This work presents an approach for recognition of plastics using a low-cost spectroscopy sensor module together with a set of machine learning methods. The sensor is a multi-spectral module capable of measuring 18 wavelength from the visible to near-infrared spectra. Data processing and analysis are performed using a set of ten machine learning (Random Forest, Support Vector Machines, Multi-Layer Perceptron, Convolutional Neural Networks, Decision Trees, Logistic Regression, Naive Bayes, k-Nearest Neighbour, AdaBoost, Linear Discriminant Analysis). An experimental set up is designed for systematic data collection from six plastic types including PET, HDPE, PVC, LDPE, PP and PS household waste. The set of computational methods is implemented in a generalised pipeline for validation of the proposed approach for recognition of plastics. The results show that Convolutional Neural Networks and Multi-Layer Perceptron can recognise plastics with mean accuracy of 72.50% and 70.25%, respectively, with the largest accuracy of 83.5% for PS plastic and smallest accuracy of 66% for PET plastic. The results demonstrate that the low-cost near-infrared sensor with machine learning methods can recognise plastics effectively, making it an affordable and portable approach that contributes to the development of sustainable systems and with potential for applications in other fields such as agriculture, e-waste recycling, healthcare and manufacturing.
Original languageEnglish
Article number2821
Issue number9
Early online date28 Apr 2024
Publication statusPublished - 1 May 2024

Data Availability Statement

Data are contained within the article.


Dive into the research topics of 'Low-cost recognition of plastic waste using deep learning and multi-spectral near-infrared sensor'. Together they form a unique fingerprint.

Cite this