Browsing by Author "Meireles, I."
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- Benchmarking operational efficiency in waste collection: discussion of current approaches and possible alternativesPublication . Sousa, Vítor; Ferreira, Célia; Fernández Braña, Álvaro; Meireles, I.Efficiency assessment and benchmarking are crucial for managing any organization. However, especially from a regulatory perspective, such efficiency assessment and benchmarking must be unbiased from context-specific issues and should provide an absolute rating, rather than a relative one. The current work reviews the approaches used for performance assessment and benchmarking waste collection services, revealing that the majority are biased and are not absolute, and proposes two alternative context-unbiased and absolute performance indicators, the collection capacity use (CCU) and the segregated waste collection efficiency (SWE). The proposed indicators were calculated for 246 utilities operating in Portugal. The utilities were then ranked accordingly, and their position was compared with the position attained using the equivalent performance indicators in the system currently in use by the Portuguese service regulator. The results reveal ranking differences of over 50 positions and illustrate how misleading the results from context-biased and relative metrics can be.
- Prediction performance of separate collection of packaging waste yields using support vector machinesPublication . Sousa, Vítor; Meireles, I.; Oliveira, Verónica; Ferreira, CéliaUnderstanding the drivers underlying waste production in general, and source-segregated waste in particular, is of utmost importance for waste managers. This work aims at evaluating the performance of support vector machines (SVM) models in the prediction of separate collection yields for packaging waste at municipal level. Two SVM models were developed for a case study of 42 municipalities simultaneously serviced by separate collection of packaging waste and by unsorted waste collection. The “SVM-fxed” model used a fxed set of 5 variables to predict collection yields, whereas the “SVM-optimal” model chose from a pool of 14 variables those that optimized performance, using a genetic algorithm. These SVM models were compared with 3 traditional regression models: the ordinary least square linear (OLS-L), the ordinary least square non-linear (OLS-NL) and robust regression. The robust regression model was further compared against the other regression models in order to assess the infuence of the dataset outliers on the model performance. The coefcient of determination, R2 , was used to evaluate the performance of these models. The highest performance was attained by the SVM-optimal model (R2=0.918), compared to the SVM-fxed model (R2=0.670). The performance of the SVM-optimal model was 42% higher than the best performing regression model, the OLS-NL model (R2=0.646). The diferences in performance among the 3 regression models are small (circa 3%), whereas the exclusion of outliers improved their performance by 13%, indicating that outliers impacted more on performance than the type of traditional regression technique used. The results demonstrate that SVM model can be a viable alternative for prediction of separate collection of packaging waste yields and that there are nine important drivers that all together explain roughly 92% (R2=0.918) of the variability in the separate collection yields data.
- Preliminary evaluation of the potential performance of a future PAYT system in PortugalPublication . Sousa, V.; Dinis, J.; Drumond, A.; Bonnet, M. J.; Leal, P.; Meireles, I.; Ferreira, CéliaThe use of Pay-As-You-Throw systems is a reality in several cities throughout the globe, in some cases for several year by now. In Portugal, as well as many other countries around the Mediterranean, there have been only a few experiences and limited information exists regarding their performance. In this contribution, the results of a first stage towards an experimental PAYT system recently implemented in the municipality of Cascais are detailed. The strategy involved the increase of collection points for packaging waste and the use of gamification as positive incentive. Following the infrastructure improvements, the segregated waste collection doubled from 10% to 20–21%. With the gamification, the proportion of waste segregation increased to nearly 30%.