An Optimized Neural Network with Bat Algorithm for DNA Sequence Classification  

作　　者：Muhammad Zubair Rehman Muhammad Aamir Nazri Mohd.Nawi Abdullah Khan Saima Anwar Lashari Siyab Khan 

机构地区：[1]Faculty of Computing and Information Technology,Sohar University,Sohar,311,Sultanate of Oman [2]Soft Computing&Data Mining Centre(SMC),Faculty of Computer Science&Information Technology,Universiti Tun Hussein Onn Malaysia(UTHM),Batu Pahat,86400,Malaysia [3]School of Electronics,Computing and Mathematics,University of Derby,Derby,DE221GB,United Kingdom [4]Institute of Computer Sciences and Information Technology,The University of Agriculture,25120,Peshawar,Pakistan [5]College of Computing and Informatics,Saudi Electronic University,Riyadh,Saudi Arabia

出　　处：《Computers, Materials & Continua》2022年第10期493-511,共19页计算机、材料和连续体（英文）

基　　金：This research is supported by Tier-1 Research Grant, vote no. H938 by ResearchManagement Office (RMC), Universiti Tun Hussein Onn Malaysia and Ministry of Higher Education,Malaysia.

摘　　要：Recently, many researchers have used nature inspired metaheuristicalgorithms due to their ability to perform optimally on complex problems. Tosolve problems in a simple way, in the recent era bat algorithm has becomefamous due to its high tendency towards convergence to the global optimummost of the time. But, still the standard bat with random walk has a problemof getting stuck in local minima. In order to solve this problem, this researchproposed bat algorithm with levy flight random walk. Then, the proposedBat with Levy flight algorithm is further hybridized with three differentvariants of ANN. The proposed BatLFBP is applied to the problem ofinsulin DNA sequence classification of healthy homosapien. For classificationperformance, the proposed models such as Bat levy flight Artificial NeuralNetwork (BatLFANN) and Bat levy Flight Back Propagation (BatLFBP) arecompared with the other state-of-the-art algorithms like Bat Artificial NeuralNetwork (BatANN), Bat back propagation (BatBP), Bat Gaussian distribution Artificial Neural Network (BatGDANN). And Bat Gaussian distributionback propagation (BatGDBP), in-terms of means squared error (MSE) andaccuracy. From the perspective of simulations results, it is show that theproposed BatLFANN achieved 99.88153% accuracy with MSE of 0.001185,and BatLFBP achieved 99.834185 accuracy with MSE of 0.001658 on WL5.While on WL10 the proposed BatLFANN achieved 99.89899% accuracy withMSE of 0.00101, and BatLFBP achieved 99.84473% accuracy with MSE of0.004553. Similarly, on WL15 the proposed BatLFANN achieved 99.82853%accuracy with MSE of 0.001715, and BatLFBP achieved 99.3262% accuracywith MSE of 0.006738 which achieve better accuracy as compared to the otherhybrid models.

关 键 词：DNA sequence classification bat algorithm levy flight back propagation neural network hybrid artificial neural networks(HANN) 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]