Intelligent Deep Data Analytics Based Remote Sensing Scene Classification Model

作     者：Ahmed Althobaiti Abdullah Alhumaidi Alotaibi Sayed Abdel-Khalek Suliman A.Alsuhibany Romany F.Mansour 

作者机构：Department of Electrical EngineeringCollege of EngineeringTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Science and TechnologyCollege of RanyahTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of MathematicsCollege of ScienceP.O.Box 11099Taif UniversityTaif21944Saudi Arabia Department of Computer ScienceCollege of ComputerQassim UniversityBuraydah51452Saudi Arabia Department of MathematicsFaculty of ScienceNew Valley UniversityEl-Kharga72511Egypt 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第72卷第7期

页      面：1921-1938页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：The authors would like to thank the Taif University for funding this work through Taif University Research Supporting Project Number.(TURSP-2020/277) Taif University Taif Saudi Arabia 

主　　题：Remote sensing unmanned aerial vehicles deep learning artificial intelligence scene classification 

摘      要：Latest advancements in the integration of camera sensors paves a way for newUnmannedAerialVehicles(UAVs)applications such as analyzing geographical(spatial)variations of earth science in mitigating harmful environmental impacts and climate *** have achieved significant attention as a remote sensing environment,which captures high-resolution images from different scenes such as land,forest fire,flooding threats,road collision,landslides,and so on to enhance data analysis and decision *** scene classification has attracted much attention in the examination of earth data captured by *** paper proposes a new multi-modal fusion based earth data classification(MMF-EDC)*** MMF-EDC technique aims to identify the patterns that exist in the earth data and classifies them into appropriate class *** MMF-EDC technique involves a fusion of histogram of gradients(HOG),local binary patterns(LBP),and residual network(ResNet)*** fusion process integrates many feature vectors and an entropy based fusion process is carried out to enhance the classification *** addition,the quantum artificial flora optimization(QAFO)algorithm is applied as a hyperparameter optimization *** AFO algorithm is inspired by the reproduction and the migration of flora helps to decide the optimal parameters of the ResNet model namely learning rate,number of hidden layers,and their number of ***,Variational Autoencoder(VAE)based classification model is applied to assign appropriate class labels for a useful set of feature *** proposedMMF-EDCmodel has been tested using UCM and WHU-RS *** proposed MMFEDC model attains exhibits promising classification results on the applied remote sensing images with the accuracy of 0.989 and 0.994 on the test UCM and WHU-RS dataset respectively.