 ARTIFICIAL INTELLIGENCE AND SENSOR TECHNOLOGY-DRIVEN AUTOMATED WASTE SORTING SYSTEMS USING REAL-TIME COMPUTER VISION AND IOT-BASED MONITORINGOybek Asrorov ()
Synoptic: International Journal of Multidisciplinary Research, vol. 1, issue 1, 1-9 Abstract: The amount of municipal solid waste just keeps growing fast, from about 2.01 billion tons back in 2016 to something like 3.40 billion tons projected by 2050. That really makes things tougher for handling waste in cities, with more environmental issues and operational headaches piling up. Manual sorting the way its usually done takes a lot of labor, and its full of mistakes too. Plus, it cant handle all the extra volume and the way waste is getting more complicated these days. So, this paper suggests a system that pulls together AI for computer vision to sort plastics, metals, and organics right away. It pairs that with smart bins using IoT to keep track of how full they are, their weight, and stuff like temperature or humidity around them. The deep learning part gets trained on a bigger version of that TrashNet dataset, and it runs on an edge device so it can spot waste types in real time without lagging. Then sensors, ultrasonic ones and load cells, measure the bin conditions nonstop and send data up to a cloud engine that optimizes everything. I think the experiments they ran, with 8,000 labeled images and some simulated collection trucks, turned out pretty good. The classification accuracy hit 95.8 percent overall. Compared to a basic rule-based setup, it cut down collection distances by 31.4 percent, fewer trips by 27.2 percent, and overflow problems dropped a lot, like 62.5 percent. That seems significant. Combining the AI vision with IoT sensing, it looks like it boosts how well waste gets separated and makes collection runs more efficient. Kind of a way forward for sustainable management thats data driven and can scale up, though this part gets a bit messy to explain fully. Keywords: waste sorting; computer vision; IoT; smart bins; municipal solid waste; deep learning; route optimization (search for similar items in EconPapers) Downloads: (external link) Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:snp:journl:art-1777067578539 Access Statistics for this article More articles in Synoptic: International Journal of Multidisciplinary Research from Synoptic Publisher |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.