###
计算机系统应用:2020,29(4):170-174
本文二维码信息
码上扫一扫!
基于Cotraining-LSTM空气质量校准算法
(1.中国科学院 沈阳计算技术研究所, 沈阳 110168;2.中国科学院大学, 北京 100049;3.辽宁省沈阳生态环境监测中心, 沈阳 110000;4.辽宁省医疗器械检验检测院, 沈阳 110000)
Air Quality Calibration Algorithm Based on Catraining-LSTM
(1.Shenyang Institute of Computing Technology, Chinese Academy of Sciences, Shenyang 110168, China;2.University of Chinese Academy of Sciences, Beijing 100049, China;3.Shenyang Ecological Environment Monitoring Center of Liaoning Province, Shenyang 110000, China;4.Liaoning Medical Device Inspection and Testing Institute, Shenyang 110000, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 282次   下载 279
投稿时间:2019-08-20    修订日期:2019-09-09
中文摘要: 空气环境问题越发成为人们关注的焦点.除了工厂排放的各种废气,私家车的普及都导致了当前令人担忧的空气环境状况.国家相关部门也开始加大对空气环境的治理,提出了环境质量网格化监测的相关政策.在此背景下,市场涌现出很多微型监测仪器,但由于自身内部的传感器精准度不够,存在数据偏差的问题.为了解决这一问题,本文通过利用神经网络技术中的长短期记忆网络(Long Short-Term Memory,LSTM)模型结合半监督学习方法,达到提高监测数据的精准度的目的.通过与其它模型进行对比分析,该方法达到了一定的效果.
Abstract:The problem of air environment has become the focus of attention. Apart from the exhaust emissions from factories, the popularity of private cars has led to worrisome air conditions. Related government agencis have also begun to strengthen the control of air environment, and put forward relevant policies for grid monitoring of environmental quality. In this context, many micro-monitoring instruments have emerged into the market, but due to the inadequate accuracy of internal sensors, there is a problem of data deviation. In order to solve this problem, this study uses the Long Short-Term Memory (LSTM) model of neural network technology and semi-supervised learning method to improve the accuracy of monitoring data. By comparing with other models, this method achieves a sound effect.
文章编号:7357     中图分类号:    文献标志码:
基金项目:辽宁省“兴辽英才计划”项目(XLYC1808004)
引用文本:
祁柏林,张欣,刘闽,魏景锋,杜毅明,金继鑫.基于Cotraining-LSTM空气质量校准算法.计算机系统应用,2020,29(4):170-174
QI Bo-Lin,ZHANG Xin,LIU Min,WEI Jing-Feng,DU Yi-Ming,JIN Ji-Xin.Air Quality Calibration Algorithm Based on Catraining-LSTM.COMPUTER SYSTEMS APPLICATIONS,2020,29(4):170-174

用微信扫一扫

用微信扫一扫