Resumen

CERNA-CUEVA, Alberto Franco; ROSAS-ECHEVARRIA, Cesar; PERALES-FLORES, Roberto  y  ATAUCUSI-FLORES, Pierina Lisbeth. Prediction of solid household waste generation with machine learning in a rural area of Puno. Tecnia [online]. 2022, vol.32, n.1, pp.44-52.  Epub 30-Jun-2022. ISSN 0375-7765.  http://dx.doi.org/10.21754/tecnia.v32i1.1378.

Solid waste management is one of the main environmental challenges in all cities of the world due to factors such as population growth and consumption habits. One of the main tools for the design of waste management projects is the estimation of per capita generation, however, the traditional method to obtain this information demands a lot of effort and time, so this research proposes an alternative approach to estimate per capita generation based on socioeconomic factors. For this purpose, socioeconomic demographic information and information on the per capita generation of solid waste was collected from 50 families in the "El Juncal" population center, department of Puno, then the variables that have significant influence were determined from the Spearman's ρ correlation coefficient for numerical variables and an ANOVA for categorical variables with an acceptance threshold of 0.4 and 0.05 respectively. The selected variables were used to train neural network models, multiple linear regression, Support Vector Machine, Gaussian processes and Random Forest, whose performances were R2 = 0.986, 0.982, 0.959, 0.942, 0.832; respectively. Cross validation and data partitioning were used for validation. The results indicate that the influential variables are per capita income, expenditure on inputs and outputs, family size and household services. It is concluded that the predictions of the models are reliable with root mean square error (RMSE) values of 8 to 27 g.

Palabras clave : Waste; social factor; machine learning algorithms; management; suburbs; domicile.

        · resumen en Español     · texto en Español     · Español ( pdf )