Intelligent Fusion of Deep Features for Improved Waste Classification

<p dir="ltr">In this article, we address the problem of an image-based automatic classification of waste materials. Given the large number of waste categories and the importance of proper management of waste materials, the problem is known to be critical and of a particular interest....

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Kashif Ahmad (12592762) (author)
مؤلفون آخرون: Khalil Khan (9333883) (author), Ala Al-Fuqaha (4434340) (author)
منشور في: 2020
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513505646870528
author Kashif Ahmad (12592762)
author2 Khalil Khan (9333883)
Ala Al-Fuqaha (4434340)
author2_role author
author
author_facet Kashif Ahmad (12592762)
Khalil Khan (9333883)
Ala Al-Fuqaha (4434340)
author_role author
dc.creator.none.fl_str_mv Kashif Ahmad (12592762)
Khalil Khan (9333883)
Ala Al-Fuqaha (4434340)
dc.date.none.fl_str_mv 2020-06-04T09:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2020.2995681
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Intelligent_Fusion_of_Deep_Features_for_Improved_Waste_Classification/27003508
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Data management and data science
Waste management
waste classification
deep features
fusion
double fusion
particle swarm optimization genetic algorithms
IOWA
Feature extraction
Computer architecture
Analytical models
Computational modeling
Correlation
Genetic algorithms
dc.title.none.fl_str_mv Intelligent Fusion of Deep Features for Improved Waste Classification
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">In this article, we address the problem of an image-based automatic classification of waste materials. Given the large number of waste categories and the importance of proper management of waste materials, the problem is known to be critical and of a particular interest. To achieve reliable waste classification capability, we propose a novel approach, that we name double fusion, which optimally combines multiple deep learning models using feature and score-level fusion methods. The double fusion scheme ensures an optimized contribution of the deep models by, firstly, combining their capabilities in an early and late fusion scheme followed by a score-level fusion of the classification results obtained with early and late fusion methods. In total, we employ and compare six different fusion methods including two feature-level fusion schemes, namely (i) Discriminant Correlation Analysis and (ii) simple concatenation of deep features, and four late fusion methods, namely (i) Particle Swarm Optimization, (ii) Genetic modeling of deep features (iii) Induced Ordered Weighted Averaging and (iv) a baseline method where all the deep models are treated equally. Moreover, we also evaluate the performance of the individual deep models, and compare our results against state-of-the-art methods demonstrating a significant improvement of 3.58% over state-of-the-art.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2020.2995681" target="_blank">https://dx.doi.org/10.1109/access.2020.2995681</a></p>
eu_rights_str_mv openAccess
id Manara2_9ca867a9eaa4c0e26207e51e63df55d0
identifier_str_mv 10.1109/access.2020.2995681
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/27003508
publishDate 2020
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Intelligent Fusion of Deep Features for Improved Waste ClassificationKashif Ahmad (12592762)Khalil Khan (9333883)Ala Al-Fuqaha (4434340)Information and computing sciencesArtificial intelligenceComputer vision and multimedia computationData management and data scienceWaste managementwaste classificationdeep featuresfusiondouble fusionparticle swarm optimization genetic algorithmsIOWAFeature extractionComputer architectureAnalytical modelsComputational modelingCorrelationGenetic algorithms<p dir="ltr">In this article, we address the problem of an image-based automatic classification of waste materials. Given the large number of waste categories and the importance of proper management of waste materials, the problem is known to be critical and of a particular interest. To achieve reliable waste classification capability, we propose a novel approach, that we name double fusion, which optimally combines multiple deep learning models using feature and score-level fusion methods. The double fusion scheme ensures an optimized contribution of the deep models by, firstly, combining their capabilities in an early and late fusion scheme followed by a score-level fusion of the classification results obtained with early and late fusion methods. In total, we employ and compare six different fusion methods including two feature-level fusion schemes, namely (i) Discriminant Correlation Analysis and (ii) simple concatenation of deep features, and four late fusion methods, namely (i) Particle Swarm Optimization, (ii) Genetic modeling of deep features (iii) Induced Ordered Weighted Averaging and (iv) a baseline method where all the deep models are treated equally. Moreover, we also evaluate the performance of the individual deep models, and compare our results against state-of-the-art methods demonstrating a significant improvement of 3.58% over state-of-the-art.</p><h2>Other Information</h2><p dir="ltr">Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/deed.en" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2020.2995681" target="_blank">https://dx.doi.org/10.1109/access.2020.2995681</a></p>2020-06-04T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2020.2995681https://figshare.com/articles/journal_contribution/Intelligent_Fusion_of_Deep_Features_for_Improved_Waste_Classification/27003508CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/270035082020-06-04T09:00:00Z
spellingShingle Intelligent Fusion of Deep Features for Improved Waste Classification
Kashif Ahmad (12592762)
Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Data management and data science
Waste management
waste classification
deep features
fusion
double fusion
particle swarm optimization genetic algorithms
IOWA
Feature extraction
Computer architecture
Analytical models
Computational modeling
Correlation
Genetic algorithms
status_str publishedVersion
title Intelligent Fusion of Deep Features for Improved Waste Classification
title_full Intelligent Fusion of Deep Features for Improved Waste Classification
title_fullStr Intelligent Fusion of Deep Features for Improved Waste Classification
title_full_unstemmed Intelligent Fusion of Deep Features for Improved Waste Classification
title_short Intelligent Fusion of Deep Features for Improved Waste Classification
title_sort Intelligent Fusion of Deep Features for Improved Waste Classification
topic Information and computing sciences
Artificial intelligence
Computer vision and multimedia computation
Data management and data science
Waste management
waste classification
deep features
fusion
double fusion
particle swarm optimization genetic algorithms
IOWA
Feature extraction
Computer architecture
Analytical models
Computational modeling
Correlation
Genetic algorithms