A Comparative Study of Azure Custom Vision Versus Google Vision API Integrated into AI Custom Models Using Object Classification for Residential Waste DOI Creative Commons
Cosmina-Mihaela Roșca, Adrian Stancu,

M. Tanase

et al.

Applied Sciences, Journal Year: 2025, Volume and Issue: 15(7), P. 3869 - 3869

Published: April 1, 2025

The residential separate collection of waste is the first stage in recyclability for sustainable development. paper focuses on designing and implementing a low-cost automatic sorting bin (RBin) recycling, alleviating user’s classification burden. Next, an analysis two object identification models was conducted to sort materials into categories cardboard, glass, plastic, metal. A major challenge distinguishing between glass plastic due their similar visual characteristics. research assesses performance Azure Custom Vision Service (ACVS) model, which achieves high accuracy training data but underperforms real-time applications, with 95.13%. In contrast, second Waste Sorting Model (CWSM), demonstrates (96.25%) during proves be effective applications. CWSM uses two-tier approach, identifying descriptively using Google API (GVAS) followed by through CWSM, predicate-based custom model. employs LbfgsMaximumEntropyMulti algorithm dataset 1000 records training, divided equally across categories. This study proposes innovative evaluation metric, Weighted Classification Confidence Score (WCCS). results show that outperforms ACVS real-world testing, achieving real 99.75% after applying WCCS. explores importance customized over pre-implemented services when model characteristics not pixel-by-pixel examination.

Language: Английский

Artificial intelligence for waste management in smart cities: a review DOI Creative Commons

Bingbing Fang,

Jiacheng Yu,

Zhonghao Chen

et al.

Environmental Chemistry Letters, Journal Year: 2023, Volume and Issue: 21(4), P. 1959 - 1989

Published: May 9, 2023

Abstract The rising amount of waste generated worldwide is inducing issues pollution, management, and recycling, calling for new strategies to improve the ecosystem, such as use artificial intelligence. Here, we review application intelligence in waste-to-energy, smart bins, waste-sorting robots, generation models, monitoring tracking, plastic pyrolysis, distinguishing fossil modern materials, logistics, disposal, illegal dumping, resource recovery, cities, process efficiency, cost savings, improving public health. Using logistics can reduce transportation distance by up 36.8%, savings 13.35%, time 28.22%. Artificial allows identifying sorting with an accuracy ranging from 72.8 99.95%. combined chemical analysis improves carbon emission estimation, energy conversion. We also explain how efficiency be increased costs reduced management systems cities.

Language: Английский

Citations

212
Artificial intelligence applications for sustainable solid waste management practices in Australia: A systematic review DOI
Lynda Andeobu, Santoso Wibowo, Srimannarayana Grandhi

et al.

The Science of The Total Environment, Journal Year: 2022, Volume and Issue: 834, P. 155389 - 155389

Published: April 20, 2022

Language: Английский

Citations

120
Applications of convolutional neural networks for intelligent waste identification and recycling: A review DOI

Ting-Wei Wu,

Hua Zhang, Wei Peng

et al.

Resources Conservation and Recycling, Journal Year: 2022, Volume and Issue: 190, P. 106813 - 106813

Published: Dec. 14, 2022

Language: Английский

Citations

92
Recent advances in applications of artificial intelligence in solid waste management: A review DOI
Ihsanullah Ihsanullah, Gulzar Alam, Arshad Jamal

et al.

Chemosphere, Journal Year: 2022, Volume and Issue: 309, P. 136631 - 136631

Published: Sept. 29, 2022

Language: Английский

Citations

79
Garbage detection and classification using a new deep learning-based machine vision system as a tool for sustainable waste recycling DOI
Shoufeng Jin, Zixuan Yang, Grzegorz Królczyk

et al.

Waste Management, Journal Year: 2023, Volume and Issue: 162, P. 123 - 130

Published: March 27, 2023

Language: Английский

Citations

54
Revolutionizing municipal solid waste management (MSWM) with machine learning as a clean resource: Opportunities, challenges and solutions DOI
Muhammad Tajammal Munir, Bing Li, Muhammad Naqvi

et al.

Fuel, Journal Year: 2023, Volume and Issue: 348, P. 128548 - 128548

Published: May 4, 2023

Language: Английский

Citations

54
Impact of leachate and landfill gas on the ecosystem and health: Research trends and the way forward towards sustainability DOI
Arpita Ghosh, Sunil Kumar,

Jit Das

et al.

Journal of Environmental Management, Journal Year: 2023, Volume and Issue: 336, P. 117708 - 117708

Published: March 11, 2023

Language: Английский

Citations

49
Machine learning in construction and demolition waste management: Progress, challenges, and future directions DOI
Yu Gao,

Jiayuan Wang,

Xiaoxiao Xu

et al.

Automation in Construction, Journal Year: 2024, Volume and Issue: 162, P. 105380 - 105380

Published: March 16, 2024

Language: Английский

Citations

28
A waste separation system based on sensor technology and deep learning: A simple approach applied to a case study of plastic packaging waste DOI Creative Commons

Rok Pučnik,

Monika Dokl, Yee Van Fan

et al.

Journal of Cleaner Production, Journal Year: 2024, Volume and Issue: 450, P. 141762 - 141762

Published: March 12, 2024

Plastic waste pollution is a challenging and complex issue caused mainly by high consumption of single-use plastics the linear economy "extract-make-use-throw". Improvements in recycling efficiency, behaviour changes, circular business models, more precise management system are essential to reduce volume plastic waste. This paper proposes simplified conceptual model for smart separation based on sensor technology deep learning (DL) facilitate recovery recycling. The proposed could be applied either at source (in bins) or centralised sorting facility. Two systems have been investigated: i) one utilising 6 sensors (near-infrared (NIR), humidity, temperature, CO2, CH4, laser profile sensor) ii) with an RGB camera separate packaging materials their composition, size, cleanliness, appearance. Simulations case study showed that camera-based sorting, Inception-v3, DL convolution neural networks (CNN), achieved best overall accuracy (78%) compared ResNet-50, MobileNet-v2, DenseNet-201. In addition, resulted higher number misclassified items bins, as it focused solely appearance rather than material composition. Sensor-based faced limitations, particularly dark colouration organic matter entrapment. Combining information from cameras potentially mitigate limitations each individual method, thus resulting purity separated fractions.

Language: Английский

Citations

22
Recent Developments in Technology for Sorting Plastic for Recycling: The Emergence of Artificial Intelligence and the Rise of the Robots DOI Creative Commons

Cesar Lubongo,

Mohammed A. A. Bin Daej, Paschalis Alexandridis

et al.

Recycling, Journal Year: 2024, Volume and Issue: 9(4), P. 59 - 59

Published: July 15, 2024

Plastics recycling is an important component of the circular economy. In mechanical recycling, recovery high-quality plastics for subsequent reprocessing requires plastic waste to be first sorted by type, color, and size. chemical certain types should removed as they negatively affect process. Such sortation objects at Materials Recovery Facilities (MRFs) relies increasingly on automated technology. Critical any sorting proper identification type. Spectroscopy used this end, augmented machine learning (ML) artificial intelligence (AI). Recent developments in application ML/AI are highlighted here, state art presented. Commercial equipment recyclables identified from a survey publicly available information. Automated equipment, ML/AI-based sorters, robotic sorters currently market evaluated regarding their sensors, capability sort plastics, primary application, throughput, accuracy. This information reflects rapid progress achieved plastics. However, film, dark comprising multiple polymers remains challenging. Improvements and/or new solutions forthcoming.

Language: Английский

Citations

20