Browsing by Author "Sousa, Vitor"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Artificial neural network modelling of the amount of separately-collected household packaging wastePublication . Oliveira, Verónica; Sousa, Vitor; Ferreira, CéliaThis work develops an artificial neural network (ANN) model using genetic algorithms to estimate the annual amount (kg/inhabitant/year) of separately-collected household packaging waste. The ANN model comprises one input layer, one hidden layer with seven neurons and one output layer. Ten variables affecting the amount of separately-collected packaging waste were identified and used in the ANN model. These variables are related to the level of education of the population, the size and level of urbanisation of the municipality, social aspects related to poverty and economic power and factors intrinsic to the waste collection service. A comparison between ANN and regression models for the estimation of packaging waste is also carried out. The performance of the proposed ANN model for a data set of 42 municipalities located in the centre of Portugal, measured by the R2 , is 0.98. This value is 34% higher than the best regression model applied to the same data set (R2 ¼ 0.73), indicating that ANN has a significantly higher explanatory power than traditional regression techniques. Another advantage is that ANN is not as sensitive to outliers as regression. However, ANN is more complex, has a higher number of variables, and the model development and interpretation of the results are more difficult. Nevertheless, the higher performance of ANN makes it a valuable tool in the definition of strategies to increase recycling and achieve circular economy goals.
- Dataset of socio-economic and waste collection indicators for Portugal at municipal levelPublication . Oliveira, Verónica; Sousa, Vitor; Ferreira, CéliaThis data article presents demographic, socio-economic and wasterelated data at municipal level for Portugal. The dataset includes raw data collected from 4 main sources: (i) the annual reports of waste management companies; (ii) the database of the Portuguese water, sanitation and waste regulatory entity; (iii) the Portuguese Environmental Agency; and (iv) national statistical data. Relevant indicators for waste generation and for the separate collection of waste are proposed and calculated using the raw data. The dataset comprises municipalities with high, medium and low separate collection yields, providing socio-economic and waste infrastructures data that can be used for benchmarking. The dataset can also be used to define a baseline against which the progress of the collection of packaging waste can be assessed over time, or else serve as input to mathematical models predicting waste generation and collection. Moreover, data can serve as the base to calculate new waste-related indicators. In addition to being a valuable input to the waste topic, the dataset can also be used in a large range of other topics where demographic and socio-economic parameters are relevant. The data presented herein are associated with the research articles “Model for the separate collection of packaging waste in Portuguese low-performing recycling regions” [1] and “Artificial neural network modelling of the amount of separatelycollected household packaging waste” [2].
- Life-cycle cost as basis to optimize waste collection in space and time: a methodology for obtaining a detailed cost breakdown structurePublication . Sousa, Vitor; Ferreira, Célia; Vaz, João M.; Meireles, InêsExtensive research has been carried out on waste collection costs mainly to differentiate costs of distinct waste streams and spatial optimization of waste collection services (e.g. routes, number, and location of waste facilities). However, waste collection managers also face the challenge of optimizing assets in time, for instance deciding when to replace and how to maintain, or which technological solution to adopt. These issues require a more detailed knowledge about the waste collection services’ cost breakdown structure. The present research adjusts the methodology for buildings’ life-cycle cost (LCC) analysis, detailed in the ISO 15686-5:2008, to the waste collection assets. The proposed methodology is then applied to the waste collection assets owned and operated by a real municipality in Portugal (Cascais Ambiente – EMAC). The goal is to highlight the potential of the LCC tool in providing a baseline for time optimization of the waste collection service and assets, namely assisting on decisions regarding equipment operation and replacement.