2019
Ferrer, Javier; Alba, Enrique
BIN-CT: Urban waste collection based on predicting the container fill level. Journal Article
In: BioSystems, 186 , pp. 103962, 2019, ISSN: 1872-8324.
Abstract | Links | BibTeX | Tags: Forecasting, Machine learning, Recycling, Routes generation, Waste collection
@article{Ferrer2018Bio,
title = {BIN-CT: Urban waste collection based on predicting the container fill level.},
author = {Javier Ferrer and Enrique Alba},
url = {http://arxiv.org/abs/1807.01603 https://linkinghub.elsevier.com/retrieve/pii/S0303264718301333 http://dx.doi.org/10.1016/j.biosystems.2019.04.006 http://www.ncbi.nlm.nih.gov/pubmed/31004697},
doi = {10.1016/j.biosystems.2019.04.006},
issn = {1872-8324},
year = {2019},
date = {2019-12-01},
journal = {BioSystems},
volume = {186},
pages = {103962},
abstract = {The fast demographic growth, together with the population concentration in cities and the increasing amount of daily waste, are factors that are pushing to the limit the ability of waste assimilation by Nature. Therefore, we need technological means to optimally manage of the waste collection process, which represents 70% of the operational cost in waste treatment. In this article, we present a free intelligent software system called BIN-CT (BIN for the CiTy), based on computational learning algorithms, which plans the best routes for waste collection supported by past (historical) and future (predictions) data. The objective of the system is to reduction the cost of the waste collection service minimizing the distance traveled by a truck to collect the waste from a container, thereby reducing the fuel consumption. At the same time the quality of service for the citizen is increased, avoiding the annoying overflows of containers thanks to the accurate fill-level predictions given by BIN-CT. In this article we show the features of our software system, illustrating its operation with a real case study of a Spanish city. We conclude that the use of BIN-CT avoids unnecessary trips to containers, reduces the distance traveled to collect a container by 20%, and generates routes 33.2% shorter than the routes used by the company. Therefore it enables a considerable reduction of total costs and harmful emissions thrown up into the atmosphere.},
keywords = {Forecasting, Machine learning, Recycling, Routes generation, Waste collection},
pubstate = {published},
tppubtype = {article}
}
The fast demographic growth, together with the population concentration in cities and the increasing amount of daily waste, are factors that are pushing to the limit the ability of waste assimilation by Nature. Therefore, we need technological means to optimally manage of the waste collection process, which represents 70% of the operational cost in waste treatment. In this article, we present a free intelligent software system called BIN-CT (BIN for the CiTy), based on computational learning algorithms, which plans the best routes for waste collection supported by past (historical) and future (predictions) data. The objective of the system is to reduction the cost of the waste collection service minimizing the distance traveled by a truck to collect the waste from a container, thereby reducing the fuel consumption. At the same time the quality of service for the citizen is increased, avoiding the annoying overflows of containers thanks to the accurate fill-level predictions given by BIN-CT. In this article we show the features of our software system, illustrating its operation with a real case study of a Spanish city. We conclude that the use of BIN-CT avoids unnecessary trips to containers, reduces the distance traveled to collect a container by 20%, and generates routes 33.2% shorter than the routes used by the company. Therefore it enables a considerable reduction of total costs and harmful emissions thrown up into the atmosphere.