Transportation and Air Quality. Perspectives and Projections in a Mediterranean Country. The Case of Greece

This study provides a thorough review and analysis of the evolution of the Greek vehicle fleet over the last ~30 years, which is next used for the generation of high granularity fleet projections and for the estimation of relevant environmental benefits by 2030. The integrated methodology developed takes also into account vehicle clustering and the Brown’s Double Simple Exponential Smoothing technique that together with the adoption of COPERT based emission factors allow for the estimation of the anticipated emissions in 2030. Expected 2030 emissions levels suggest a reduction across all pollutants in comparison to 2018, ranging from 3.7% for PM10 to 54.5% for NMVOC (and 46% for CO, 14% for SO2, 28% for NOX and 21% for CO2). We find that Greece is on track with national goals concerning the reduction of air pollution from the transportation sector, stressing the positive contribution of EVs and new, "greener" vehicles, and setting new challenges for the further improvement of the sector beyond the 2030 outlook.

Experiments with Fuzzy Methods for Forecasting Time Series as Alternatives to Classical Methods

Even though forecasting methods have advanced in the last few decades, economists still face a simple question: which prediction method gives the most accurate results? Econometric forecasting methods can deal with different types of time series and have good results, but in specific cases, they may fail to provide accurate predictions. Recently, new techniques borrowed from the soft computing area were adopted for economic forecasting. Starting from the importance of economic forecasts, we present an experimental study where we compared the accuracy of some of the most used econometric forecasting methods, namely the simple exponential smoothing, Holt and ARIMA methods, with that of two new methods based on the concept of fuzzy time series. We used a set of time series extracted from the Eurostat database and the R software for all data processing. The results of the experiments show that despite not being fully superior to the econometric techniques, the fuzzy time series forecasting methods could be considered as an alternative for specific time series.

A Branching Process Model for the Novel Coronavirus (Covid-19) Spread in Greece

The novel coronavirus (covid-19) was initially identified at the end of 2019 and caused a global health care crisis. The increased transmissibility of the virus, that led to high mortality, raises the interest of scientists worldwide. Thus, various methods and models have been extensively discussed, so to study and control covid-19 transmission. Mathematical modeling constitutes an important tool to estimate key parameters of the transmission and predict the dynamic of the virus. More precisely, in the relevant literature, epidemiology is considered as a classical application area of branching processes, which are stochastic individual-based processes. In this paper, we develop a classical Galton-Watson branching process approach for the covid-19 spread in Greece at the early stage. This approach is structured in two parts, initial and latter transmission stages, so to provide a comprehensive view of the virus spread through basic and effective reproduction numbers respectively, along with the probability of an outbreak. Additionally, the effectiveness of control measures is discussed, based on a simple exponential smoothing model, which is used to build a non-mitigation scenario. Finally, our primary aim is to model all transmission stages through branching processes in order to analyze the first semiannual spread of the ongoing coronavirus pandemic in the region of Greece.

Estimating hidden models and trends in COVID-19 Infected cases

The main aim of the present investigation is to estimate the hidden models and trends in COVID-19 infected cases in all the thirty seven district of from the period from 1st August,2020 to 31st December, 2020. Different statistical curve fitting tools like, Linear, Quadratic, S-Curve, Simple Exponential Smoothing, Holt’s Linear Exponential, Brown’s Linear Exponential Smoothing and Auto Regressive Integrated Moving Average models were employed to study the COVID-19 infected trends and it’s future predictions.

The Global Case-Fatality Rate of COVID-19 Has Been Declining Since May 2020

The objective of this study was to evaluate the trend of reported case fatality rate (rCFR) of COVID-19 over time, using globally reported COVID-19 cases and mortality data. We collected daily COVID-19 diagnoses and mortality data from the WHO’s daily situation reports dated January 1 to December 31, 2020. We performed three time-series models [simple exponential smoothing, auto-regressive integrated moving average, and automatic forecasting time-series (Prophet)] to identify the global trend of rCFR for COVID-19. We used beta regression models to investigate the association between the rCFR and potential predictors of each country and reported incidence rate ratios (IRRs) of each variable. The weekly global cumulative COVID-19 rCFR reached a peak at 7.23% during the 17th week (April 22–28, 2020). We found a positive and increasing trend for global daily rCFR values of COVID-19 until the 17th week (pre-peak period) and then a strong declining trend up until the 53rd week (post-peak period) toward 2.2% (December 29–31, 2020). In pre-peak of rCFR, the percentage of people aged 65 and above and the prevalence of obesity were significantly associated with the COVID-19 rCFR. The declining trend of global COVID-19 rCFR was not merely because of increased COVID-19 testing, because COVID-19 tests per 1,000 population had poor predictive value. Decreasing rCFR could be explained by an increased rate of infection in younger people or by the improvement of health care management, shielding from infection, and/or repurposing of several drugs that had shown a beneficial effect on reducing fatality because of COVID-19.

Forecasting daily COVID-19 confirmed, deaths and recovered cases using univariate time series models: A case of Pakistan study

The increasing confirmed cases and death counts of Coronavirus disease 2019 (COVID-19) in Pakistan has disturbed not only the health sector, but also all other sectors of the country. For precise policy making, accurate and efficient forecasts of confirmed cases and death counts are important. In this work, we used five different univariate time series models including; Autoregressive (AR), Moving Average (MA), Autoregressive Moving Average (ARMA), Nonparametric Autoregressive (NPAR) and Simple Exponential Smoothing (SES) models for forecasting confirmed, death and recovered cases. These models were applied to Pakistan COVID-19 data, covering the period from 10, March to 3, July 2020. To evaluate models accuracy, computed two standard mean errors such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The findings show that the time series models are useful in predicting COVID-19 confirmed, deaths and recovered cases. Furthermore, MA model outperformed the rest of all models for confirmed and deaths counts prediction, while ARMA is second best model. The SES model seems superior to other models for prediction of recovered counts, however MA is competitive. On the basis of best selected models, we forecast form 4th July to 14th August, 2020, which will be helpful for decision making of public health and other sectors of Pakistan.

Predicting Total Business Sales using Time Series Analysis

aEconomic activity undergoes 4 phases (expansion, peak, contraction, trough/recession) in which recession is a period of lowest activity and peak indicates the highest activity. Total Business sales is one of the key factors that influence the economic activity of a country. Total sales or gross sales is the grand total of all sales revenues a business generates from normal activities. The frequency of time series sales data can be monthly, quarterly, or annually. Prediction of business sales is highly important as it determines various factors in the market including Gross Domestic Product (GDP). The algorithms or models required for prediction of time series data are different from other machine learning models. Since sales is affected by time, a time series data should be stationary. Only when the data is stationarized, we can apply the algorithms on them. In this paper, monthly sales data is collected and predictions are done using moving average, simple exponential smoothing, Holt’s model, ARIMA, and SARIMAX. Root Mean Square(RMS) is the accuracy metric of time series models and lower RMS indicates higher accuracy. In this paper, a lower value of RMS is obtained for the SARIMAX model.

Modeling and Short-Term Forecasts of Indicators for COVID-19 Outbreak in 25 Countries at the end of March

Objective: The coronavirus, which originated in Wuhan, causing the disease called COVID-19, spread more than 200 countries and continents end of the March. In this study, it was aimed to model the outbreak with different time series models and also predict the indicators. Materials and Methods: The data was collected from 25 countries which have different process at least 20 days. ARIMA(p,d,q), Simple Exponential Smoothing, Holt’s Two Parameter, Brown’s Double Exponential Smoothing Models were used. The prediction and forecasting values were obtained for the countries. Trends and seasonal effects were also evaluated. Results and Discussion: China has almost under control according to forecasting. The cumulative death prevalence in Italy and Spain will be the highest, followed by the Netherlands, France, England, China, Denmark, Belgium, Brazil and Sweden respectively as of the first week of April. The highest daily case prevalence was observed in Belgium, America, Canada, Poland, Ireland, Netherlands, France and Israel between 10% and 12%.The lowest rate was observed in China and South Korea. Turkey was one of the leading countries in terms of ranking these criteria. The prevalence of the new case and the recovered were higher in Spain than Italy. Conclusion: More accurate predictions for the future can be obtained using time series models with a wide range of data from different countries by modelling real time and retrospective data. Bangladesh Journal of Medical Science Vol.19(0) 2020 p.06-20

Modeling and Short-Term Forecasts of Indicators for COVID-19 Outbreak in 25 Countries at the end of March

ABSTRACTBackgroundThe coronavirus, which originated in Wuhan, causing the disease called COVID-19, spread more than 200 countries and continents end of the March. There is a lot of data since the virus started. However, these data will be explanatory when accurate analyzes are made and will allow future predictions to be made. In this study, it was aimed to model the outbreak with different time series models and also predict the indicators.MethodsThe data was collected from 25 countries which have different process at least 20 days. ARIMA(p,d,q), Simple Exponential Smoothing, Holt’s Two Parameter, Brown’s Double Exponential Smoothing Models were used. The prediction and forecasting values were obtained for the countries. Trends and seasonal effects were also evaluated.ResultsChina has almost under control according to forecasting. The cumulative death prevalence in Italy and Spain will be the highest, followed by the Netherlands, France, England, China, Denmark, Belgium, Brazil and Sweden respectively as of the first week of April. The highest daily case prevalence was observed in Belgium, America, Canada, Poland, Ireland, Netherlands, France and Israel between 10% and 12%.The lowest rate was observed in China and South Korea. Turkey was one of the leading countries in terms of ranking these criteria. The prevalence of the new case and the recovered were higher in Spain than Italy.ConclusionsMore accurate predictions for the future can be obtained using time series models with a wide range of data from different countries by modelling real time and retrospective data.