Karacuha Ertugrul, Onal Nisa Ozge, Ergun Esra, Tabatadze Vasil, Alkas Hasan, Karacuha Kamil, Tontus Haci Omer, Nu Nguyen Vinh Ngoc
Informatics Institute, Istanbul Technical University 34467 Istanbul Turkey.
Faculty of Society and EconomicsRhine-Waal University of Applied Science 47533 Kleve Germany.
IEEE Access. 2020 Sep 4;8:164012-164034. doi: 10.1109/ACCESS.2020.3021952. eCollection 2020.
This study focuses on modeling, prediction, and analysis of confirmed, recovered, and death cases of COVID-19 by using Fractional Calculus in comparison with other models for eight countries including China, France, Italy, Spain, Turkey, the UK, and the US. First, the dataset is modeled using our previously proposed approach Deep Assessment Methodology, next, one step prediction of the future is made using two methods: Deep Assessment Methodology and Long Short-Term Memory. Later, a Gaussian prediction model is proposed to predict the short-term (30 Days) future of the pandemic, and prediction performance is evaluated. The proposed Gaussian model is compared to a time-dependent susceptible-infected-recovered (SIR) model. Lastly, an analysis of understanding the effect of history is made on memory vectors using wavelet-based denoising and correlation coefficients. Results prove that Deep Assessment Methodology successfully models the dataset with 0.6671%, 0.6957%, and 0.5756% average errors for confirmed, recovered, and death cases, respectively. We found that using the proposed Gaussian approach underestimates the trend of the pandemic and the fastest increase is observed in the US while the slowest is observed in China and Spain. Analysis of the past showed that, for all countries except Turkey, the current time instant is mainly dependent on the past two weeks where countries like Germany, Italy, and the UK have a shorter average incubation period when compared to the US and France.
本研究聚焦于运用分数阶微积分对包括中国、法国、意大利、西班牙、土耳其、英国和美国在内的八个国家的新冠肺炎确诊、康复和死亡病例进行建模、预测及分析，并与其他模型进行比较。首先，使用我们先前提出的深度评估方法对数据集进行建模，接下来，运用深度评估方法和长短期记忆两种方法对未来进行一步预测。随后，提出一个高斯预测模型来预测疫情的短期（30天）未来情况，并对预测性能进行评估。将所提出的高斯模型与时间依赖的易感-感染-康复（SIR）模型进行比较。最后，使用基于小波的去噪和相关系数对历史对记忆向量的影响进行分析。结果证明，深度评估方法分别以0.6671%、0.6957%和0.5756%的平均误差成功对确诊、康复和死亡病例的数据集进行了建模。我们发现，使用所提出的高斯方法低估了疫情趋势，美国的增长最快，而中国和西班牙的增长最慢。对过去的分析表明，除土耳其外，所有国家当前时刻主要依赖过去两周，与美国和法国相比，德国、意大利和英国等国家的平均潜伏期较短。
