...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Expert systems: The international journal of knowledge engineering >Forecasting COVID-19 cases using dynamic time warping and incremental machine learning methods
【24h】

Forecasting COVID-19 cases using dynamic time warping and incremental machine learning methods

机译：Forecasting COVID-19 cases using dynamic time warping and incremental machine learning methods

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       
页面导航
  • 摘要
  • 著录项
  • 相关主题

摘要

The investment of time and resources for developing better strategies is key to dealingwith future pandemics. In this work, we recreated the situation of COVID-19across the year 2020, when the pandemic started spreading worldwide. We conductedexperiments to predict the coronavirus cases for the 50 countries with themost cases during 2020. We compared the performance of state-of-the-art machinelearning algorithms, such as long-short-term memory networks, against that of onlineincremental machine learning algorithms. To find the best strategy, we performedexperiments to test three different approaches. In the first approach (single-country),we trained each model using data only from the country we were predicting. In thesecond one (multiple-country), we trained a model using the data from the 50 countries,and we used that model to predict each of the 50 countries. In the third experiment,we first applied clustering to calculate the nine most similar countries to thecountry that we were predicting. We consider two countries to be similar if the differencesbetween the curve that represents the COVID-19 time series are small. Todo so, we used time series similarity measures (TSSM) such as Euclidean Distance(ED) and Dynamic Time Warping (DTW). TSSM return a real value that representsthe distance between the points in two time series which can be interpreted as howsimilar they are. Then, we trained the models with the data from the nine more similarcountries to the one that was predicted and the predicted one. We used the modelARIMA as a baseline for our results. Results show that the idea of using TSSM is avery effective approach. By using it with the ED, the obtained RMSE in the singlecountryand multiple-country approaches was reduced by 74.21% and 74.70%,respectively. And by using the DTW, the RMSE was reduced by 74.89% and 75.36%.The main advantage of our methodology is that it is very simple and fast to applysince it is only based on time series data, as opposed to more complex methodologiesthat require a deep and thorough study to consider the number of parameters involved in the spread of the virus and their corresponding values. We made our codepublic to allow other researchers to explore our proposed methodology.

著录项

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