Rapid discrimination of plastic packaging materials using MIR spectroscopy coupled with independent components analysis (ICA)

Kassouf, Amine; Maalouly, Jacqueline; Rutledge, Douglas N.; Chébib, Hanna; Ducruet, Violette

doi:10.1016/j.wasman.2014.06.015

Cited by 72 publications

(31 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The observed signals are considered as weighted sums of pure source signals, the weights being proportional to the contribution of the corresponding pure signals to each mixture . Therefore, the objective of ICA is to search for the least Gaussian possible sources, ie, the most independent . A number of ICA algorithms are to be found in the study of Krishnaveni et al In our case, we used the MFICA algorithm .…”

Section: Chemometric Methodsmentioning

confidence: 99%

“…44,45 Therefore, the objective of ICA is to search for the least Gaussian possible sources, ie, the most independent. [46][47][48][49] A number of ICA algorithms are to be found in the study of Krishnaveni et al 49 In our case, we used the MFICA algorithm. 50 The particularities of MFICA are the non-negativity of components and weights, its appealing convergence, and high computational speed for high dimensional data.…”

Section: Independent Components Analysismentioning

confidence: 99%

See 1 more Smart Citation

Analysis of time‐resolved laser‐induced breakdown spectra by mean field‐independent components analysis (MFICA) and multivariate curve resolution–alternating least squares (MCR‐ALS)

Rakwe

Rutledge

Moutiers

et al. 2017

Journal of Chemometrics

View full text Add to dashboard Cite

Laser‐induced breakdown spectroscopy (LIBS) is an analytical technique allowing the determination of elemental concentrations in a variety of matrices in the solid, liquid, and gaseous phases. Because of the inherent complexity of the signal and to the high dimensionality of experimental data, chemometrics has been more and more applied in LIBS to perform samples identification or quantitative measurements. But multivariate methods can also be used for the description and physical interpretation of the plasma, particularly to exploit the temporal dimension of the LIBS signal, which is usually neglected in spectrochemical measurements. In this work, time‐resolved spectra of a pure aluminum sample were treated with 2 methods, mean field‐independent components analysis and multivariate curve resolution–alternating least squares, applying non‐negativity constraints for scores and components in both cases. Results obtained were compared with reference univariate measurements of the emission of the species of interest (ions, neutral atoms, and molecules). The interpretation of scores and components provided a physical description of phenomena that take place between species in the plasma, like ionic recombination and molecules formation. Overall, mean field‐independent components analysis and multivariate curve resolution–alternating least squares yield equivalent solutions with our dataset. This new approach is very promising for the treatment of time‐resolved data obtained by LIBS.

show abstract

Section: Chemometric Methodsmentioning

confidence: 99%

Section: Independent Components Analysismentioning

confidence: 99%

Analysis of time‐resolved laser‐induced breakdown spectra by mean field‐independent components analysis (MFICA) and multivariate curve resolution–alternating least squares (MCR‐ALS)

Rakwe

Rutledge

Moutiers

et al. 2017

Journal of Chemometrics

View full text Add to dashboard Cite

show abstract

“…With the emergence of hyperspectral imaging, some industrial firms have designed sorting devices able to discriminate several categories of plastics based on their absorption or transmittance spectra. The sorting process is generally performed with supervised classification that has been well developed with the emergence of computer sciences and data science [17,38,22]. The classification performance might be affected by several issues such as noises or overlapping regions in the feature space [34,21].…”

Section: Introductionmentioning

confidence: 99%

Evidential Classification of Incomplete Data via Imprecise Relabelling: Application to Plastic Sorting

Jacquin

Imoussaten

Trousset

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Besides the ecological issues, recycling of plastics involves economical matters that encourage industrial firms to invest in the field. Part of them have focused on the waste sorting phase by designing optical device able to discriminate on line among plastics categories. For achieving ecological and economical objectives, sorting errors must be minimized to avoid serious recycling problems and significant quality degradation of the final recycled product. Even with the most recent acquisition technologies based on spectra imaging, plastic recognition remains a tough task due to the presence of imprecision and uncertainty, e.g., variability in the measurement due to atmospheric disturbances, ageing of plastics, dark or black coloured materials etc. The enhancement of the recent sorting techniques based on classification algorithms leads to rather good performance results, however for such applications, the remaining errors have serious consequences. In this article, we propose an imprecise classification algorithm to minimize sorting errors of standard classifiers when dealing with incomplete data by both integrating the processing of classification's doubt and hesitation in the decision process and improving the classification performances. To this aim, we propose a relabelling procedure that allows to better represent the imprecision of the learning data and we introduce the belief functions framework to represent the posterior probability provided by a classifier. Finally, the performances of our approach compared to existing imprecise classifiers is illustrated on the sorting problem of four plastics categories from mid-wavelength infra-red spectra acquired in an industrial context.

show abstract

“…In addition, microorganisms might cause the decomposition, deterioration, and corruption of various materials, which can have economic impacts . Traditional food packaging materials including polypropylene, polyethylene, and polystyrene are difficult to degrade and easily produce white pollution, and the development of environmentally friendly alternative packaging materials is needed . With new technologies, new materials can be developed, which can not only resist bacterial growth but also minimize ecological impact.…”

Section: Introductionmentioning

confidence: 99%

Preparation and characterization of PHB/PBAT–based biodegradable antibacterial hydrophobic nanofibrous membranes

Lin

Fan

et al. 2017

Polymers for Advanced Techs

View full text Add to dashboard Cite

In this study, polyhydroxybutyrate/poly(butyleneadipate-co-terephthalate) (PHB/PBAT) nanofibrous membranes were produced by electrospinning the blends of biodegradable PHB and PBAT. The antibacterial hydrophobic nanofiber membranes were obtained by grafting 1-allylhydantoin and perfluorooctyl acrylate onto the PHB/PBAT membranes. The prepared nanofibrous membranes were chlorinated with chlorine bleach and characterized by scanning electron microscopy, Fourier transform infrared, and thermogravimetric analysis. The chlorinated nanofibrous membranes exhibited efficient antimicrobial activity against Escherichia coli O157:H7 (ATCC 43895) and Staphylococcus aureus (ATCC 6538) with 6.08 and 5.78 log reduction, respectively. The contact angle of this antibacterial membrane was 123.1°± 1.9°. The treated membranes showed good stability and durability towards UV-A light exposure and storage. To effectively block the entry of water and moisture and slow down food spoilage, food packaging materials need to be hydrophobic.Hydrophobic agents including wax, aluminum soap, zirconium soap, | ElectrospinningEight percent (wt) of PHB and PBAT (PHB/PBAT, 1:1, w/w) were dissolved in a mixture of CHCl 3 and DMF (CHCl 3 /DMF, 10:1, w/w).Electrospinning was performed at 20 kV with a flow rate of 1.5 mL·h −1 at ambient temperature. The distance from tip to collector was 15 cm. The electrospun fibrous membranes were collected on a rotating drum covered with an aluminum foil at a speed of 50 rpm. | Grafting AH and PFAThe mechanism scheme of AH and PFA grafting on PHB/PBAT surfaces is shown in Scheme 1. Initially, AH (1, 2, 3, 4, 5, 7, and 9 wt%) and AIBN (10 wt% of AH) were dissolved in ethanol solution in an ultrasonic bath for 20 minutes. Ethanol solution was at a bath ratio of 50:1 on the weight of fibrous membranes. Then, a certain amount of PHB/PBAT fibrous membranes was immersed in the above solution in a water bath at 75°C for 3 hours. Subsequently, fibrous membrane was extracted in ethanol for 24 hours using a Soxhlet extractor.Perfluorooctyl acrylate (3, 5, 7, 9, 11, and 13 wt%), AIBN (10 wt% of PFA), and OP-10 (2 wt% of PFA) were dissolved in ethanol solution by ultrasonic vibration for 20 minutes at room temperature. The PHB/PBAT fibrous membranes were added into the solution in a water bath at 75°C for 3 hours. Subsequently, fibrous membrane was extracted in ethanol for 24 hours using a Soxhlet extractor. | Chlorination and titrationThe PHB/PBAT-AH/PFA fibrous membranes were immersed in a 0.05% of NaOCl solution, pH 7, at ambient temperature for 1 hour to become an antimicrobial material. Then, the chlorinated fibrous membranes were washed thoroughly with deionized water and dried at 45°C for 1 hour to remove the unbound chlorine. The loaded active chlorine content on the membranes was measured by the modified iodometric/thiosulfate titration method. The chlorine weight percent of the membranes was calculated according to the equation below:where Cl + (%) is the weight percent of active chlorine on the sample; N and V are...

show abstract

Rapid discrimination of plastic packaging materials using MIR spectroscopy coupled with independent components analysis (ICA)

Cited by 72 publications

References 27 publications

Analysis of time‐resolved laser‐induced breakdown spectra by mean field‐independent components analysis (MFICA) and multivariate curve resolution–alternating least squares (MCR‐ALS)

Analysis of time‐resolved laser‐induced breakdown spectra by mean field‐independent components analysis (MFICA) and multivariate curve resolution–alternating least squares (MCR‐ALS)

Evidential Classification of Incomplete Data via Imprecise Relabelling: Application to Plastic Sorting

Preparation and characterization of PHB/PBAT–based biodegradable antibacterial hydrophobic nanofibrous membranes

Contact Info

Product

Resources

About