Design of Super Resolution and Fuzzy Deep Learning Architecture for the Classification of Land Cover and Landsliding Using Aerial Remote Sensing Data
The diversity, noise, interimage interference, image distortion, and increase in the number of classes in aerial remotely sensed dataset cause exertion in the classification. The efficacy and stability of convolutional neural networks increase in image classification with the specified use of featur...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10741345/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533420751028224 |
|---|---|
| author | Junaid Ali Khan Muhammad Attique Khan Mohammed Al-Khalidi Dina Abdulaziz AlHammadi Areej Alasiry Mehrez Marzougui Yudong Zhang Faheem Khan |
| author_facet | Junaid Ali Khan Muhammad Attique Khan Mohammed Al-Khalidi Dina Abdulaziz AlHammadi Areej Alasiry Mehrez Marzougui Yudong Zhang Faheem Khan |
| author_sort | Junaid Ali Khan |
| collection | DOAJ |
| description | The diversity, noise, interimage interference, image distortion, and increase in the number of classes in aerial remotely sensed dataset cause exertion in the classification. The efficacy and stability of convolutional neural networks increase in image classification with the specified use of feature selection algorithm that causes remarkably improved decision making. To address the associated difficulties, a fuzzy deep learning architecture has been designed with a super-resolution technique that consists of 40 convolutional, four polling, four inverted bottleneck blocks, and one fully connected layer. The fuzzy optimistic formula is implemented in 4 blocks as an activation function where information is fused from the previous layers and present block while the rest are using the ReLU transfer function to handle the issue of noise and interimage interference. Feature selection is performed based on the physics of chaotic particle swarm optimization hybrid with the active set algorithm. The accuracy of the proposed architecture is examined on three diverse datasets: Bijie earth landslide/nonlandslide, EuroSAT, and NWPU-RESISC45, comprised of varying classes. The results are compared with state-of-the-art models, such as the hybrid version of VGGNet-16, Yolov4, ResNet-50, DenseNet-121, and other reported techniques. Moreover, the stability and computational complexity of the presented architecture are computed on 50 independent runs. It has been observed that the proposed architecture is stable, accurate, and viable and exploits a smaller number of learnable parameters than the models considered in comparison. |
| format | Article |
| id | doaj-art-8930b064bea04faa9e5d438dcd4adccd |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-8930b064bea04faa9e5d438dcd4adccd2025-01-16T00:00:24ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-011833735110.1109/JSTARS.2024.349077510741345Design of Super Resolution and Fuzzy Deep Learning Architecture for the Classification of Land Cover and Landsliding Using Aerial Remote Sensing DataJunaid Ali Khan0https://orcid.org/0009-0004-0967-1211Muhammad Attique Khan1https://orcid.org/0000-0001-5723-3858Mohammed Al-Khalidi2https://orcid.org/0000-0002-1655-8514Dina Abdulaziz AlHammadi3Areej Alasiry4https://orcid.org/0000-0003-4088-5942Mehrez Marzougui5https://orcid.org/0000-0003-0445-5371Yudong Zhang6https://orcid.org/0000-0002-4870-1493Faheem Khan7https://orcid.org/0000-0001-6220-0225Department of Computer Science, HITEC University, Taxila, PakistanDepartment of Artificial Intelligence, College of Computer Engineering and Science, Prince Mohammad Bin Fahd University, Dhahran, Saudi ArabiaDepartment of Computing and Mathematics, Manchester Metropolitan University, Manchester, U.K.Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi ArabiaCollege of Computer Science, King Khalid University, Abha, Saudi ArabiaCollege of Computer Science, King Khalid University, Abha, Saudi ArabiaUniverslity of Leicester, Leicester, U.K.Department of Computer Engineering, Gachon University, Seongnam, South KoreaThe diversity, noise, interimage interference, image distortion, and increase in the number of classes in aerial remotely sensed dataset cause exertion in the classification. The efficacy and stability of convolutional neural networks increase in image classification with the specified use of feature selection algorithm that causes remarkably improved decision making. To address the associated difficulties, a fuzzy deep learning architecture has been designed with a super-resolution technique that consists of 40 convolutional, four polling, four inverted bottleneck blocks, and one fully connected layer. The fuzzy optimistic formula is implemented in 4 blocks as an activation function where information is fused from the previous layers and present block while the rest are using the ReLU transfer function to handle the issue of noise and interimage interference. Feature selection is performed based on the physics of chaotic particle swarm optimization hybrid with the active set algorithm. The accuracy of the proposed architecture is examined on three diverse datasets: Bijie earth landslide/nonlandslide, EuroSAT, and NWPU-RESISC45, comprised of varying classes. The results are compared with state-of-the-art models, such as the hybrid version of VGGNet-16, Yolov4, ResNet-50, DenseNet-121, and other reported techniques. Moreover, the stability and computational complexity of the presented architecture are computed on 50 independent runs. It has been observed that the proposed architecture is stable, accurate, and viable and exploits a smaller number of learnable parameters than the models considered in comparison.https://ieeexplore.ieee.org/document/10741345/Aerial remote sensing (RS)chaotic particle swarm optimization (C-PSO)fuzzy-CNN deep learning (DL)Monte Carlo simulationsstatistical analysis and model stability |
| spellingShingle | Junaid Ali Khan Muhammad Attique Khan Mohammed Al-Khalidi Dina Abdulaziz AlHammadi Areej Alasiry Mehrez Marzougui Yudong Zhang Faheem Khan Design of Super Resolution and Fuzzy Deep Learning Architecture for the Classification of Land Cover and Landsliding Using Aerial Remote Sensing Data IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Aerial remote sensing (RS) chaotic particle swarm optimization (C-PSO) fuzzy-CNN deep learning (DL) Monte Carlo simulations statistical analysis and model stability |
| title | Design of Super Resolution and Fuzzy Deep Learning Architecture for the Classification of Land Cover and Landsliding Using Aerial Remote Sensing Data |
| title_full | Design of Super Resolution and Fuzzy Deep Learning Architecture for the Classification of Land Cover and Landsliding Using Aerial Remote Sensing Data |
| title_fullStr | Design of Super Resolution and Fuzzy Deep Learning Architecture for the Classification of Land Cover and Landsliding Using Aerial Remote Sensing Data |
| title_full_unstemmed | Design of Super Resolution and Fuzzy Deep Learning Architecture for the Classification of Land Cover and Landsliding Using Aerial Remote Sensing Data |
| title_short | Design of Super Resolution and Fuzzy Deep Learning Architecture for the Classification of Land Cover and Landsliding Using Aerial Remote Sensing Data |
| title_sort | design of super resolution and fuzzy deep learning architecture for the classification of land cover and landsliding using aerial remote sensing data |
| topic | Aerial remote sensing (RS) chaotic particle swarm optimization (C-PSO) fuzzy-CNN deep learning (DL) Monte Carlo simulations statistical analysis and model stability |
| url | https://ieeexplore.ieee.org/document/10741345/ |
| work_keys_str_mv | AT junaidalikhan designofsuperresolutionandfuzzydeeplearningarchitecturefortheclassificationoflandcoverandlandslidingusingaerialremotesensingdata AT muhammadattiquekhan designofsuperresolutionandfuzzydeeplearningarchitecturefortheclassificationoflandcoverandlandslidingusingaerialremotesensingdata AT mohammedalkhalidi designofsuperresolutionandfuzzydeeplearningarchitecturefortheclassificationoflandcoverandlandslidingusingaerialremotesensingdata AT dinaabdulazizalhammadi designofsuperresolutionandfuzzydeeplearningarchitecturefortheclassificationoflandcoverandlandslidingusingaerialremotesensingdata AT areejalasiry designofsuperresolutionandfuzzydeeplearningarchitecturefortheclassificationoflandcoverandlandslidingusingaerialremotesensingdata AT mehrezmarzougui designofsuperresolutionandfuzzydeeplearningarchitecturefortheclassificationoflandcoverandlandslidingusingaerialremotesensingdata AT yudongzhang designofsuperresolutionandfuzzydeeplearningarchitecturefortheclassificationoflandcoverandlandslidingusingaerialremotesensingdata AT faheemkhan designofsuperresolutionandfuzzydeeplearningarchitecturefortheclassificationoflandcoverandlandslidingusingaerialremotesensingdata |