Getting smarter with waste bin management
University of South Australia (UniSA) researchers are using artificial intelligence (AI) to work out how best to manage waste collections from public rubbish bins — predicting which locations accumulate the most rubbish and where resources should be allocated.
Using algorithms to analyse data from smart bin sensors, UniSA PhD student Sabbir Ahmed is designing a deep learning model to predict where waste is accumulating in cities and how often public bins should be cleared.
Ahmed said sensors in public smart bins can give a lot of information regarding how busy locations are, what type of rubbish is being disposed of and how much methane gas is being produced from food waste in bins. This data can be fed into a neural network model to predict where bins are likely to fill up quickly and which are rarely visited.
This can help councils optimise waste management services, schedule bin clearances and relocate rarely used bins to where they are needed.
A pilot project is now being developed in collaboration with Wyndham Council in Victoria, using its smart bin data to develop an AI model which could be deployed by councils across the country.
The research is published in the International Journal of Environmental Research and Public Health.
Sameera Mubarak, co-author of the paper, said waste management is a growing concern around the world as many urban areas struggle to cope with an increase in garbage due to rapid population growth.
In developing an AI model, the researchers have analysed sensor data from public bin sites, routing paths and pick-up locations. The sensors capture different types of waste: solid, organic, industry or chemical waste, medical waste and recycling waste.
According to Mubarak, the use of AI can predict patterns of waste generation in public sites and forecast which days would be busier in certain locations by flagging upcoming events that will result in a spike in garbage and scheduling waste collection around these predictions.
Improper waste collection can cause health and environmental hazards for cities, something that this research looks to address.
The researchers plan to investigate the impact of socioeconomic factors and public utility investment on waste generation in future work.
Phone: 1300 301 703
The pco.pixelfly 1.3 SWIR is a machine vision camera with an InGaAs image sensor that is...
The V12so Odour Control Cannon combines four different functions in one machine — eliminate...
The Series PMI Particulate Matter Transmitter is designed to measure indoor air quality by...