The compost is a biological process of degradation of organic matter that has different applications in agriculture and the remediation of soils. Use of the package for data mining Orange was possible the development of an artificial intelligence algorithm, which was carried out through the treatment of images and their classification in the middle of the methods Logistic Regression, Neural Network, Random Forest, Support Vector Machine (SVM) and k-Nearest-Neighbors. With the algorithm, the stage of the compost process is identified by comparing the images of compost under controlled conditions. It is possible to create a supervised learning algorithm to be able to predict the stages of the composting process using only photographic images of the compost. Because of this, the algorithm that best performs the classification is the multilayer perceptron neural network. This result will allow the development of a portable device that allows identifying the quality of the soil.
machine learning algorithms, composting
1. Oviedo-Ocaña E.R., Dominguez I., Komilis D., Sánchez, A. Co-composting of green waste mixed with unprocessed and processed food waste: influence on the composting process and product quality. Waste and Biomass Valorization, 219, vol. 10, no. 1, pp. 63-74.
2. Saviñon-Flores M.F. Diseño y construcción de un sistema de compostaje empleando las plataformas Arduino y Python (Tesis de pregrado). Benemérita Universidad Autónoma de Puebla, Puebla, México, 2019. [Saviñon-Flores M. F. Design and construction of a composting system using the Arduino and Python platforms. Undergraduate Thesis, Benemérita Autonomous University of Puebla, Puebla, Mexico, 2019. (In Span.)]
3. Al-Turjman, F. Artificial Intelligence in IoT. Springer, 2019.
4. Pejovic V., Majhen I., Janez M., Zupan B. RICERCANDO: Data Mining Toolkit for Mobile Broadband Measurements. 2019. arXiv preprint arXiv:1901.07287.
5. Jie M.A., Collins G.S., Steyerberg E.W., Verbakel J.Y., van Calster B. A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models. Journal of clinical epidemiology, 2019.
6. Heidari A.A., Faris H., Mirjalili S., Aljarah I., Mafarja M. Ant Lion Optimizer: Theory, Literature Review, and Application in Multi-layer Perceptron Neural Networks. In Nature-Inspired Optimizers. Springer, Cham., 2019, pp. 23-46
7. Tyralis H., Papacharalampous G., Langousis A. A brief review of random forests for water scientists and practitioners and their recent history in water resources. Water, 2019, vol. 11, no. 5, p. 910.
8. Guo H., Wang W. Granular support vector machine: a review. Artificial Intelligence Review, vol. 51, no. 1, pp. 19-32.
9. Paez A., López F., Ruiz M., Camacho M. Inducing non-orthogonal and non-linear decision boundaries in decision trees via interactive basis functions. Expert Systems with Applications, vol. 122, pp. 183-206.
10. Jiang J., Chen Y., Meng X., Wang L., Li K. A novel density peaks clustering algorithm based on k nearest neighbors for improving assignment process. Physica A: Statistical Mechanics and its Applications, vol. 523, pp. 702-713.
11. Rabinowicz A., Rosset S. Cross-Validation for Correlated Data. 2019. arXiv preprint arXiv:1904.02438.
