Efficient Classification of Imbalanced Natural Disasters Data Using Generative Adversarial Networks for Data Augmentation
Rapid damage identification and classification in disastrous situations and natural disasters are crucial for efficiently directing aid and resources. With the development of deep learning techniques and the availability of imagery content on social media platforms, extensive research has focused on...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-06-01
|
Series: | ISPRS International Journal of Geo-Information |
Subjects: | |
Online Access: | https://www.mdpi.com/2220-9964/12/6/245 |
_version_ | 1797594435872096256 |
---|---|
author | Rokaya Eltehewy Ahmed Abouelfarag Sherine Nagy Saleh |
author_facet | Rokaya Eltehewy Ahmed Abouelfarag Sherine Nagy Saleh |
author_sort | Rokaya Eltehewy |
collection | DOAJ |
description | Rapid damage identification and classification in disastrous situations and natural disasters are crucial for efficiently directing aid and resources. With the development of deep learning techniques and the availability of imagery content on social media platforms, extensive research has focused on damage assessment. Through the use of geospatial data related to such incidents, the visual characteristics of these images can quickly determine the safety situation in the region. However, training accurate disaster classification models has proven to be challenging due to the lack of labeled imagery data in this domain. This paper proposes a disaster classification framework, which combines a set of synthesized diverse disaster images generated using generative adversarial networks (GANs) and domain-specific fine-tuning of a deep convolutional neural network (CNN)-based model. The proposed model utilizes bootstrap aggregating (bagging) to further stabilize the target predictions. Since past work in this domain mainly suffers from limited data resources, a sample dataset that highlights the issue of imbalanced classification of multiple natural disasters was constructed and augmented. Qualitative and quantitative experiments show the validity of the data augmentation method employed in producing a balanced dataset. Further experiments with various evaluation metrics verified the proposed framework’s accuracy and generalization ability across different classes for the task of disaster classification in comparison to other state-of-the-art techniques. Furthermore, the framework outperforms the other models by an average validation accuracy of 11%. These results provide a deep learning solution for real-time disaster monitoring systems to mitigate the loss of lives and properties. |
first_indexed | 2024-03-11T02:22:38Z |
format | Article |
id | doaj.art-8ac1a7eb5fb240daad81337c60917276 |
institution | Directory Open Access Journal |
issn | 2220-9964 |
language | English |
last_indexed | 2024-03-11T02:22:38Z |
publishDate | 2023-06-01 |
publisher | MDPI AG |
record_format | Article |
series | ISPRS International Journal of Geo-Information |
spelling | doaj.art-8ac1a7eb5fb240daad81337c609172762023-11-18T10:43:54ZengMDPI AGISPRS International Journal of Geo-Information2220-99642023-06-0112624510.3390/ijgi12060245Efficient Classification of Imbalanced Natural Disasters Data Using Generative Adversarial Networks for Data AugmentationRokaya Eltehewy0Ahmed Abouelfarag1Sherine Nagy Saleh2Computer Engineering Department, College of Engineering & Technology, Arab Academy for Science & Technology (AAST), Cairo 2033, EgyptCollege of Artificial Intelligence, Arab Academy for Science & Technology (AAST), El Alamein 51718, EgyptComputer Engineering Department, College of Engineering & Technology, Arab Academy for Science & Technology (AAST), Alexandria 1029, EgyptRapid damage identification and classification in disastrous situations and natural disasters are crucial for efficiently directing aid and resources. With the development of deep learning techniques and the availability of imagery content on social media platforms, extensive research has focused on damage assessment. Through the use of geospatial data related to such incidents, the visual characteristics of these images can quickly determine the safety situation in the region. However, training accurate disaster classification models has proven to be challenging due to the lack of labeled imagery data in this domain. This paper proposes a disaster classification framework, which combines a set of synthesized diverse disaster images generated using generative adversarial networks (GANs) and domain-specific fine-tuning of a deep convolutional neural network (CNN)-based model. The proposed model utilizes bootstrap aggregating (bagging) to further stabilize the target predictions. Since past work in this domain mainly suffers from limited data resources, a sample dataset that highlights the issue of imbalanced classification of multiple natural disasters was constructed and augmented. Qualitative and quantitative experiments show the validity of the data augmentation method employed in producing a balanced dataset. Further experiments with various evaluation metrics verified the proposed framework’s accuracy and generalization ability across different classes for the task of disaster classification in comparison to other state-of-the-art techniques. Furthermore, the framework outperforms the other models by an average validation accuracy of 11%. These results provide a deep learning solution for real-time disaster monitoring systems to mitigate the loss of lives and properties.https://www.mdpi.com/2220-9964/12/6/245data augmentationdeep neural network architecturesdisaster classificationensemble classifiersgenerative adversarial networks |
spellingShingle | Rokaya Eltehewy Ahmed Abouelfarag Sherine Nagy Saleh Efficient Classification of Imbalanced Natural Disasters Data Using Generative Adversarial Networks for Data Augmentation ISPRS International Journal of Geo-Information data augmentation deep neural network architectures disaster classification ensemble classifiers generative adversarial networks |
title | Efficient Classification of Imbalanced Natural Disasters Data Using Generative Adversarial Networks for Data Augmentation |
title_full | Efficient Classification of Imbalanced Natural Disasters Data Using Generative Adversarial Networks for Data Augmentation |
title_fullStr | Efficient Classification of Imbalanced Natural Disasters Data Using Generative Adversarial Networks for Data Augmentation |
title_full_unstemmed | Efficient Classification of Imbalanced Natural Disasters Data Using Generative Adversarial Networks for Data Augmentation |
title_short | Efficient Classification of Imbalanced Natural Disasters Data Using Generative Adversarial Networks for Data Augmentation |
title_sort | efficient classification of imbalanced natural disasters data using generative adversarial networks for data augmentation |
topic | data augmentation deep neural network architectures disaster classification ensemble classifiers generative adversarial networks |
url | https://www.mdpi.com/2220-9964/12/6/245 |
work_keys_str_mv | AT rokayaeltehewy efficientclassificationofimbalancednaturaldisastersdatausinggenerativeadversarialnetworksfordataaugmentation AT ahmedabouelfarag efficientclassificationofimbalancednaturaldisastersdatausinggenerativeadversarialnetworksfordataaugmentation AT sherinenagysaleh efficientclassificationofimbalancednaturaldisastersdatausinggenerativeadversarialnetworksfordataaugmentation |