Improving Smart Waste Collection Using AutoML

• Type: Article in International Conference Proceedings Book
• Date: 2021

Authors

Teixeira, Sónia (Author) FEP; Londres, G (Author) Other; Veloso, B (Author) FEP; Rita Ribeiro (Author) FCUP; João Gama (Author) FEP

Conference proceedings International

Title: MACHINE LEARNING AND PRINCIPLES AND PRACTICE OF KNOWLEDGE DISCOVERY IN DATABASES, PT II

Pages: 283-298

21st Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

ELECTR NETWORK, SEP 13-17, 2021

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 0 Citations

Other information

Authenticus ID: P-00W-ANY

DOI: 10.1007/978-3-030-93733-1_20

Abstract (EN): The production and management of urban waste is a growing challenge and a consequence of our day-to-day resources and activities. According to the Portuguese Environment Agency, in 2019, Portugal produced 1% more tons compared to 2018. The proper management of this waste can be co-substantiated by existing policies, namely, national legislation and the Strategic Plan for Urban Waste. Those policies assess and support the amount of waste processed, allowing the recovery of materials. Among the solutions for waste management is the selective collection of waste. We improve the possibility of manage the smart waste collection of Paper, Plastic, and Glass packaging from corporate customers who joined a recycling program. We have data collected since 2017 until 2020. The main objective of this work is to increase the system's predictive performance, without any loss for citizens, but with improvement in the collection management. We analyze two types of problems: (i) the presence or absence of containers; and (ii) the prediction of the number of containers by type of waste. To carry out the analysis, we applied three machine learning algorithms: XGBoost, Random Forest, and Rpart. Additionally, we also use AutoML for XGBoost and Random Forest algorithms. The results show that with AutoML, generally, it is possible to obtain better results for classifying the presence or absence of containers by type of waste and predict the number of containers.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 16