Aim of this work is to recognize different waste polymers through an innovative strategy based on a multivariate approach and a non-invasive spectroscopic technique. Five different plastic waste samples were chosen for the investigation: polyvinyl chloride (PVC), polypropylene (PP), polystyrene (PS), high density polyethylene (HDPE) and low density polyethylene (LDPE). A calibration dataset was realized utilizing the corresponding virgin polymers. Hyperspectral imaging in the short wave infrared range (1000-2500 nm) was thus chosen to evaluate the different plastic spectral attributes finalized to perform their recognition/classification. After exploring polymer spectral differences by principal component analysis (PCA), a hierarchical PLS-DA model was built allowing to classify the five different plastic waste typologies. Finally, an interval PLSDA was applied in order to reduce the number of useful wavelengths to speed up the process without losing quality in the classification. The proposed methodology, based on hierarchical classification, is very powerful and fast, allowing to recognize the five different polymers in a single step.

A hierarchical classification approach for the identification of different waste polymers by hyperspectral imaging / Bonifazi, Giuseppe; Capobianco, Giuseppe; di giovenale, Vanessa; Serranti, Silvia. - (2017), pp. 146-146. (Intervento presentato al convegno Colloquium Spectroscopicum Internationale XL (CSI-XL) tenutosi a Pisa) [10.13140/RG.2.2.23093.88805].

A hierarchical classification approach for the identification of different waste polymers by hyperspectral imaging

giuseppe bonifazi
Primo
;
giuseppe capobianco
Secondo
;
silvia serranti
Ultimo
2017

Abstract

Aim of this work is to recognize different waste polymers through an innovative strategy based on a multivariate approach and a non-invasive spectroscopic technique. Five different plastic waste samples were chosen for the investigation: polyvinyl chloride (PVC), polypropylene (PP), polystyrene (PS), high density polyethylene (HDPE) and low density polyethylene (LDPE). A calibration dataset was realized utilizing the corresponding virgin polymers. Hyperspectral imaging in the short wave infrared range (1000-2500 nm) was thus chosen to evaluate the different plastic spectral attributes finalized to perform their recognition/classification. After exploring polymer spectral differences by principal component analysis (PCA), a hierarchical PLS-DA model was built allowing to classify the five different plastic waste typologies. Finally, an interval PLSDA was applied in order to reduce the number of useful wavelengths to speed up the process without losing quality in the classification. The proposed methodology, based on hierarchical classification, is very powerful and fast, allowing to recognize the five different polymers in a single step.
2017
Colloquium Spectroscopicum Internationale XL (CSI-XL)
04 Pubblicazione in atti di convegno::04d Abstract in atti di convegno
A hierarchical classification approach for the identification of different waste polymers by hyperspectral imaging / Bonifazi, Giuseppe; Capobianco, Giuseppe; di giovenale, Vanessa; Serranti, Silvia. - (2017), pp. 146-146. (Intervento presentato al convegno Colloquium Spectroscopicum Internationale XL (CSI-XL) tenutosi a Pisa) [10.13140/RG.2.2.23093.88805].
File allegati a questo prodotto
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1176207
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact