The COVID-19 that spread globally severe health complications and substantial economic impact in various parts of the world. The COVID-19 forecast on infections is a significant and crucial information that will help in executing policies to effectively reduces the number of cases. Filtering techniques be a considerable technique to model dynamic structures because they provide good valuations over the recursive Bayesian updates. Kalman filters being one of the filtering techniques are extensively useful in the learning of contagious infections. Kalman filter algorithm performs an important role in the development of an actual and comprehensive approach to inhibit, learn, react, and reduces spreadable disorder outbreaks in people. The purpose of this paper is to forecast the COVID-19 infections using Kalman filter method. The Kalman filter (KF) was applied for the three most affected countries, namely USA, India, and Brazil. Based on the results obtained, the KF method is capable in keeping track with the real COVID-19 data in nearly all scenario. Kalman filter in the archetype background to implement and produce decent COVID-19 predictions. The results of KF method provides benefit in supporting decision making process for short term strategies in handling the COVID-19 outbreak.

中文翻译：

---

使用卡尔曼滤波器分析和预测前三个受影响国家的 COVID-19 病毒死亡、康复和确诊病例数

COVID-19 在全球范围内传播严重的健康并发症，并对世界各地的经济产生重大影响。COVID-19 对感染的预测是一项重要且关键的信息，将有助于执行政策以有效减少病例数。过滤技术是建模动态结构的重要技术，因为它们提供了对递归贝叶斯更新的良好估值。作为过滤技术之一的卡尔曼滤波器在传染性感染的学习中非常有用。卡尔曼滤波器算法在开发一种实际而全面的方法来抑制、学习、反应和减少人类可传播疾病爆发方面发挥着重要作用。本文的目的是使用卡尔曼滤波器方法预测 COVID-19 感染。卡尔曼滤波器 (KF) 应用于三个受影响最严重的国家，即美国、印度和巴西。根据获得的结果，KF 方法能够在几乎所有情况下跟踪真实的 COVID-19 数据。原型背景中的卡尔曼滤波器以实现和产生体面的 COVID-19 预测。KF 方法的结果为支持处理 COVID-19 爆发的短期策略的决策过程提供了好处。