基于GAN网络的菌菇表型数据生成研究

被引：21

作者：

袁培森 ^{[1
]}

吴茂盛 ^{[1
]}

翟肇裕 ^{[2
]}

杨承林 ^{[1
]}

徐焕良 ^{[1
]}

机构：

[1] 南京农业大学信息科学技术学院

[2] 马德里理工大学技术工程和电信系统高级学院

来源：

农业机械学报 | 2019年 / 50卷 / 12期

关键词：

菌菇表型; 生成式对抗网络; 生成器; 判别器; Wasserstein距离;

D O I：

暂无

中图分类号：

TP183 [人工神经网络与计算]; S646 [菌类（食用菌）];

学科分类号：

090202 [蔬菜学]; 140502 [人工智能];

摘要：

生成式对抗网络是基于对抗过程生成数据模型的新框架,它能够生成高质量的图像数据,为解决小样本数据、非均衡数据分析等提供了行之有效的方法。菌菇作为重要的真菌之一,其种类繁多,数据长尾分布、非均衡性等为其表型智能化识别与分类带来了困难。针对蘑菇表型数据,设计了一个高效的蘑菇表型生成式对抗网络MPGAN。研究了菌菇表型数据生成技术,设计了用于菌菇表型数据生成的生成式对抗网络结构,系统分为模型训练和表型图像生成两个模块。为了提升生成质量,使用Wasserstein距离和带有梯度惩罚的损失函数。利用开源数据和私有数据集测试学习率、处理所需的批次数EPOCH与Wasserstein距离。系统生成的菌菇表型数据为后期菌菇数据分类与识别提供了大数据基础。

引用

页码：231 / 239

页数：9

共 20 条

[1]

Detection of exudates in fundus photographs with imbalanced learning using conditional generative adversarial network [J].

Zheng, Rui ;

Liu, Lei ;

Zhang, Shulin ;

Zheng, Chun ;

Bunyak, Filiz ;

Xu, Ronald ;

Li, Bin ;

Sun, Mingzhai .

BIOMEDICAL OPTICS EXPRESS, 2018, 9 (10) :4863-4878

[2]

Deep phenotyping: deep learning for temporal phenotype/genotype classification.[J].Sarah Taghavi Namin;Mohammad Esmaeilzadeh;Mohammad Najafi;Tim B. Brown;Justin O. Borevitz.Plant Methods.2018, 1鈥

[3]

Wasserstein GAN-Based Small-Sample Augmentation for New-Generation Artificial Intelligence: A Case Study of Cancer-Staging Data in Biology [J].

Liu, Yufei ;

Zhou, Yuan ;

Liu, Xin ;

Dong, Fang ;

Wang, Chang ;

Wang, Zihong .

ENGINEERING, 2019, 5 (01) :156-163

[4]

Effective data generation for imbalanced learning using conditional generative adversarial networks.[J].Georgios Douzas;Fernando Bacao.Expert Systems With Applications.2018,

[5]

druGAN: An Advanced Generative Adversarial Autoencoder Model for de Novo Generation of New Molecules with Desired Molecular Properties in Silico [J].

Kadurin, Artur ;

Nikolenko, Sergey ;

Khrabrov, Kuzma ;

Aliper, Alex ;

Zhavoronkov, Alex .

MOLECULAR PHARMACEUTICS, 2017, 14 (09) :3098-3104

[6]

A Fast and Accurate Algorithm to Test for Binary Phenotypes and Its Application to PheWAS [J].

Dey, Rounak ;

Schmidt, Ellen M. ;

Abecasis, Goncalo R. ;

Lee, Seunggeun .

AMERICAN JOURNAL OF HUMAN GENETICS, 2017, 101 (01) :37-49

[7]

COSNet: An R package for label prediction in unbalanced biological networks.[J].Marco Frasca;Giorgio Valentini.Neurocomputing.2017,

[8]

Learning from imbalanced data: open challenges and future directions [J].

Krawczyk B. .

Progress in Artificial Intelligence, 2016, 5 (04) :221-232

[9]

Modeling Genotype × Environment Interaction for Genomic Selection with Unbalanced Data from a Wheat Breeding Program.[J].Bettina Lado;Pablo González Barrios;Martín Quincke;Paula Silva;Lucía Gutiérrez.Crop Science.2016, 5

[10]

Learning from class-imbalanced data: Review of methods and applications.[J].Guo Haixiang;Li Yijing;Jennifer Shang;Gu Mingyun;Huang Yuanyue;Gong Bing.Expert Systems With Applications.2016,

← 1 2 →