北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2023, Vol. 46 ›› Issue (3): 1-6.

• 人工智能使能网络通信 •    下一篇

一种适用于航天大数据的深度决策树算法

常霄1,黄智濒1,禹旻2,杨武兵2
  

  1. 1. 北京邮电大学 计算机学院 2. 中国航天空气动力技术研究院 第一研究所四室



  • 收稿日期:2022-05-23 修回日期:2022-07-05 出版日期:2023-06-28 发布日期:2023-06-05
  • 通讯作者: 黄智濒 E-mail:huangzb@bupt.edu.cn

A Deep Decision Tree Model for Aerospace Big Data

CHANG Xiao1 ,HUANZhibin1 ,YU Min2 ,YANWubing2
  

  • Received:2022-05-23 Revised:2022-07-05 Online:2023-06-28 Published:2023-06-05

摘要:

常规处理百万网格航天大数据的物理量回归分析方法不适用于复杂的流场环境,可使用多种机器学习模型解决该问题但已有的机器学习模型无法同时具备高预测精度模型可解释性和大数据处理能力对此,提出了一种新型深度决策树模型基于堆叠的深度森林模型,通过自适应多粒度扫描和自生长级联森林对隐藏特征进行提取和利用使用航天大数据进行实验,结果表明所提模型在预测精度泛化性能和核心功能增益等方面优于随机森林、XGBoost LightGBM 模型

关键词:

Abstract:

The conventional quantitative regression analysis method for processing millions of grid aerospace big data is not suitable for complex flow field environments. Under this background,  machine learning models may be a promising toll that can be used to solve this problem. However, the existing machine learning models may not simultaneously have sufficient prediction accuracy, model interpretability, and big data processing capabilities. To solve this challenge, a new deep decision tree model is proposed. Based on the stacked deep forest model, the hidden features are extracted and utilized by adaptive multi-granularity scanning and self-growing cascade forests. Using aerospace big data for experiments, the results show that the proposed model is superior to the random forest, extreme gradient boosting, and light gradient boosting machine models in terms of prediction accuracy, generalization performance, and core function gain.

Key words:

中图分类号: