Journal of South China University of Technology(Natural Science Edition) ›› 2020, Vol. 48 ›› Issue (12): 135-143.doi: 10.12141/j.issn.1000-565X.200389

• Artificial Intelligence Special • Previous Articles     Next Articles

Marine Mineral Classification Based on Single-Output Chebyshev-Polynomial Neural Network

JIN Long1 CHEN Xiufang1 CHEN Liangming1 FU Jinshan2   

  1. 1． School of Information Science and Engineering，Lanzhou University，Lanzhou 730000，Gansu，China; 2． College of Underwater Acoustic Engineering，Harbin Engineering University，Harbin 150000，Heilongjiang，China
  • Received:2020-07-06 Revised:2020-07-07 Online:2020-12-25 Published:2020-12-01
  • Contact: 金龙 ( 1988-) ，男，博士，教授，主要从事神经网络、机器人、智能信息处理研究。 E-mail:jinlongsysu@foxmail.com
  • About author:金龙 ( 1988-) ，男，博士，教授，主要从事神经网络、机器人、智能信息处理研究。
  • Supported by:

    Supported by the National Key Research and Development Program of China ( 2017YFE0118900) ，the National Natural Science Foundation of China ( 61703189，11561029) ，the Key Project of the Natural Science Foundation of Gansu Province ( 18JR3RA264) ，the Team Project of Natural Science Foundation of Qinghai Province ( 2020-ZJ-903) ，the Opening Fund of Acoustics Science and Technology Laboratory ( SSKF2018005) and the Fundamental Research Funds for the Central Universities ( lzujbky-2019-89)

PDF

73

Abstract:

Aiming at the classification of marine minerals，an improved single-output Chebyshev-polynomial neural network with general solution ( SOCPNN-G) was proposed． This model uses the general solution of pseudo-inverse to find the parameters and expand the solution space，and it can obtain weights with better generalization performances． In addition，in this model，the subset method was used to determine the initial number of neurons and obtain the optimal number of the cross validation． Finally，the modified SOCPNN-G was tested in the marine mineral data set． The experimental results show that the training accuracy and test accuracy of the model can reach 90. 96% and 83. 33% ，respectively，and the requirements for computing performance are low． These advantages indicate that this model has excellent application prospects in marine minerals．

Key words: marine mineral, classification, single-output Chebyshev-polynomial neural network with general solution ( SOCPNN-G) , weights, accuracy

CLC Number: