Post-earthquake building waste (PBW) management and recovery is a crucial aspect to manage because natural disasters produce a large amount of waste composed of heterogeneous materials, including construction and demolition waste (CDW) and hazardous materials. The inert components of PBW have a high potential for recycling and reuse, and they can represent an essential resource, if adequately separated, as secondary raw materials. This work aims to present the utilization of hyperspectral imaging to define the most accurate and reliable strategy for the automatic detection and sorting of different types of inert (e.g., concrete, brick, ceramic material, etc.). Principal Component Analysis (PCA) was applied to reduce the data dimension. A Support Vector MachineDiscriminant Analysis (SVM-DA) was adopted to build an efficient classifier. The results have been evaluated in terms of prediction maps and statistical parameters. Results showed that it is possible to recognize and classify PBW materials, distinguishing different types of materials, despite their very similar compositions. The achieved results represent an essential starting point for developing innovative strategies finalized to design, implement and set up automatic recognition and classification procedures of inert fractions. Moreover, this approach can also be applied to the quality control of recycled materials. The system could play a fundamental role in the recovery of PBW and efficient recycling management in post-earthquake areas.

Classification of post-earthquake building waste through Hyperspectral imaging approach

G. Bonifazi;G. Capobianco;S. Serranti;O. Trotta
2022

Abstract

Post-earthquake building waste (PBW) management and recovery is a crucial aspect to manage because natural disasters produce a large amount of waste composed of heterogeneous materials, including construction and demolition waste (CDW) and hazardous materials. The inert components of PBW have a high potential for recycling and reuse, and they can represent an essential resource, if adequately separated, as secondary raw materials. This work aims to present the utilization of hyperspectral imaging to define the most accurate and reliable strategy for the automatic detection and sorting of different types of inert (e.g., concrete, brick, ceramic material, etc.). Principal Component Analysis (PCA) was applied to reduce the data dimension. A Support Vector MachineDiscriminant Analysis (SVM-DA) was adopted to build an efficient classifier. The results have been evaluated in terms of prediction maps and statistical parameters. Results showed that it is possible to recognize and classify PBW materials, distinguishing different types of materials, despite their very similar compositions. The achieved results represent an essential starting point for developing innovative strategies finalized to design, implement and set up automatic recognition and classification procedures of inert fractions. Moreover, this approach can also be applied to the quality control of recycled materials. The system could play a fundamental role in the recovery of PBW and efficient recycling management in post-earthquake areas.
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: http://hdl.handle.net/11573/1654025
 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