Academic Journal
Προβολή σε EDS

R3sNet: optimized residual neural network architecture for the classification of urban solid waste via images

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος: R3sNet: optimized residual neural network architecture for the classification of urban solid waste via images
Συγγραφείς: Castro Bello, Mirna, Romero Juárez, Victor M., Fuentes Pacheco, Jorge, Morales Morales, Cornelio, Marmolejo Vega, Carlos Virgilio, Zagal Barrera, Sergio R., Gutierrez Valencia, Diego Esteban, Marmolejo Duarte, Carlos Ramiro
Συνεισφορές: Universitat Politècnica de Catalunya. Departament de Tecnologia de l'Arquitectura, Universitat Politècnica de Catalunya. QURBIS - Quality of Urban Life: Innovation, Sustainability and Social Engagement
Στοιχεία εκδότη: Multidisciplinary Digital Publishing Institute (MDPI)
Έτος έκδοσης: 2025
Συλλογή: Universitat Politècnica de Catalunya, BarcelonaTech: UPCommons - Global access to UPC knowledge
Θεματικοί όροι: Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic, Àrees temàtiques de la UPC::Desenvolupament humà i sostenible::Política i gestió ambiental::Gestió de residus, Recycling (Waste, etc.) -- Computer software -- Design and construction, Automatic classification -- Mathematical models -- Industrial applications, Deep learning (Machine learning) -- Industrial applications, Deep learning, Waste classification, Convolution neuronal network, Optimized architecture, Residual networks, Reciclatge (Residus, etc.) -- Programari -- Disseny i construcció, Classificació automàtica -- Models matemàtics -- Aplicacions industrials, Aprenentatge profund -- Aplicacions industrials
Περιγραφή: Municipal solid waste (MSW) accumulation is a critical global challenge for society and governments, impacting environmental and social sustainability. Efficient separation of MSW is essential for resource recovery and advancing sustainable urban management practices. However, manual classification remains a slow and inefficient practice. In response, advances in artificial intelligence, particularly in machine learning, offer more precise and efficient alternative solutions to optimize this process. This research presents the development of a light deep neural network called R3sNet (three “Rs” for Reduce, Reuse, and Recycle) with residual modules trained end-to-end for the binary classification of MSW, with the capability for faster inference. The results indicate that the combination of processing techniques, optimized architecture, and training strategies contributes to an accuracy of 87% for organic waste and 94% for inorganic waste. R3sNet outperforms the pre-trained ResNet50 model by up to 6% in the classification of both organic and inorganic MSW, while also reducing the number of hyperparameters by 98.60% and GFLOPS by 65.17% compared to ResNet50. R3sNet contributes to sustainability by improving the waste separation processes, facilitating higher recycling rates, reducing landfill dependency, and promoting a circular economy. The model’s optimized computational requirements also translate into lower energy consumption during inference, making it well-suited for deployment in resource-constrained devices in smart urban environments. These advancements support the following Sustainable Development Goals (SDGs): SDG 11: Sustainable Cities and Communities, SDG 12: Responsible Consumption and Production, and SDG 13: Climate Action. ; Peer Reviewed ; Objectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats Sostenibles ; Objectius de Desenvolupament Sostenible::12 - Producció i Consum Responsables ; Objectius de Desenvolupament Sostenible::13 - Acció per al Clima ; Postprint (published version)
Τύπος εγγράφου: article in journal/newspaper
Περιγραφή αρχείου: application/pdf
Γλώσσα: English
Relation: https://www.mdpi.com/2071-1050/17/8/3502; Castro, M. [et al.]. R3sNet: optimized residual neural network architecture for the classification of urban solid waste via images. "Sustainability (Basel)", 14 Abril 2025, vol. 17, núm. 8, article 3502.; https://hdl.handle.net/2117/429447
DOI: 10.3390/su17083502
Διαθεσιμότητα: https://hdl.handle.net/2117/429447
https://doi.org/10.3390/su17083502
Rights: http://creativecommons.org/licenses/by/4.0/ ; Open Access ; Attribution 4.0 International
Αριθμός Καταχώρησης: edsbas.331A2567
Βάση Δεδομένων: BASE
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://hdl.handle.net/2117/429447#
    Name: EDS - BASE (ns324271)
    Category: fullText
    Text: View record from BASE
Header DbId: edsbas
DbLabel: BASE
An: edsbas.331A2567
RelevancyScore: 970
AccessLevel: 3
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 969.935607910156
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: R3sNet: optimized residual neural network architecture for the classification of urban solid waste via images
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Castro+Bello%2C+Mirna%22">Castro Bello, Mirna</searchLink><br /><searchLink fieldCode="AR" term="%22Romero+Juárez%2C+Victor+M%2E%22">Romero Juárez, Victor M.</searchLink><br /><searchLink fieldCode="AR" term="%22Fuentes+Pacheco%2C+Jorge%22">Fuentes Pacheco, Jorge</searchLink><br /><searchLink fieldCode="AR" term="%22Morales+Morales%2C+Cornelio%22">Morales Morales, Cornelio</searchLink><br /><searchLink fieldCode="AR" term="%22Marmolejo+Vega%2C+Carlos+Virgilio%22">Marmolejo Vega, Carlos Virgilio</searchLink><br /><searchLink fieldCode="AR" term="%22Zagal+Barrera%2C+Sergio+R%2E%22">Zagal Barrera, Sergio R.</searchLink><br /><searchLink fieldCode="AR" term="%22Gutierrez+Valencia%2C+Diego+Esteban%22">Gutierrez Valencia, Diego Esteban</searchLink><br /><searchLink fieldCode="AR" term="%22Marmolejo+Duarte%2C+Carlos+Ramiro%22">Marmolejo Duarte, Carlos Ramiro</searchLink>
– Name: Author
  Label: Contributors
  Group: Au
  Data: Universitat Politècnica de Catalunya. Departament de Tecnologia de l'Arquitectura<br />Universitat Politècnica de Catalunya. QURBIS - Quality of Urban Life: Innovation, Sustainability and Social Engagement
– Name: Publisher
  Label: Publisher Information
  Group: PubInfo
  Data: Multidisciplinary Digital Publishing Institute (MDPI)
– Name: DatePubCY
  Label: Publication Year
  Group: Date
  Data: 2025
– Name: Subset
  Label: Collection
  Group: HoldingsInfo
  Data: Universitat Politècnica de Catalunya, BarcelonaTech: UPCommons - Global access to UPC knowledge
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22Àrees+temàtiques+de+la+UPC%3A%3AInformàtica%3A%3AIntel·ligència+artificial%3A%3AAprenentatge+automàtic%22">Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic</searchLink><br /><searchLink fieldCode="DE" term="%22Àrees+temàtiques+de+la+UPC%3A%3ADesenvolupament+humà+i+sostenible%3A%3APolítica+i+gestió+ambiental%3A%3AGestió+de+residus%22">Àrees temàtiques de la UPC::Desenvolupament humà i sostenible::Política i gestió ambiental::Gestió de residus</searchLink><br /><searchLink fieldCode="DE" term="%22Recycling+%28Waste%22">Recycling (Waste</searchLink><br /><searchLink fieldCode="DE" term="%22etc%2E%29+--+Computer+software+--+Design+and+construction%22">etc.) -- Computer software -- Design and construction</searchLink><br /><searchLink fieldCode="DE" term="%22Automatic+classification+--+Mathematical+models+--+Industrial+applications%22">Automatic classification -- Mathematical models -- Industrial applications</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning+%28Machine+learning%29+--+Industrial+applications%22">Deep learning (Machine learning) -- Industrial applications</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Waste+classification%22">Waste classification</searchLink><br /><searchLink fieldCode="DE" term="%22Convolution+neuronal+network%22">Convolution neuronal network</searchLink><br /><searchLink fieldCode="DE" term="%22Optimized+architecture%22">Optimized architecture</searchLink><br /><searchLink fieldCode="DE" term="%22Residual+networks%22">Residual networks</searchLink><br /><searchLink fieldCode="DE" term="%22Reciclatge+%28Residus%22">Reciclatge (Residus</searchLink><br /><searchLink fieldCode="DE" term="%22etc%2E%29+--+Programari+--+Disseny+i+construcció%22">etc.) -- Programari -- Disseny i construcció</searchLink><br /><searchLink fieldCode="DE" term="%22Classificació+automàtica+--+Models+matemàtics+--+Aplicacions+industrials%22">Classificació automàtica -- Models matemàtics -- Aplicacions industrials</searchLink><br /><searchLink fieldCode="DE" term="%22Aprenentatge+profund+--+Aplicacions+industrials%22">Aprenentatge profund -- Aplicacions industrials</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Municipal solid waste (MSW) accumulation is a critical global challenge for society and governments, impacting environmental and social sustainability. Efficient separation of MSW is essential for resource recovery and advancing sustainable urban management practices. However, manual classification remains a slow and inefficient practice. In response, advances in artificial intelligence, particularly in machine learning, offer more precise and efficient alternative solutions to optimize this process. This research presents the development of a light deep neural network called R3sNet (three “Rs” for Reduce, Reuse, and Recycle) with residual modules trained end-to-end for the binary classification of MSW, with the capability for faster inference. The results indicate that the combination of processing techniques, optimized architecture, and training strategies contributes to an accuracy of 87% for organic waste and 94% for inorganic waste. R3sNet outperforms the pre-trained ResNet50 model by up to 6% in the classification of both organic and inorganic MSW, while also reducing the number of hyperparameters by 98.60% and GFLOPS by 65.17% compared to ResNet50. R3sNet contributes to sustainability by improving the waste separation processes, facilitating higher recycling rates, reducing landfill dependency, and promoting a circular economy. The model’s optimized computational requirements also translate into lower energy consumption during inference, making it well-suited for deployment in resource-constrained devices in smart urban environments. These advancements support the following Sustainable Development Goals (SDGs): SDG 11: Sustainable Cities and Communities, SDG 12: Responsible Consumption and Production, and SDG 13: Climate Action. ; Peer Reviewed ; Objectius de Desenvolupament Sostenible::11 - Ciutats i Comunitats Sostenibles ; Objectius de Desenvolupament Sostenible::12 - Producció i Consum Responsables ; Objectius de Desenvolupament Sostenible::13 - Acció per al Clima ; Postprint (published version)
– Name: TypeDocument
  Label: Document Type
  Group: TypDoc
  Data: article in journal/newspaper
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: application/pdf
– Name: Language
  Label: Language
  Group: Lang
  Data: English
– Name: NoteTitleSource
  Label: Relation
  Group: SrcInfo
  Data: https://www.mdpi.com/2071-1050/17/8/3502; Castro, M. [et al.]. R3sNet: optimized residual neural network architecture for the classification of urban solid waste via images. "Sustainability (Basel)", 14 Abril 2025, vol. 17, núm. 8, article 3502.; https://hdl.handle.net/2117/429447
– Name: DOI
  Label: DOI
  Group: ID
  Data: 10.3390/su17083502
– Name: URL
  Label: Availability
  Group: URL
  Data: https://hdl.handle.net/2117/429447<br />https://doi.org/10.3390/su17083502
– Name: Copyright
  Label: Rights
  Group: Cpyrght
  Data: http://creativecommons.org/licenses/by/4.0/ ; Open Access ; Attribution 4.0 International
– Name: AN
  Label: Accession Number
  Group: ID
  Data: edsbas.331A2567
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsbas&AN=edsbas.331A2567
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.3390/su17083502
    Languages:
      – Text: English
    Subjects:
      – SubjectFull: Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
        Type: general
      – SubjectFull: Àrees temàtiques de la UPC::Desenvolupament humà i sostenible::Política i gestió ambiental::Gestió de residus
        Type: general
      – SubjectFull: Recycling (Waste
        Type: general
      – SubjectFull: etc.) -- Computer software -- Design and construction
        Type: general
      – SubjectFull: Automatic classification -- Mathematical models -- Industrial applications
        Type: general
      – SubjectFull: Deep learning (Machine learning) -- Industrial applications
        Type: general
      – SubjectFull: Deep learning
        Type: general
      – SubjectFull: Waste classification
        Type: general
      – SubjectFull: Convolution neuronal network
        Type: general
      – SubjectFull: Optimized architecture
        Type: general
      – SubjectFull: Residual networks
        Type: general
      – SubjectFull: Reciclatge (Residus
        Type: general
      – SubjectFull: etc.) -- Programari -- Disseny i construcció
        Type: general
      – SubjectFull: Classificació automàtica -- Models matemàtics -- Aplicacions industrials
        Type: general
      – SubjectFull: Aprenentatge profund -- Aplicacions industrials
        Type: general
    Titles:
      – TitleFull: R3sNet: optimized residual neural network architecture for the classification of urban solid waste via images
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Castro Bello, Mirna
      – PersonEntity:
          Name:
            NameFull: Romero Juárez, Victor M.
      – PersonEntity:
          Name:
            NameFull: Fuentes Pacheco, Jorge
      – PersonEntity:
          Name:
            NameFull: Morales Morales, Cornelio
      – PersonEntity:
          Name:
            NameFull: Marmolejo Vega, Carlos Virgilio
      – PersonEntity:
          Name:
            NameFull: Zagal Barrera, Sergio R.
      – PersonEntity:
          Name:
            NameFull: Gutierrez Valencia, Diego Esteban
      – PersonEntity:
          Name:
            NameFull: Marmolejo Duarte, Carlos Ramiro
      – PersonEntity:
          Name:
            NameFull: Universitat Politècnica de Catalunya. Departament de Tecnologia de l'Arquitectura
      – PersonEntity:
          Name:
            NameFull: Universitat Politècnica de Catalunya. QURBIS - Quality of Urban Life: Innovation, Sustainability and Social Engagement
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2025
          Identifiers:
            – Type: issn-locals
              Value: edsbas
            – Type: issn-locals
              Value: edsbas.oa
ResultId 1