Auto-sorting commonly recovered plastics from waste household appliances and electronics using near-infrared spectroscopy

Wu, Xiaoyu; Li, Jia; Yao, Lin; Xu, Zhenming

doi:10.1016/j.jclepro.2019.118732

Cited by 120 publications

(57 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, automatic waste sorting and recycling facility systems based on the common sensor spectrum have been proposed. For example, Wu et al [16] proposed an automatic plastic sorting system; they focused on sorting different plastics from waste electrical and electronic equipment based on near-infrared (NIR) spectroscopy. Additionally, Riba et al [17] presented an approach for the sensing and classification of parts of an automatic waste textile sorting machine based on the infrared spectra of textile samples.…”

Section: Introductionmentioning

confidence: 99%

EnCNN-UPMWS: Waste Classification by a CNN Ensemble Using the UPM Weighting Strategy

Zheng

2021

Electronics

View full text Add to dashboard Cite

The accurate and effective classification of household solid waste (HSW) is an indispensable component in the current procedure of waste disposal. In this paper, a novel ensemble learning model called EnCNN-UPMWS, which is based on convolutional neural networks (CNNs) and an unequal precision measurement weighting strategy (UPMWS), is proposed for the classification of HSW via waste images. First, three state-of-the-art CNNs, namely GoogLeNet, ResNet-50, and MobileNetV2, are used as ingredient classifiers to separately predict and obtain three predicted probability vectors, which are significant elements that affect the prediction performance by providing complementary information about the patterns to be classified. Then, the UPMWS is introduced to determine the weight coefficients of the ensemble models. The actual one-hot encoding labels of the validation set and the predicted probability vectors from the CNN ensemble are creatively used to calculate the weights for each classifier during the training phase, which can bring the aggregated prediction vector closer to the target label and improve the performance of the ensemble model. The proposed model was applied to two datasets, namely TrashNet (an open-access dataset) and FourTrash, which was constructed by collecting a total of 47,332 common HSW images containing four types of waste (wet waste, recyclables, harmful waste, and dry waste). The experimental results demonstrate the effectiveness of the proposed method in terms of its accuracy and F1-scores. Moreover, it was found that the UPMWS can simply and effectively enhance the performance of the ensemble learning model, and has potential applications in similar tasks of classification via ensemble learning.

show abstract

Section: Introductionmentioning

confidence: 99%

EnCNN-UPMWS: Waste Classification by a CNN Ensemble Using the UPM Weighting Strategy

Zheng

2021

Electronics

View full text Add to dashboard Cite

show abstract

“…It uses Spectral Angle Mapper (SAM) as implemented in the R package RStoolbox (Leutner et al, 2019). The algorithm recognizes different polymers successfully (Wu et al, 2020b), and to this end the waste recycling industry has used it for over 15 years (Kulcke et al, 2003). The SAM algorithm is, however, just one of the classical methods used for hyperspectral image classification.…”

Section: Software Functionalitiesmentioning

confidence: 99%

“…Although the Spectral Mapper Algorithm discriminates well between polymers (Wu et al, 2020b) we tested whether it was correctly implemented in the uFTIR package. To do so, we recorded the spectra of one polyethylene bag, two plastic cups -one made of polypropylene and the other made of polystyrene-, and a polystyrene standard film (VARIAN P/N 883-9120).…”

Section: Algorithm Validationmentioning

confidence: 99%

“…It summarizes the likeness as an angular degree; the smaller the degree, the greater the likeness. The algorithm recognizes different polymers successfully (Wu et al, 2020b), and to this end the waste recycling industry has used it for over 15 years (Kulcke et al, 2003). The post-processing included clipping the image to remove the membrane's polypropylene support ring, filtering all pixels that did not have a good match with any of the reference polymers (angular degree >= 1.2°), and smoothing the image using a 3x3 moving window (i.e.…”

Section: Identification -Ftir Microscopementioning

confidence: 99%

“…The spectral angle mapper algorithm discriminates well between polymers, and both scientists and industry have used it to classify plastic polymers (Wu et al, 2020b). However, we tested whether it was correctly implemented in the 'uFTIR' package.…”

Section: Ftir Microscope -Validation Test For Image Processing and Polymer Recognitionmentioning

confidence: 99%

See 2 more Smart Citations

Development and application of tests for microplastic detection in soil

Santander¹,

Alfonso²

View full text Add to dashboard Cite

China 20 Plastic mulch Sludge Flotation (NaCl) Visual sorting & μ-FTIR 78 ±13 63 ±13 PP PE PET * Polyethylene (PE), polystyrene (PS), polypropylene (PP), polyethylene terephthalate (PET), polyamide (PA), polybutylene (PB), ethylene vinyl acetate (EVA), high density polyethylene (HDPE), polyvinyl chloride (PVC), and polyurethane (PUR). ** The 'visual sorting' test requires a stereomicroscope to look for microplastics. 1 Time-of-flight secondary ion mass spectrometry. 2 Ding et al. (2020) did the visual sorting with a metallographic microscope. 3 Transmission electronic microscopy. 4 Pyrolysis coupled to gas chromatography and mass spectrometry.

show abstract

Strategic Approach Towards Plastic Waste Valorization: Challenges and Promising Chemical Upcycling Possibilities

et al. 2021

View full text Add to dashboard Cite

Plastic waste, which is one of the major sources of pollution in the landfills and oceans, has raised global concern, primarily due to the huge production rate, high durability, and the lack of utilization of the available waste management techniques. Recycling methods are preferable to reduce the impact of plastic pollution to some extent. However, most of the recycling techniques are associated with different drawbacks, high cost and downgrading of product quality being among the notable ones. The sustainable option here is to upcycle the plastic waste to create high-value materials to compensate for the cost of production. Several upcycling techniques are constantly being investigated and explored, which is currently the only economical option to resolve the plastic waste issue. This Review provides a comprehensive insight on the promising chemical routes available for upcycling of the most widely used plastic and mixed plastic wastes. The challenges inherent to these processes, the recent advances, and the significant role of the science and research community in resolving these issues are further emphasized.

show abstract

Auto-sorting commonly recovered plastics from waste household appliances and electronics using near-infrared spectroscopy

Cited by 120 publications

References 28 publications

EnCNN-UPMWS: Waste Classification by a CNN Ensemble Using the UPM Weighting Strategy

EnCNN-UPMWS: Waste Classification by a CNN Ensemble Using the UPM Weighting Strategy

Development and application of tests for microplastic detection in soil

Strategic Approach Towards Plastic Waste Valorization: Challenges and Promising Chemical Upcycling Possibilities

Contact Info

Product

Resources

About