Classification accuracy improvement of neural network classifiers by using unlabeled data

被引：17
|
作者：
Fardanesh, MT [1 ]
Ersoy, OK
机构：
[1] Calif State Univ, Seaside, CA 93955 USA
[2] Purdue Univ, Sch Elect & Comp Engn, W Lafayette, IN 47907 USA
来源：
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING | 1998年 / 36卷 / 03期
关键词：
D O I：
10.1109/36.673695
中图分类号：
P3 [地球物理学]; P59 [地球化学];
学科分类号：
0708 ; 070902 ;
摘要：
Classification accuracy improvement of neural network classifiers using unlabeled testing data is presented. In order to increase the classification accuracy without increasing the number of training data, the network makes use of testing data along with training data for learning; It is shown that including the unlabeled samples from underrepresented classes in the training set improves the classification accuracy of some of the classes during supervised-unsupervised learning.
引用
收藏
页码：1020 / 1025
页数：6
相关论文
共 50 条
  • [1] Data Correction For Enhancing Classification Accuracy By Unknown Deep Neural Network Classifiers
    Kwon, Hyun
    Yoon, Hyunsoo
    Choi, Daeseon
    KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, 2021, 15 (09): : 3243 - 3257
  • [2] Accuracy of neural network classifiers as a property of the size of the data set
    Crowther, Patricia S.
    Cox, Robert J.
    KNOWLEDGE-BASED INTELLIGENT INFORMATION AND ENGINEERING SYSTEMS, PT 3, PROCEEDINGS, 2006, 4253 : 1143 - 1149
  • [3] A STUDY OF NEURAL NETWORK PARAMETERS FOR IMPROVEMENT IN CLASSIFICATION ACCURACY
    Pathak, Avijit
    Tiwari, K. C.
    ALGORITHMS AND TECHNOLOGIES FOR MULTISPECTRAL, HYPERSPECTRAL, AND ULTRASPECTRAL IMAGERY XXII, 2016, 9840
  • [4] Increasing the accuracy of neural network classification using refined training data
    Kavzoglu, Taskin
    ENVIRONMENTAL MODELLING & SOFTWARE, 2009, 24 (07) : 850 - 858
  • [5] Predicting Classification Accuracy of Unlabeled Datasets Using Multiple Deep Neural Networks
    You, Shingchern D.
    Liu, Hsiao-Chung
    Liu, Chien-Hung
    IEEE ACCESS, 2022, 10 : 44627 - 44637
  • [6] Using convolutional neural network autoencoders to understand unlabeled data
    Edwards, Samuel
    Lee, Michael S.
    ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING FOR MULTI-DOMAIN OPERATIONS APPLICATIONS, 2019, 11006
  • [7] Classification of Weeds Using Neural Network Algorithms and Image Classifiers
    Joshi, Rakesh
    Sharma, Garima
    Tripathi, Vikas
    Nainwal, Ankita
    INTELLIGENT HUMAN COMPUTER INTERACTION, IHCI 2023, PT II, 2024, 14532 : 26 - 36
  • [8] Classification of plant somatic embryos by using neural network classifiers
    Ruan, R
    Xu, JZ
    Zhang, C
    Chi, CM
    Hu, WS
    BIOTECHNOLOGY PROGRESS, 1997, 13 (06) : 741 - 746
  • [9] Classification of plant somatic embryos by using neural network classifiers
    Ruan, Roger
    Xu, Jianzhong
    Zhang, Chun
    Chi, Chung-Ming
    Hu, Wei-Shou
    Biotechnology Progress, 13 (06): : 741 - 746
  • [10] Bayesian network classifiers: Beyond classification accuracy
    dos Santos, Edimilson B.
    Hruschka, Estevam R., Jr.
    Hruschka, Eduardo R.
    Ebecken, Nelson F. F.
    INTELLIGENT DATA ANALYSIS, 2011, 15 (03) : 279 - 298
12345