Performance Evaluation of Soft Computing Approaches for Forecasting COVID-19 Pandemic Cases

Prediction of the burden of road traffic injuries in Iran by 2030: Prevalence, death, and disability-adjusted life years

PURPOSE

Road traffic accidents pose a global challenge with substantial human and economic costs. Iran experiences a high incidence of road traffic injuries, leading to a significant burden on society. This study aims to predict the future burden of road traffic injuries in Iran until 2030, providing valuable insights for policy-making and interventions to improve road safety and reduce the associated human and economic costs.

METHODS

This analytical study utilized time series models, specifically autoregressive integrated moving average (ARIMA) and artificial neural networks (ANNs), to predict the burden of road traffic accidents by analyzing past data to identify patterns and trends in Iran until 2030. The required data related to prevalence, death, and disability-adjusted life years (DALYs) rates were collected from the Institute for Health Metrics and Evaluation database and analyzed using R software and relevant modeling and statistical analysis packages.

RESULTS

Both prediction models, ARIMA and ANNs indicate that the prevalence rates (per 100,000) of all road traffic injuries, except for motorcyclist road injuries which have an almost flat trend, remaining at around 430, increase by 2030. Based on estimations of both models, the rates of death and DALYs due to motor vehicle and pedestrian road traffic injuries decrease. For motor vehicle road injuries, estimated trends decrease to approximately 520 DALYs and 10 deaths. Also, for pedestrian road injuries these rates reached approximately 300 DALYs and 6 deaths, according to the models. For cyclists and other road traffic injuries, the predicted DALY rates by the ANN model increase to almost 50 and 8, while predictions conducted by the ARIMA model show a static trend, remaining at 40 and approximately 6.5. Moreover, these rates for the prediction of death rate by the ANN model increased to 0.6 and 0.1, while predictions conducted by the ARIMA model show a static trend, remaining at 0.43 and 0.07. According to the ANN model, the predicted rates of DALY and death for motorcyclists decrease to 100 and approximately 2.7, respectively. On the other hand, predictions made by the ARIMA model show a static trend, with rates remaining at 200 and approximately 3.2, respectively.

CONCLUSION

The prevalence of road traffic injuries is predicted to increase, while the death and DALY rates of road traffic injuries show different patterns. Effective intervention programs and safety measures are necessary to prevent and reduce road traffic accidents. Different interventions should be designed and implemented specifically for different groups of pedestrians, cyclists, motorcyclists, and motor vehicle drivers.

Improving performance of deep learning predictive models for COVID-19 by incorporating environmental parameters

The Coronavirus disease 2019 (COVID-19) pandemic has severely crippled the economy on a global scale. Effective and accurate forecasting models are essential for proper management and preparedness of the healthcare system and resources, eventually aiding in preventing the rapid spread of the disease. With the intention to provide better forecasting tools for the management of the pandemic, the current research work analyzes the effect of the inclusion of environmental parameters in the forecasting of daily COVID-19 cases. Three univariate variants of the long short-term memory (LSTM) model (basic/vanilla, stacked, and bi-directional) were employed for the prediction of daily cases in 9 cities across 3 countries with varying climatic zones (tropical, sub-tropical, and frigid), namely India (New Delhi and Nagpur), USA (Yuma and Los Angeles) and Sweden (Stockholm, Skane, Uppsala and Vastra Gotaland). The results were compared to a basic multivariate LSTM model with environmental parameters (temperature (T) and relative humidity (RH)) as additional inputs. Periods with no or minimal lockdown were chosen specifically in these cities to observe the uninhibited spread of COVID-19 and explore its dependence on daily environmental parameters. The multivariate LSTM model showed the best overall performance; the mean absolute percentage error (MAPE) showed an average of 64% improvement from other univariate models upon the inclusion of the above environmental parameters. Correlation with temperature was generally positive for the cold regions and negative for the warm regions. RH showed mixed correlations, most likely driven by its temperature dependence and effect of allied local factors. The results suggest that the inclusion of environmental parameters could significantly improve the performance of LSTMs for predicting daily cases of COVID-19, although other positive and negative confounding factors can affect the forecasting power.

Machine Learning and Deep Learning Based Time Series Prediction and Forecasting of Ten Nations' COVID-19 Pandemic

In the paper, the authors investigated and predicted the future environmental circumstances of a COVID-19 to minimize its effects using artificial intelligence techniques. The experimental investigation of COVID-19 instances has been performed in ten countries, including India, the United States, Russia, Argentina, Brazil, Colombia, Italy, Turkey, Germany, and France using machine learning, deep learning, and time series models. The confirmed, deceased, and recovered datasets from January 22, 2020, to May 29, 2021, of Novel COVID-19 cases were considered from the Kaggle COVID dataset repository. The country-wise Exploratory Data Analysis visually represents the active, recovered, closed, and death cases from March 2020 to May 2021. The data are pre-processed and scaled using a MinMax scaler to extract and normalize the features to obtain an accurate prediction rate. The proposed methodology employs Random Forest Regressor, Decision Tree Regressor, K Nearest Regressor, Lasso Regression, Linear Regression, Bayesian Regression, Theilsen Regression, Kernel Ridge Regressor, RANSAC Regressor, XG Boost, Elastic Net Regressor, Facebook Prophet Model, Holt Model, Stacked Long Short-Term Memory, and Stacked Gated Recurrent Units to predict active COVID-19 confirmed, death, and recovered cases. Out of different machine learning, deep learning, and time series models, Random Forest Regressor, Facebook Prophet, and Stacked LSTM outperformed to predict the best results for COVID-19 instances with the lowest root-mean-square and highest R ² score values.

Vulture-Based AdaBoost-Feedforward Neural Frame Work for COVID-19 Prediction and Severity Analysis System

In today's scenario, many scientists and medical researchers have been involved in deep research for discovering the desired medicine to reduce the spread of COVID-19 disease. However, still, it is not the end. Hence, predicting the COVID possibility in an early stage is the most required matter to reduce the death risks. Therefore, many researchers have focused on designing an early prediction mechanism in the basis of deep learning (DL), machine learning (Ml), etc., on detecting the COVID virus and severity in the human body in an earlier stage. However, the complexity of X-ray images has made it difficult to attain the finest prediction accuracy. Hence, the present research work has aimed to develop a novel Vulture Based Adaboost-Feedforward Neural (VbAFN) scheme to forecast the COVID-19 severity early. Here, the chest X-ray images were employed to identify the COVID risk feature in humans. The preprocessing function is done in the initial phase; the error-free data is imported to the classification layer for the feature extraction and segmentation process. This investigation aims to track and segment the affected parts from the trained X-ray images by the vulture fitness and to segment them with a good exactness rate. Subsequently, the designed model has gained a better segmentation accuracy of 99.9% and a lower error rate of 0.0145, which is better than other compared models. Hence, this proposed model in medical applications will offer the finest results.