VISPNN:VGG-Inspired Stochastic Pooling Neural Network  

作　　者：Shui-Hua Wang Muhammad Attique Khan Yu-Dong Zhang 

机构地区：[1]School of Mathematics and Actuarial Science,University of Leicester,Leicester,LE17RH,United Kingdom [2]Department of Computer Science,HITEC University Taxila,Taxila,47080,Pakistan [3]School of Informatics,University of Leicester,Leicester,LE17RH,United Kingdom

出　　处：《Computers, Materials & Continua》2022年第2期3081-3097,共17页计算机、材料和连续体（英文）

基　　金：This paper is partially supported by the Royal Society International Exchanges Cost Share Award,UK(RP202G0230);Medical Research Council Confidence in Concept Award,UK(MC_PC_17171);Hope Foundation for Cancer Research,UK(RM60G0680);British Heart Foundation Accelerator Award,UK;Sino-UK Industrial Fund,UK(RP202G0289);Global Challenges Research Fund(GCRF),UK(P202PF11).In addition,we acknowledge the help of Dr.Hemil Patel and Dr.Qinghua Zhou for their help in English correction.

摘　　要：Aim Alcoholism is a disease that a patient becomes dependent or addicted to alcohol.This paper aims to design a novel artificial intelligence model that can recognize alcoholism more accurately.Methods We propose the VGG-Inspired stochastic pooling neural network(VISPNN)model based on three components:(i)a VGG-inspired mainstay network,(ii)the stochastic pooling technique,which aims to outperform traditional max pooling and average pooling,and(iii)an improved 20-way data augmentation(Gaussian noise,salt-and-pepper noise,speckle noise,Poisson noise,horizontal shear,vertical shear,rotation,Gamma correction,random translation,and scaling on both raw image and its horizontally mirrored image).In addition,two networks(Net-I and Net-II)are proposed in ablation studies.Net-I is based on VISPNN by replacing stochastic pooling with ordinary max pooling.Net-II removes the 20-way data augmentation.Results The results by ten runs of 10-fold cross-validation show that our VISPNN model gains a sensitivity of 97.98±1.32,a specificity of 97.80±1.35,a precision of 97.78±1.35,an accuracy of 97.89±1.11,an F1 score of 97.87±1.12,an MCC of 95.79±2.22,an FMI of 97.88±1.12,and an AUC of 0.9849,respectively.Conclusion The performance of our VISPNN model is better than two internal networks(Net-I and Net-II)and ten state-of-the-art alcoholism recognition methods.

关 键 词：Deep learning ALCOHOLISM multiple-way data augmentation VGG convolutional neural network stochastic pooling 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]