A machine learning approach for cost analysis in plastic recycling classification

Nowadays, plastic usage and production is increasing leading to an augmentation in waste generation as well as to raw materials consumption. Consequently, plastic waste management is becoming one of the main concerns of society, as it has a direct impact on environment and sustainability. Recycling plastics can reduce waste generation and also improve plastic waste management, but both cost reduction and increase of incomes are needed in the recycling industry to be economically viable. Recently, recycling plastic classification techniques with Artificial Intelligence have gained popularity as they can avoid manual sorting, which is time-consuming and economically less profitable than automatic processing. This paper probes that FTIR and NIR spectroscopies combined with machine learning algorithms are suitable for plastic classification as four datasets and seven algorithms have been tested to classify Polyethylene (PE), Polypropylene (PP), Polyethylene terephthalate (PET), polystyrene (PS), and Polyvinyl chloride (PVC). Also, a method for selecting the algorithm presenting the maximum economic benefits according to every polymer’s class revenue is presentedObjectius de Desenvolupament Sostenible::12 - Producció i Consum Responsable