• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Grey Systems and Intelligent Services >A new virtual-sample-generating method based on the heuristics algorithm
【24h】

A new virtual-sample-generating method based on the heuristics algorithm

机译：一种新的基于启发式算法的虚拟样本生成方法

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

While back-propagation neural networks (BPNN) are effective learning tools for building non-linear models, they are often unstable when using small-data-sets. Therefore, in order to solve this problem, we construct artificial samples, called virtual samples, to improve the learning robustness. This research develops a novel method of virtual sample generation (VSG), named genetic algorithm-based virtual sample generation (GABVSG), which considers the integrated effects and constraints of data attributes. We first determine the acceptable range by using MTD functions, and construct the feasibility-based programming (FBP) model with BPNN. A genetic algorithm (GA) is then applied to accelerate the generation of feasible virtual samples. Finally, we use two real cases to verify the performance of the proposed method by comparing the results with those of two forecasting models, BPNN and support vector machine for regression (SVR). The experimental results indicate that the performance of the GABVSG method is superior to that of using original training data without artificial samples. Consequently, the proposed method can improve learning performance significantly when working with small samples.
机译：虽然背部传播神经网络（BPNN）是用于构建非线性模型的有效学习工具，但在使用小数据集时，它们通常是不稳定的。因此，为了解决这个问题，我们构建人为样本，称为虚拟样本，以提高学习鲁棒性。该研究开发了一种虚拟样本生成（VSG）的新方法，名为基于遗传算法的虚拟样本生成（GABVSG），其考虑了数据属性的集成效果和约束。我们首先通过使用MTD函数来确定可接受的范围，并使用BPNN构建基于可行性的编程（FBP）模型。然后应用遗传算法（GA）以加速可行虚拟样本的产生。最后，我们使用两个真实情况来验证所提出的方法的性能，通过将结果与两种预测模型，BPNN和支持向量机进行回归（SVR）的结果进行比较。实验结果表明，GABVSG方法的性能优于使用没有人造样品的原始训练数据的性能。因此，在使用小样品时，所提出的方法可以显着提高学习性能。

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