...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>The Aeronautical Journal >Prediction of warning level in aircraft accidents using data mining techniques
【24h】

Prediction of warning level in aircraft accidents using data mining techniques

机译：使用数据挖掘技术预测飞机事故中的警告等级

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Data mining is a data analysis process which is designed for large amounts of data. It proposes a methodology for evaluating risk and safety and describes the main issues of aircraft accidents. We have a huge amount of knowledge and data collection in aviation companies. This paper focuses on different feature selectwindion techniques applied to the datasets of airline databases to understand and clean the dataset. CFS subset evaluator, consistency subset evaluator, gain ratio feature evaluator, information gain attribute evaluator, OneR attribute evaluator, principal components attribute transformer, ReliefF attribute evaluatoboundar and symmetrical uncertainty attribute evaluator are used in this study in order to reduce the number of initial attributes. The classification algorithms, such as DT, KNN, SVM, NN and NB, are used to predict the warning level of the component as the class attribute. We have explored the use of different classification techniques on aviation components data. For this purpose Weka software tools are used. This study also proves that the principal components attribute with decision tree classifier would perform better than other attributes and techniques on airline data. Accuracy is also very highly improved. This work may be useful for an aviation company to make better predictions. Some safety recommendations are also addressed to airline companies.
机译：数据挖掘是一个数据分析过程，旨在处理大量数据。它提出了一种评估风险和安全性的方法，并描述了飞机事故的主要问题。我们在航空公司中拥有大量的知识和数据收集。本文重点介绍了应用于航空公司数据库数据集的不同特征选择缠绕技术，以了解和清理数据集。为了减少初始属性的数量，在本研究中使用了CFS子集评估器，一致性子集评估器，增益比率特征评估器，信息增益属性评估器，OneR属性评估器，主成分属性变换器，ReliefF属性评估边界和对称不确定性属性评估器。分类算法（例如DT，KNN，SVM，NN和NB）用于预测作为类别属性的组件的警告级别。我们已经探索了在航空部件数据上使用不同分类技术的方法。为此，使用了Weka软件工具。这项研究还证明，决策树分类器的主成分属性在航空数据上的性能优于其他属性和技术。准确性也得到了极大提高。这项工作可能对航空公司做出更好的预测很有用。还向航空公司提出了一些安全建议。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号