...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of The Institution of Engineers (India): Series B >An Application of Data Mining Techniques for Flood Forecasting: Application in Rivers Daya and Bhargavi, India
【24h】

An Application of Data Mining Techniques for Flood Forecasting: Application in Rivers Daya and Bhargavi, India

机译：数据挖掘技术在洪水预报中的应用：在印度达亚河和巴尔加维河中的应用

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

In the present study, with a view to speculate the water flow of two rivers in eastern India namely river Daya and river Bhargavi, the focus was on developing Cascaded Functional Link Artificial Neural Network (C-FLANN) model. Parameters of C-FLANN architecture were updated using Harmony Search (HS) and Differential Evolution (DE). As the numbers of samples are very low, there is a risk of over fitting. To avoid this Map reduce based ANOVA technique is used to select important features. These features were used and provided to the architecture which is used to predict the water flow in both the rivers, one day, one week and two weeks ahead. The results of both the techniques were compared with Radial Basis Functional Neural Network (RBFNN) and Multilayer Perceptron (MLP), two widely used artificial neural network for prediction. From the result it was confirmed that C-FLANN trained through HS gives better prediction result than being trained through DE or RBFNN or MLP and can be used for predicting water flow in different rivers.
机译：在本研究中，为了推测印度东部的两条河流，即大亚河和巴尔加维河的水流量，重点是开发级联功能链接人工神经网络（C-FLANN）模型。使用和谐搜索（HS）和差分进化（DE）更新了C-FLANN体系结构的参数。由于样本数量非常少，因此存在过度拟合的风险。为了避免这种情况，使用了基于Map Reduce的ANOVA技术来选择重要特征。这些功能已被使用并提供给用于预测未来一天，一周和两周的两条河流中水流量的体系结构。将两种技术的结果与径向基函数神经网络（RBFNN）和多层感知器（MLP）进行了比较，这两种神经网络是用于预测的广泛使用的人工神经网络。从结果可以证实，通过HS训练的C-FLANN比通过DE或RBFNN或MLP训练得到的预测结果更好，并且可以用于预测不同河流的水流量。

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