基于单输出切比雪夫多项式神经网络的海洋矿物分类  

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

作　　者：金龙 陈秀芳 陈良铭 付金山[2] JIN Long;CHEN Xiufang;CHEN Liangming;FU Jinshan(School of Information Science and Engineering,Lanzhou University,Lanzhou 730000,Gansu,China;College of Underwater Acoustic Engineering,Harbin Engineering University,Harbin 150000,Heilongjiang,China)

机构地区：[1]兰州大学信息科学与工程学院,甘肃兰州730000 [2]哈尔滨工程大学水声工程学院,黑龙江哈尔滨150000

出　　处：《华南理工大学学报（自然科学版）》2020年第12期135-143,共9页Journal of South China University of Technology(Natural Science Edition)

基　　金：国家重点研发计划政府间科技合作项目(2017YFE0118900);国家自然科学基金资助项目(61703189,11561029);甘肃省自然科学基金重点资助项目(18JR3RA264);青海省自然科学基金团体项目(2020-ZJ-903);水声技术重点实验室开放基金资助项目(SSKF2018005);中央高校基础科研基金资助项目(lzujbky-2019-89)。

摘　　要：针对海洋矿物分类问题,提出了改进后的单输出切比雪夫多项式神经网络(single-output Chebyshev-polynomial neural network with general solution,SOCPNN-G)。该模型利用伪逆的通解来求参数,扩大解空间,能获得泛化性能更加优良的权重。在该模型中,子集方法用于确定神经元的初始数量和获得交叉验证的最佳重数。最后将改进的SOCPNN-G模型用于海洋矿物数据集中进行实验,结果表明,该模型训练准确率和测试准确率分别达到90.96%和83.33%,且对计算性能要求较低。这些优越性表明该模型在海洋矿物的实际应用中具有很好的前景。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 ge-neralization performances.In addition,in this model,the subset method was used to determine the initial nu-mber 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 perfor-mance are low.These advantages indicate that this model has excellent application prospects in marine minerals.

关 键 词：海洋矿物 分类 单输出切比雪夫多项式神经网络 权重 准确率 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]