We propose the implementation of Machine Learning techniques for the classification of fruits and their ripening days using photographs of them. As a supervised learning method, a multilayer perceptron neural network was used. The results obtained from the neural network were compared with the K-nearest neighbors method through a Bayesian t-test, finding that the neural network is a better classifier of the type of fruit. Finally, Hierarchical Clustering was used to determine the ripening days of the fruits. The results obtained show that it is possible to generalize the neural network to improve its precision by increasing the variety of fruits and the size of the database.
neural network, ripening stages, prediction
1. Molina-Besch K., Wikström F., Williams H. The environmental impact of packaging in food supply chains-does life cycle assessment of food provide the full picture? The International Journal of Life Cycle Assessment, 2019, vol. 24 (1), pp. 37-50. DOI:https://doi.org/10.1007/s11367-018-1500-6.
2. Soares P., Almendra-Pegueros R., Benítez-Brito N., Fernández-Villa T., Lozano-Lorca M., Valera-Gran D., Navarrete-Muñoz E.M. Sistemas alimentarios sostenibles para una alimentación saludable. Revista Española de Nutrición Humana y Dietética, 2020.
3. Halonen N.J., Palvölgyi P.S., Bassani A., Fiorentini C., Nair R., Spigno G., Kordas K. Bio-based smart materials for food packaging and sensors-a review. Frontiers in Materials, 2020, vol. 7, p. 82. DOI:https://doi.org/10.3389/fmats.2020.00082.
4. Bouzembrak Y., Klüche M., Gavai A., Marvin H.J.Internet of Things in food safety: Literature review and a bibliometric analysis. Trends in Food Science & Technology, 2019, vol. 94, pp. 54-64. DOI:https://doi.org/10.1016/j.tifs.2019.11.002.
5. Camaréna S. Artificial Intelligence in the design of transition to Sustainable Food Systems. Journal of Cleaner Production, 2020, p. 122574. DOI:https://doi.org/10.1016/j.jclepro.2020.122574.
6. Smola A., Vishwanathan S.V.N.Introduction to machine learning. Cambridge University, UK, 2008, vol. 32 (34).
7. Müller A.C., Guido S.Introduction to machine learning with Python: a guide for data scientists. O'Reilly Media, Inc., 2016.
8. Berzal F. Redes neuronales & deep learning: vol. 2. Independently published, 2019.
9. Iandola F.N., Han S., Moskewicz M.W., Ashraf K., Dally W.J., Keutzer K. SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. 2016. arXiv preprint arXiv:1602.07360.
10. Godec P., Pančur M., Ilenič N., Čopar A., Stražar M., Erjavec A., Žagar L. Democratized image analytics by visual programming through integration of deep models and small-scale machine learning. Nature communications, 2019, vol. 10 (1), pp. 1-7. DOI:https://doi.org/10.1038/s41467-019-12397-x.
11. Tan C., Sun F., Kong T., Zhang W., Yang C., Liu C. A survey on deep transfer learning. In International conference on artificial neural networks. Springer, Cham., 2018, pp. 270-279.
12. Jolliffe I.T., Cadima J. Principal component analysis: a review and recent developments. Philosophical Transactions of the Royal Society A. Mathematical, Physical and Engineering Sciences, 2016, vol. 374 (2065), p. 20150202. DOI:https://doi.org/10.1098/rsta.2015.0202.
13. Corani G., Benavoli A. A Bayesian approach for comparing cross-validated algorithms on multiple data sets. Machine Learning, 2015, vol. 100 (2-3), pp. 285-304.
14. Demsar J., Curk T., Erjavec A., Gorup C., Hocevar T., Milutinovic M., Mozina M., Polajnar M., Toplak M., Staric A., Stajdohar M., Umek L., Zagar L., Zbontar J., Zitnik M., Zupan B. Orange: Data Mining Toolbox in Python. Journal of Machine Learning Research, 2013, pp. 2349-2353. DOI: 10.5555/ 2567709.2567736
15. Murtagh F., Contreras P. Methods of hierarchical clustering. 2011. arXiv preprint arXiv:1105.0121.
