,2024).

Mitchell, T. M. (1997). Machine learning. McGraw Hill, Amazon, [online], ( https://www.amazon.com/Machine-Learning-Tom-Mitchell/dp/007042808X, accessed June 11,2024).

Powers, D. M. W. (2011). Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation. Journal of Machine Learning Technologies, 2(1), 37-63, [online], (https://www.researchgate.net/publication/

ElearningUseintheTertiaryEducationnCyprus, accessed June 11,2024).

Zhang, H., & Ling, C. (2018). A tutorial on Naive Bayes classification. Computational Statistics & Data Analysis, 52(5), 414-426, Science Direct,[online],(https://www.sciencedirect.com/science/article/abs/pii/S0167947

, accessed June 11, 2024).

Fuglie, L. J. (2001). The Miracle Tree: The Multiple Attributes of Moringa, Scientific Research, [online], (https://www.scirp.org/reference/referencespapers?referen

ceid=2855695, accessed June 11, 2024).