A Spectral Convolutional Neural Network Model Based on Adaptive Fick’s Law for Hyperspectral Image Classification

作     者：Tsu-Yang Wu Haonan Li Saru Kumari Chien-Ming Chen 

作者机构：School of Artificial Intelligence(School of Future Technology)Nanjing University of Information Science&TechnologyNanjing210044China College of Computer Science and EngineeringShandong University of Science and TechnologyQingdao266590China Department of MathematicsChaudhary Charan Singh UniversityMeerutUttar Pradesh250004India 

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

年 卷 期：2024年第79卷第4期

页      面：19-46页

核心收录：

学科分类：0810[工学-信息与通信工程] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 081002[工学-信号与信息处理] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Natural Science Foundation of Shandong Province China(Grant No.ZR202111230202) 

主　　题：Adaptive Fick’s law algorithm spectral convolutional neural network metaheuristic algorithm intelligent optimization algorithm hyperspectral image classification 

摘      要：Hyperspectral image classification stands as a pivotal task within the field of remote sensing,yet achieving highprecision classification remains a significant *** response to this challenge,a Spectral Convolutional Neural Network model based on Adaptive Fick’s Law Algorithm(AFLA-SCNN)is *** Adaptive Fick’s Law Algorithm(AFLA)constitutes a novel metaheuristic algorithm introduced herein,encompassing three new strategies:Adaptive weight factor,Gaussian mutation,and probability update *** adaptive weight factor,the algorithmcan adjust theweights according to the change in the number of iterations to improve the performance of the *** helps the algorithm avoid falling into local optimal solutions and improves the searchability of the *** probability update strategy helps to improve the exploitability and adaptability of the *** the AFLA-SCNN model,AFLA is employed to optimize two hyperparameters in the SCNN model,namely,“numEpochsand“miniBatchSize,to attain their optimal ***’s performance is initially validated across 28 functions in 10D,30D,and 50D for CEC2013 and 29 functions in 10D,30D,and 50D for *** results indicate AFLA’s marked performance superiority over nine other prominent optimization ***,the AFLA-SCNN model was compared with the Spectral Convolutional Neural Network model based on Fick’s Law Algorithm(FLA-SCNN),Spectral Convolutional Neural Network model based on Harris Hawks Optimization(HHO-SCNN),Spectral Convolutional Neural Network model based onDifferential Evolution(DE-SCNN),SpectralConvolutionalNeuralNetwork(SCNN)model,and SupportVector Machines(SVM)model using the Indian Pines dataset and PaviaUniversity *** experimental results show that the AFLA-SCNN model outperforms other models in terms of Accuracy,Precision,Recall,and F1-score on Indian Pines and Pavia *** them,the Accuracy of the AFLA-SCNN model on India