Ecology: artificial intelligence for environmental care, a prototype for classifying solid waste at the point of origin
Copyright (c) 2021 Investigación e Innovación en Ingenierías
This work is licensed under a Creative Commons Attribution 4.0 International License.
- Articles
- Submited: August 5, 2021
-
Published: December 13, 2021
Abstract
Objective: To build the first prototype of a smart ecological point that assists the user in the correct classification of solid waste at the point of origin using Deep Learning, providing new technologies focused on mitigating climate impact caused by poor solid waste management. Methodology: to conduct the research, the Toyota LEAN methodology and the Solid Works tool were implemented to design a prototype according to the needs of an ecological point, including a structural analysis and weight tests in order to measure its resistance capacity. The agile methodology applied for the development of the artificial intelligence and the conformation of the set of images was extreme programming. Results and conclusions: a dataset of three classes was built according to resolution 2184 of 2019 of Colombia, containing a total of 400 samples taken from the prototype. The sorting model using a low computational cost architecture - MobileNet - obtained an accuracy of 97.91% in the validation and a kappa coefficient of 0.95. The trained model runs on a Raspberry Pi in order to minimize production costs. The research presents a test of acceptance and usability of the prototype.
References
- S. Kaza, L. Yao, P. Bhada-Tata y F. Van Woerden, “What a waste 2.0, a global snapshot of solid waste management to 2050,” World Bank Group, Washington, DC, 2018.
- ABRELPE, “Panorama dos resíduos sólidos no Brasil 2015,” São Paulo, 2015.
- SEMARNAT, “Informe de la situación del medio ambiente en México,” Semarnat, México, 2016.
- Superservicios, “Informe de disposición final de residuos sólidos; informe nacional - 2018,” Bogotá, 2019.
- H. N. Guo, S. B. Wu, Y. J. Tian, J. Zhang y H. T. Liu, “Application of machine learning methods for the prediction of organic solid waste treatment and recycling processes: A review,” Bioresource Technology, vol. 319, 2020.
- S. Sudha, M. Vidhyalakshmi, K. Pavithra, K. Sangeetha y V. Swaathi, “An automatic classification method for environment: Friendly waste segregation using deep learning,” IEEE TIAR, pp. 65 - 70, 2016.
- A. H. Vo, L. H. Son, M. T. Vo y T. A. Le, “A novel framework for trash classification using deep transfer learning,” IEEE Access, Volume 7, pp. 178631 - 178639, 2019.
- M. Toğaçar, B. Ergen y Z. Cömert, “Waste classification using autoencoder network with integrated feature selection method in convolutional neural network models,” Measurement, 2019.
- Z. Song, Y. Chen, Z. Yang y H. Gong, “Computer vision based two-stage waste recogniton-retrieval algorithm for waste classification,” Resources, Conservaton & Recycling, vol. 169, nº 105543, 2021.
- O. I. Funch, R. Marhaug, S. Kohtala y M. Steinert, “Detecting glass and metal in consumer trash bags during waste collection using convolutional neural networks,” Waste management, vol. 119, pp. 30 - 38, 2021.
- M. Yang y G. Thung, “Classification of trash for recyclability status,” 2016.
- P. Davis, F. Aziz, M. T. Newaz, W. Sher y L. Simon, “The classification of construction waste material using a deep convolutional neural network,” Automation in construction, vol. 122, nº 103481, 2021.
- S. H. Sunny, D. R. Dipta, S. Hossain, H. M. Faruque y E. Hossain, “Design of a convolutional neural network based smart waste disposal system,” IEEE - ICASERT, 2019.
- SolidWorks, “Comprobación del factor de seguridad,” 2020. [En línea]. Available: http://help.solidworks.com/2020/spanish/solidworks/cworks/c_factor_of_safety_check.htm.
- V. Pinto-Rodríguez, M. Pardo-Burbano y J. Muñoz-Ordóñez, EcologIA Net, Zenodo, 2020.
- CJSCANECAS, “CJSCANECAS,” [En línea]. Available: https://www.catorce6.com/actualidad-ambiental/legales/19004-el-1-de-enero-entra-en-vigencia-el-nuevo-codigo-de-colores-para-separacion-de-residuos-en-colombia. [Último acceso: 01 Junio 2021].
