Pineapple Sweetness Classification using Deep Learning
Article Sidebar
Main Article Content
Abstract
Pineapple is an important economic crop in Thailand whose price depends on its sweetness. Determination of a fruit’s sweetness can be done using an optical refractometer or another tool that requires expert judgment. Furthermore, measuring the sweetness of each fruit consumes manpower and time. This study employs the AlexNet deep learning model to classify sweetness levels of pineapple based on physical characteristics demonstrated through figures. The dataset is classified into 4 classes, i.e., M1 to M4, and sorted according to the level of sweetness in ascending order. Training accounts for 80% of the dataset, whereas testing accounts for 20%. The experiments of this study were conducted five times, each with a different epoch and working with prepared data. The experiment indicates the AlexNet model generates the best results when trained at 10 epochs with balance data and contains 120 figures per class. The accuracy of the model and F1 score is 91.78% and 92.31%, respectively.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
The content and information in the articles published in the Journal of Science and Technology, Sisaket Rajabhat University reflect the opinions and responsibilities of the respective authors. The editorial board of the journal does not necessarily agree with, nor share responsibility for, these views.
Articles, information, content, images, etc., published in the Journal of Science and Technology, Sisaket Rajabhat University are copyrighted by the Faculty of Science and Technology, Sisaket Rajabhat University. If any individual or organization wishes to republish all or part of the content, or use it for any other purpose, they must obtain written permission from the Journal of Science and Technology, Sisaket Rajabhat University beforehand.
References
สำนักงานเศรษฐกิจการเกษตร. (2564). สำนักงานเศรษฐกิจการเกษตร. สืบค้น 14 มิถุนายน 2565, จาก http://mis-app.oae.go.th/product/สับปะรด
Baruwa, OI. (2013). Profitability and constraints of pineapple production in Osun State, Nigeria. Journal of Horticultural research, 21(2).
Hossain, MF., Akhtar, S. and Anwar, M. (2015). Nutritional value and medicinal benefits of pineapple. International Journal of Nutrition and Food Sciences, 4(1), 84-88.
Behera, SK., Rath, AK., and Sethy, PK. (2021). Maturity status classification of papaya fruits based on machine learning and transfer learning approach. Information Processing in Agriculture, 8(2), 244-250.
Lee, CH. & Jhou, JC. (2021). A Non-Invasive Method to Classify the Sweetness Levels of Apples. In 5th International Conference on Artificial Intelligence and Virtual Reality (AIVR): 128–134.
Chawgien, K. & Kiattisin, S. (2021). Machine learning techniques for classifying the sweetness of watermelon using acoustic signal and image processing. Computers and Electronics in Agriculture, 181, 105938.
Sangsongfa, A., Am-Dee, N. and Meesad, P. (2020). Prediction of Pineapple Sweetness from Images Using Convolutional Neural Network. EAI Endorsed Transactions on Context-aware Systems and Applications, 7(21).
Nazulan, WNSW., Asnawi, AL., Ramli, HAM., Jusoh, AZ., Ibrahim, SN. and Azmin, NFM. (2020). Detection of Sweetness Level for Fruits (Watermelon) With Machine Learning. In 2020 IEEE Conference on Big Data and Analytics (ICBDA) (pp. 79-83). IEEE.
Mejia, NL., Lobaton, HF. and Morales-Posada, B. (2019). Pineapple classification images and measured properties. mendeley data.
Krizhevsky, A., Sutskever, I. and Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25.
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... and Fei-Fei, L. (2015). Imagenet large scale visual recognition challenge. International journal of computer vision, 115(3), 211-252.
