基于LDA与改进布谷鸟算法的CNN-GRU网络木材染色配方预测
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TS664.1

基金项目:

国家自然科学基金面上项目(32171691);黑龙江省自然科学基金联合引导项目(LH2020C37)。


Wood Stain Formulation Prediction with a CNN-GRU Network based on LDA and Enhanced Cuckoo Search Algorithm
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为了精准预测木材染色配色配方,提出了一种线性判别分析(LDA)和改进布谷鸟算法(ICS)与卷积神经网络(CNN)与门控循环单元(GRU)的混合神经网络模型。该模型通过LDA处理光谱信息对其进行分类降维;利用CNN提取重要特征;将这些特征输入到GRU中进行训练;网络中的超参数由ICS算法进行寻优。该模型的表现通过多种评估标准进行测量,包括决定系数(R2)以及国际色差计算公式(CIEDE2000)等。在与多种传统模型的比较中,模型表现出优异的性能。此外,该模型的参数数量相对较少,计算效率高,且稳定性和可靠性良好。结果表明,将该模型应用于通过光谱信息进而预测木材染色配色配方问题上显示出了明显优势。

    Abstract:

    To accurately predict wood dye color matching formulations, a hybrid neural network model combining Linear Discriminant Analysis (LDA), Improved Cuckoo Search (ICS) algorithm, Convolutional Neural Network (CNN), and Gated Recurrent Unit (GRU) is proposed. The model processes and classifies the spectral information by LDA for dimensionality reduction; extracts essential features utilizing CNN; inputs these characteristics into GRU for training; and optimizes the hyperparameters in the network using the ICS algorithm. The model"s performance is measured through various evaluation criteria, including the coefficient of determination (R2) and the Color Difference Calculation Formula (CIEDE2000). In comparison with multiple traditional models, the proposed model demonstrates superior performance. Additionally, the model has a relatively low number of parameters, high computational efficiency, and excellent stability and reliability. The results indicate that the proposed model exhibits significant advantages when applied to predicting wood dye color matching formulations based on spectral information.

    参考文献
    相似文献
    引证文献
引用本文

管雪梅,崔宏博. 基于LDA与改进布谷鸟算法的CNN-GRU网络木材染色配方预测[J]. 科学技术与工程, 2024, 24(28): 12268-12276.
Guan Xuemei, Cui Hongbo. Wood Stain Formulation Prediction with a CNN-GRU Network based on LDA and Enhanced Cuckoo Search Algorithm[J]. Science Technology and Engineering,2024,24(28):12268-12276.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2024-01-20
  • 最后修改日期:2024-08-04
  • 录用日期:2024-03-21
  • 在线发布日期: 2024-11-05
  • 出版日期: