• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Constructing the function of 'Magnitude-of-Effect' for Artificial Neural Network (ANN) models and their application in Occupational Safety and Health (OSH) engineering.
【24h】

Constructing the function of 'Magnitude-of-Effect' for Artificial Neural Network (ANN) models and their application in Occupational Safety and Health (OSH) engineering.

机译：构造人工神经网络（ANN）模型的“效应量”功能及其在职业安全与健康（OSH）工程中的应用。

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

Safety professionals and practitioners are always searching for methods to accurately assess the association between exposures and possible occupational disorders or diseases and predict the outcome of any outcome. Statistical analysis and logistic regression in particular are among the most popular tools being used by them. Artificial Neural Network (ANN) models are another method of predicting outcomes, which are gradually finding their way in the safety field. It has been shown that they are capable of predicting outcomes more accurately than logistic regression, but they are incapable of demonstrating the direct correlation between exposure variables and possible outcome variables.;The first objective in this research was to demonstrate that Artificial Neural Network models can perform better that logistic regression models with data sets made of all ordinal variables, which has not been done so far. All the publications in this area were about either dichotomous or a combination of dichotomous and continuous variables.;The second objective of this study was to develop a mathematical function that can produce a measure to evaluate the direct association between exposure and possible outcome variables. This function was referred to as the function of Magnitude-of-Effect (MoE). Safety experts and practitioners can use the MoE function to interpret how strongly an exposure variable can affect the possible outcome variable. The significance of such achievement is that it can eliminate the artificial neural network models' shortcoming and make them more applicable in the occupational safety and health engineering field.;The result of this study showed that artificial neural network models performed significantly better than logistic regression models with a data set of all ordinal variables. And also the suggested MoE function was capable and valid enough to show any correlation between exposure and possible outcome variables.
机译：安全专业人员和从业人员一直在寻找方法，以准确评估暴露与可能的职业障碍或疾病之间的关联，并预测任何结果的结果。统计分析和逻辑回归尤其是它们使用的最受欢迎的工具。人工神经网络（ANN）模型是预测结果的另一种方法，正在逐渐在安全领域中找到自己的方法。研究表明，与Logistic回归相比，它们能够更准确地预测结果，但它们不能证明暴露变量与可能的结果变量之间具有直接相关性。;本研究的第一个目标是证明人工神经网络模型可以与所有序数变量组成的数据集相比，逻辑回归模型的性能更好，到目前为止尚未完成。该领域中的所有出版物都是关于二分变量或者是二分变量和连续变量的组合。本研究的第二个目标是开发一种数学函数，该函数可以产生一种评估暴露与可能的结果变量之间直接关联的方法。此功能称为效应量（MoE）的功能。安全专家和从业人员可以使用MoE函数来解释暴露变量对可能的结果变量的影响程度。这一成就的意义在于可以消除人工神经网络模型的缺点，使其更适用于职业安全与卫生工程领域。研究结果表明，人工神经网络模型的性能明显优于逻辑回归模型。具有所有序数变量的数据集。此外，建议的教育部功能足够有效，足以显示暴露与可能的结果变量之间的任何相关性。

著录项

  • 作者

    Moayed, Farman A.;

  • 作者单位

    University of Cincinnati.;

  • 授予单位 University of Cincinnati.;
  • 学科 Health Sciences Occupational Health and Safety.;Engineering Industrial.
  • 学位 Ph.D.
  • 年度 2008
  • 页码 72 p.
  • 总页数 72
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 职业性疾病预防;一般工业技术;
  • 关键词

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