• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies >Selective ensemble based on extreme learning machine and improved discrete artificial fish swarm algorithm for haze forecast
【24h】

Selective ensemble based on extreme learning machine and improved discrete artificial fish swarm algorithm for haze forecast

机译：基于极端学习机的选择性合奏和改进的离散人工鱼类群雾霾预测算法

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

Urban haze pollution is becoming increasingly serious, which is considered very harmful for humans by World Health Organization (WHO). Haze forecasts can be used to protect human health. In this paper, a Selective ENsemble based on an Extreme Learning Machine (ELM) and Improved Discrete Artificial Fish swarm algorithm (IDAFSEN) is proposed, which overcomes the drawback that a single ELM is unstable in terms of its classification. First, the initial pool of base ELMs is generated by using bootstrap sampling, which is then pre-pruned by calculating the pair-wise diversity measure of each base ELM. Second, partial-based ELMs among the initial pool after pre-pruning with higher precision and with greater diversity are selected by using an Improved Discrete Artificial Fish Swarm Algorithm (IDAFSA). Finally, the selected base ELMs are integrated through majority voting. The Experimental results on 16 datasets from the UCI Machine Learning Repository demonstrate that IDAFSEN can achieve better classification accuracy than other previously reported methods. After a performance evaluation of the proposed approach, this paper looks at how this can be used in haze forecasting in China to protect human health.
机译：城市阴霾污染正在变得越来越严重，这是世界卫生组织（世卫组织）对人类的危害。雾霾预测可用于保护人类健康。在本文中，提出了一种基于极端学习机（ELM）和改进的离散人工鱼类群算法（IDAFSEN）的选择性集成，这克服了单个ELM在其分类方面不稳定的缺点。首先，通过使用自举采样来生成初始挖掘基础挖掘池，然后通过计算每个基础榆树的一对分集度量来预先修剪。其次，通过使用改进的离散人工鱼类群（IDAFSA）选择初始池中的初始池中的初始池中的部分榆树。最后，通过多数投票整合所选择的基础elm。从UCI机器学习存储库的16个数据集上的实验结果表明，IDAFSEN可以实现比其他先前报告的方法更好的分类精度。在拟议方法进行绩效评估后，本文介绍了如何在中国的雾霾预测中用于保护人类健康。

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