Rapid classification of plastics by laser-induced breakdown spectroscopy (LIBS) coupled with partial least squares discrimination analysis based on variable importance (VI-PLS-DA)

Liu, Ke; Tian, Di; Wang, Hongxia; Yang, Gye Mo

doi:10.1039/c8ay02755b

Cited by 36 publications

(12 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In very recent years, LIBS has been applied to classify plastics and acquired satisfying results. LIBS with ANN achieved an accuracy outstripped 97.8% for LDPE/HDPE, which are difficult for NIR and Raman to separate. , Moreover, after a variable importance adjustment, LIBS and PLS-DA reached mAP at a startling 99.55%, and a detection speed outdid 10 fps …”

Section: Development and Status Quo Of Sensor-based Waste Sorting Tec...mentioning

confidence: 99%

Sensor-Based Technologies in Effective Solid Waste Sorting: Successful Applications, Sensor Combination, and Future Directions

Zhao

2022

Environ. Sci. Technol.

View full text Add to dashboard Cite

The increase in global population and improvement of living standards have stirred up a continuous increase in solid waste generation, while simple incineration and landfilling bring about serious environmental and health concerns. In order to improve resource recovery and mitigate pollution, noncontacting and nondestructive sensor-based waste sorting systems are applied to enhance solid waste classification. In recent years, in addition to the rapid development of computer hardware, especially improvements of GPU computing capacity, complicated and efficient classification algorithms have emerged and been widely used in industrial sectors. These advances allow computers to process signals from sensors more quickly and accurately and to classify matters automatically. This article introduces widely applied sensor-based technologies in solid waste sorting and analyzes applicable conditions for each specific method. The latest developed algorithms are critically compared with competitive counterparts. Successful practices are described, and findings are highlighted. Though spectroscopic-based and vision-based waste classifications have achieved high performance in accuracy and detection speed, challenges and future directions can still provide wide development opportunities. Concretely, these opportunities generally comprise classification of indistinct plastics, application of the latest object detection algorithms, appropriate data set formulating, and sensor combination for multiple sorting tasks within a single system.

show abstract

Section: Development and Status Quo Of Sensor-based Waste Sorting Tec...mentioning

confidence: 99%

Sensor-Based Technologies in Effective Solid Waste Sorting: Successful Applications, Sensor Combination, and Future Directions

Zhao

2022

Environ. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…In the thirteen types of plastics examined using PCA, the hyperspectral imaging with wavelengths ranging from 955 to 1700 nm proved that the spectral range was sufficient to identify plastics [ 47 ]. Furthermore, the most extensively used method of sorting waste plastic by multivariate analysis is with partial least squares discrimination analysis (PLS-DA), which is a very stable and straightforward approach for spectra data [ 48 ].…”

Section: Waste Plastic Recycling and Technologymentioning

confidence: 99%

Current Prospects for Plastic Waste Treatment

et al. 2022

View full text Add to dashboard Cite

The excessive amount of global plastic produced over the past century, together with poor waste management, has raised concerns about environmental sustainability. Plastic recycling has become a practical approach for diminishing plastic waste and maintaining sustainability among plastic waste management methods. Chemical and mechanical recycling are the typical approaches to recycling plastic waste, with a simple process, low cost, environmentally friendly process, and potential profitability. Several plastic materials, such as polypropylene, polystyrene, polyvinyl chloride, high-density polyethylene, low-density polyethylene, and polyurethanes, can be recycled with chemical and mechanical recycling approaches. Nevertheless, due to plastic waste’s varying physical and chemical properties, plastic waste separation becomes a challenge. Hence, a reliable and effective plastic waste separation technology is critical for increasing plastic waste’s value and recycling rate. Integrating recycling and plastic waste separation technologies would be an efficient method for reducing the accumulation of environmental contaminants produced by plastic waste, especially in industrial uses. This review addresses recent advances in plastic waste recycling technology, mainly with chemical recycling. The article also discusses the current recycling technology for various plastic materials.

show abstract

“…For PLS, latent variables are constructed that best explain the relationship between the spectral data and the output label. This technique has traditionally been popular as a chemometric tool, and can be used for both classification and regression tasks (Calvini et al, 2018;da Silva & Wiebeck, 2020;K. Liu et al, 2019;Pieszczek & Daszykowski, 2019;Saeki et al, 2003;Sato et al, 2002).…”

Section: Literature Reviewmentioning

confidence: 99%

Deep Learning for Chemometric Analysis of Plastic Spectral Data from Infrared and Raman Databases

Neo¹,

Low

Goodship³

et al. 2022

SSRN Journal

View full text Add to dashboard Cite

Rapid classification of plastics by laser-induced breakdown spectroscopy (LIBS) coupled with partial least squares discrimination analysis based on variable importance (VI-PLS-DA)

Abstract: Combination of LIBS and VI-PLS-DA is a promising approach to achieve the online analysis and process control of waste plastic recycling.

Cited by 36 publications

References 19 publications

Sensor-Based Technologies in Effective Solid Waste Sorting: Successful Applications, Sensor Combination, and Future Directions

Sensor-Based Technologies in Effective Solid Waste Sorting: Successful Applications, Sensor Combination, and Future Directions

Current Prospects for Plastic Waste Treatment

Deep Learning for Chemometric Analysis of Plastic Spectral Data from Infrared and Raman Databases

Contact Info

Product

Resources

About