Separating household waste into categories such as organic and recyclable is a critical part of waste management systems to make sure that valuable materials are recycled and utilised. This is beneficial to human health and the environment because less risky treatments are used at landfill and/or incineration, ultimately leading to improved circular economy. Conventional waste separation relies heavily on manual separation of objects by humans, which is inefficient, expensive, time consuming, and prone to subjective errors caused by limited knowledge of waste classification. However, advances in artificial intelligence (AI) research have led to automatic identification of objects from images (i.e., photos).
Project aim and objectives:
This project aims to utilise AI techniques to automate waste separation task based on images. Experimental data was collected from Mendeley Data repository (Nnamoko et al., 2022a). The data contains a collection of 24,705 images of solid household waste, categorised into two classes namely: organic (13,880) and recyclable (10,825). The author also published a preliminary research conducted with this data to evaluate the accuracy of a simple AI model in correctly categorising the images within the collection (Nnamoko et al., 2022b). Funding through the RIMES scheme was used to extend the research by applying a Transfer Learning approach to the image classification.
This research was delivered as part of the RIMES project which gives students an opportunity to engage with a range of research environments. All projects were linked to the UN’s sustainable development goals, which provide a blueprint to achieve a better and more sustainable future for all. SustainNET supported the project from inception to completion.
Nnamoko, N., Barrowclough, J., & Procter, J. (2022a). Waste Classification Dataset. Mendeley Data. https://doi.org/10.17632/n3gtgm9jxj.2
Nnamoko, N., Barrowclough, J., & Procter, J. (2022b). Solid Waste Image Classification Using Deep Convolutional Neural Network. Infrastructures, 7(4), 47. https://doi.org/10.3390/infrastructures7040047
Student Intern: Lahiru Rajamanthri
Mentors: Dr Nonso Nnamoko and Prof. Yannis Korkontzelos