...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>International Journal of Computer Science and Technology >Machine Learning Techniques used for Analysis of Air Quality
【24h】

Machine Learning Techniques used for Analysis of Air Quality

机译：用于空气质量分析的机器学习技术

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

摘要

In the populated and creating nations, governments think about the guideline of air as a noteworthy undertaking. The meteorological and traffic factors, consuming of non-renewable energy sources, mechanical parameters, for example, control plant discharges assume noteworthy jobs in air pollution. Among all the particulate issue that decide the nature of the air, Particulate issue (PM 2.5) needs more consideration. At the point when its level is high in the air, it causes difficult issues on individuals’ wellbeing. Henceforth, controlling it by always keeping aware of its level in the air is significant. In this paper, Logistic relapse is utilized to recognize whether a data test is either dirtied or not contaminated. Auto relapse is utilized to foresee future estimations of PM2.5 dependent on the past PM2.5 readings. Learning of level of PM2.5 in nearing years, month or week, empowers us to lessen its level to lesser than the destructive range. This framework endeavors to anticipate PM2.5 level and identify air quality dependent on a data set comprising of day by day air conditions in a particular city.
机译：在人口稠密的创建国中，政府将航空指南视为一项值得注意的工作。气象和交通因素，不可再生能源的消耗，机械参数（例如控制工厂的排放量）在空气污染方面承担着重要的职责。在决定空气性质的所有颗粒物问题中，颗粒物问题（PM 2.5）需要更多考虑。当它处于高水平时，会给个人的健康带来困难。从此以后，始终保持关注空气中的水平来控制它非常重要。在本文中，逻辑回归是用来识别数据测试是否被污染或未被污染。利用自动复发功能可以根据过去的PM2.5读数预测对PM2.5的未来估算。在接近的年，月或周内学习PM2.5的水平，使我们能够将其水平降低到破坏性范围以下。该框架致力于根据特定城市每天的空气状况来预测PM2.5水平并确定空气质量。

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