Small-Sample Seabed Sediment Classification Based on Deep Learning

被引:3
|
作者
Zhao, Yuxin [1 ,2 ]
Zhu, Kexin [1 ,2 ]
Zhao, Ting [3 ]
Zheng, Liangfeng [1 ,2 ]
Deng, Xiong [1 ,2 ]
机构
[1] Harbin Engn Univ, Coll Intelligent Syst Sci & Engn, Harbin 150001, Peoples R China
[2] Minist Educ, Engn Res Ctr Nav Instruments, Harbin 150001, Peoples R China
[3] Harbin Engn Univ, Coll Underwater Acoust Engn, Harbin 150001, Peoples R China
关键词
acoustic remote sensing; seabed sediment classification; small-sample; side-scan sonar; self-attention generative adversarial network; self-attention densely connected convolutional network; SCAN SONAR IMAGES; RECOGNITION; MODEL;
D O I
10.3390/rs15082178
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Seabed sediment classification is of great significance in acoustic remote sensing. To accurately classify seabed sediments, big data are needed to train the classifier. However, acquiring seabed sediment information is expensive and time-consuming, which makes it crucial to design a well-performing classifier using small-sample seabed sediment data. To avoid data shortage, a self-attention generative adversarial network (SAGAN) was trained for data augmentation in this study. SAGAN consists of a generator, which generates data similar to the real image, and a discriminator, which distinguishes whether the image is real or generated. Furthermore, a new classifier for seabed sediment based on self-attention densely connected convolutional network (SADenseNet) is proposed to improve the classification accuracy of seabed sediment. The SADenseNet was trained using augmented images to improve the classification performance. The self-attention mechanism can scan the global image to obtain global features of the sediment image and is able to highlight key regions, improving the efficiency and accuracy of visual information processing. The proposed SADenseNet trained with the augmented dataset had the best performance, with classification accuracies of 92.31%, 95.72%, 97.85%, and 95.28% for rock, sand, mud, and overall, respectively, with a kappa coefficient of 0.934. The twelve classifiers trained with the augmented dataset improved the classification accuracy by 2.25%, 5.12%, 0.97%, and 2.64% for rock, sand, mud, and overall, respectively, and the kappa coefficient by 0.041 compared to the original dataset. In this study, SAGAN can enrich the features of the data, which makes the trained classification networks have better generalization. Compared with the state-of-the-art classifiers, the proposed SADenseNet has better classification performance.
引用
收藏
页数:24
相关论文
共 50 条
  • [31] The Illusion of Distribution-Free Small-Sample Classification in Genomics
    Dougherty, Edward R.
    Zollanvari, Amin
    Braga-Neto, Ulisses M.
    CURRENT GENOMICS, 2011, 12 (05) : 333 - 341
  • [32] Small-Sample Data Pricing Based on Data Augmentation and Meta-Learning
    Shen, Junxin
    Yang, Yi
    Xiao, Fanghao
    ELECTRONICS, 2024, 13 (21)
  • [33] Learning Deep Neural Network Based Kernel Functions for Small Sample Size Classification
    Zheng, Tieran
    Han, Jiqing
    Zheng, Guibin
    NEURAL INFORMATION PROCESSING, ICONIP 2017, PT I, 2017, 10634 : 135 - 143
  • [34] Is Bagging Effective in the Classification of Small-Sample Genomic and Proteomic Data?
    Vu, T. T.
    Braga-Neto, U. M.
    EURASIP JOURNAL ON BIOINFORMATICS AND SYSTEMS BIOLOGY, 2009, (01)
  • [35] ON SMALL-SAMPLE ESTIMATION
    BROWN, GW
    ANNALS OF MATHEMATICAL STATISTICS, 1947, 18 (04): : 582 - 585
  • [36] Fault Diagnosis Algorithm for Dry-Type Transformer Based on Deep Learning of Small-Sample Acoustic Array Signals
    Zheng, Qinglu
    Wang, Youyuan
    Zhang, Zhanxi
    IEEE SENSORS LETTERS, 2024, 8 (10)
  • [37] Optimizing the Sediment Classification of Small Side-Scan Sonar Images Based on Deep Learning
    Qin, Xiaoming
    Luo, Xiaowen
    Wu, Ziyin
    Shang, Jihong
    IEEE ACCESS, 2021, 9 : 29416 - 29428
  • [38] Small-Sample Solar Power Interval Prediction Based on Instance-Based Transfer Learning
    Long, Huan
    Geng, Runhao
    Sheng, Wanxing
    Hui, Hui
    Li, Rui
    Gu, Wei
    IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS, 2023, 59 (05) : 5283 - 5292
  • [39] Pre-trained network-based transfer learning: A small-sample machine learning approach to nuclear power plant classification problem
    Zhong, Xianping
    Ban, Heng
    ANNALS OF NUCLEAR ENERGY, 2022, 175
  • [40] A Small-Sample Method with EEG Signals Based on Abductive Learning for Motor Imagery Decoding
    Zhong, Tianyang
    Wei, Xiaozheng
    Shi, Enze
    Gao, Jiaxing
    Ma, Chong
    Wei, Yaonai
    Zhang, Songyao
    Guo, Lei
    Han, Junwei
    Liu, Tianming
    Zhang, Tuo
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION, MICCAI 2023, PT I, 2023, 14220 : 416 - 424