Forecasting deaths of road traffic injuries in China using an artificial neural network

Modelling low temporal, large spatial data of fatal crashes: An application of negative binomial GSARIMAX time series

Road traffic injuries represent a critical public health concern, particularly in developing nations such as Iran, where the incidence of fatal crashes is escalating. Addressing this issue effectively requires sophisticated analytical methodologies to elucidate and mitigate the multifaceted factors contributing to traffic fatalities. This study introduces the Negative Binomial Generalized Seasonal Autoregressive Integrated Moving Average with Exogenous Variables (GSARIMAX) model as an innovative approach for analyzing low temporal (daily) and large spatial count data of fatal crashes over a ten-year period (March 2014 to March 2022) in Iran. Unlike traditional models that predominantly focus on aggregated monthly or high-resolution data, the proposed negative binomial GSARIMAX model leverages daily count data, accommodating over-dispersion inherent in crash counts and providing a more granular and accurate analysis across extensive spatial regions. The model integrates significant exogenous variables, including traffic volume, maximum and minimum temperatures, wind speed, and wind direction, alongside harmonic seasonal components to capture both annual and semi-annual periodic fluctuations in crash occurrences. Model performance was rigorously evaluated using Deviance Information Criterion (DIC) and Mean Absolute Relative Error (MARE) metrics, alongside out-of-sample predictive accuracy assessments. The negative binomial GSARIMAX (0,1,2)-SOH model demonstrated superior performance compared to the Gaussian GSARIMAX counterpart, evidenced by lower MARE and DIC values. Notably, traffic volume and maximum temperature emerged as significant predictors of fatal crashes, while seasonal harmonic terms further enhanced model accuracy by effectively capturing temporal dynamics. The Bayesian estimation framework employed facilitates robust inference and the analysis of posterior predictive distributions, affirming the Negative Binomial GSARIMAX model's superior fit and forecasting capabilities. These findings underscore the model's potential advantages over conventional Gaussian statistical methods, particularly in handling low temporal resolution and large spatial datasets. Moreover, dynamic models incorporating exogenous variables demonstrated enhanced predictive performance, highlighting the importance of integrating diverse factors in crash analysis. This study not only advances the methodological landscape for traffic crash analysis but also provides actionable insights for policymakers and safety authorities. By identifying key determinants of fatal crashes and accounting for seasonal variations, the Negative Binomial GSARIMAX model serves as a valuable tool for informing targeted interventions aimed at reducing traffic fatalities. Future research should extend this approach by incorporating additional environmental and behavioral variables and conducting comparative analyses across multiple provinces to capture a broader spectrum of influencing conditions.

Forecasting time trend of road traffic crashes in Iran using the macro-scale traffic flow characteristics

Background

The serial correlation in the time series datasets should be considered to prevent biased estimates for coefficients. Nonetheless, the current models almost cannot explicitly handle autocorrelation and seasonality, and they focus mainly on the discrete nature of data. Nonetheless, the crash time series follows a normal distribution at the macro-scale. Moreover, the influential exogenous variables have been overlooked in Iran, employing univariate models. There are also contradictory results in the literature regarding the effect of average speed on crash frequency.

Objective

This study is aimed to evaluate the distinct impacts of mean speed on total and fatal accident time series at the national level. Besides, the SARIMAX modeling framework is introduced as a robust multivariate method for short-term crash frequency prediction.

Method

To this end, monthly total and fatal crash counts were aggregated for all rural highways in Iran. Besides, the time trends of traffic exposure, and average speed recorded by loop detectors, were aggregated at the same level as covariates. The Box-Jenkins methodology was employed for time series analysis.

Results

The results illustrated that the seasonal autoregressive integrated moving average with explanatory variable (SARIMAX) model outperformed the univariate ARIMA and SARIMA models. Also, SARIMA was more appropriate than the simple ARIMA when seasonality existed in the time series. Besides, the average speed had a negative linear association with the total crashes. In contrast, it revealed an increasing effect on fatal crashes.

Conclusion

Average speed has a dissimilar effect on the different traffic crash severities. Besides, the seasonal nature of data and the dynamic effects of the influential underlying factors should be considered to prevent underfitting issues and to predict future time trends accurately.

Applications

The developed instruments could be employed by policymakers to evaluate the intervention's effectiveness and to forecast the future time trends of accidents in Iran.

Forecasting time trends of fatal motor vehicle crashes in Iran using an ensemble learning algorithm

OBJECTIVE

This study aimed to introduce the random forest (RF) method as a valuable tool for short-term crash frequency prediction. Besides, the study compares the forecast efficiency of the RF model with the classical seasonal autoregressive integrated moving average (SARIMA) model in the multivariate time-series analysis of crash counts.

METHODS

To this end, fatal accidents reported by the police and intercity traffic flow extracted from the loop detectors were aggregated in intercity highways at the country's level monthly from Farvardin 1395 to Mordad 1400. The first 55 data points were used as the training sample, and the remaining ten months were considered the test sample. The Box-Jenkins and random forest machine learning methods were employed for short-term crash frequency prediction. The mean absolute percentage error (MAPE) criterion was utilized to compare the forecast accuracy of the developed models.

RESULTS

The performance of the random forest model (MAPE = 2.6) with the exogenous variables of traffic flow, crash year, and month outperformed the best SARIMA (1,0,0) (1,0,0)12 model (MAPE = 5.7) with traffic flow as the regressor.

CONCLUSIONS

This study suggests that the random forest as an ensemble learning algorithm is a better crash prediction tool compared to the classical Box-Jenkins method, accounting for the non-linear dependencies in crash count time-series. Besides, the results illustrate that the multivariate SARIMA (SARIMAX) model significantly outperforms its univariate counterpart, accounting for the simultaneous impacts of exogenous variables.

How do the smart travel ban policy and intercity travel pattern affect COVID-19 trends? Lessons learned from Iran

COVID-19, as the most significant epidemic of the century, infected 467 million people and took the lives of more than 6 million individuals as of March 19, 2022. Due to the rapid transmission of the disease and the lack of definitive treatment, countries have employed nonpharmaceutical interventions. This study aimed to investigate the effectiveness of the smart travel ban policy, which has been implemented for non-commercial vehicles in the intercity highways of Iran since November 21, 2020. The other goal was to suggest efficient COVID-19 forecasting tools and to examine the association of intercity travel patterns and COVID-19 trends in Iran. To this end, weekly confirmed cases and deaths due to COVID-19 and the intercity traffic flow reported by loop detectors were aggregated at the country's level. The Box-Jenkins methodology was employed to evaluate the policy's effectiveness, using the interrupted time series analysis. The results indicated that the autoregressive integrated moving average with explanatory variable (ARIMAX) model outperformed the univariate ARIMA model in predicting the disease trends based on the MAPE criterion. The weekly intercity traffic and its lagged variables were entered as covariates in both models of the disease cases and deaths. The results indicated that the weekly intercity traffic increases the new weekly COVID-19 cases and deaths with a time lag of two and five weeks, respectively. Besides, the interrupted time series analysis indicated that the smart travel ban policy had decreased intercity travel by around 29%. Nonetheless, it had no significant direct effect on COVID-19 trends. This study suggests that the travel ban policy would not be efficient lonely unless it is coupled with active measures and adherence to health protocols by the people.

ARIMA and ARIMA-ERNN models for prediction of pertussis incidence in mainland China from 2004 to 2021

OBJECTIVE

To compare an autoregressive integrated moving average (ARIMA) model with a model that combines ARIMA with the Elman recurrent neural network (ARIMA-ERNN) in predicting the incidence of pertussis in mainland China.

BACKGROUND

The incidence of pertussis has increased rapidly in mainland China since 2016, making the disease an increasing public health threat. There is a pressing need for models capable of accurately predicting the incidence of pertussis in order to guide prevention and control measures. We developed and compared two models for predicting pertussis incidence in mainland China.

METHODS

Data on the incidence of pertussis in mainland China from 2004 to 2019 were obtained from the official website of the Chinese Center for Disease Control and Prevention. An ARIMA model was established using SAS (ver. 9.4) software and an ARIMA-ERNN model was established using MATLAB (ver. R2019a) software. The performances of these models were compared.

RESULTS

From 2004 to 2019, there were 104,837 reported cases of pertussis in mainland China, with an increasing incidence over time. The incidence of pertussis showed obvious seasonal characteristics, with the peak lasting from March to September every year. Compared with the mean squared error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) of the ARIMA model, those of the ARIMA-ERNN model were 81.43%, 95.97% and 80.86% lower, respectively, in fitting performance. In terms of prediction performance, the MAE, MSE and MAPE were 37.75%, 56.88% and 43.75% lower, respectively.

CONCLUSION

The fitting and prediction performances of the ARIMA-ERNN model were better than those of the ARIMA model. This provides theoretical support for the prediction of infectious diseases and should be beneficial to public health decision making.

The comparative analysis of SARIMA, Facebook Prophet, and LSTM for road traffic injury prediction in Northeast China

Objective

This cross-sectional research aims to develop reliable predictive short-term prediction models to predict the number of RTIs in Northeast China through comparative studies.

Methodology

Seasonal auto-regressive integrated moving average (SARIMA), Long Short-Term Memory (LSTM), and Facebook Prophet (Prophet) models were used for time series prediction of the number of RTIs inpatients. The three models were trained using data from 2015 to 2019, and their prediction accuracy was compared using data from 2020 as a test set. The parameters of the SARIMA model were determined using the autocorrelation function (ACF) and the partial autocorrelation function (PACF). The LSTM uses linear as the activation function, the mean square error (MSE) as the loss function and the Adam optimizer to construct the model, while the Prophet model is built on the Python platform. The root mean squared error (RMSE), mean absolute error (MAE) and Mean Absolute Percentage Error (MAPE) are used to measure the predictive performance of the model.

Findings

In this research, the LSTM model had the highest prediction accuracy, followed by the Prophet model, and the SARIMA model had the lowest prediction accuracy. The trend in medical expenditure of RTIs inpatients overlapped highly with the number of RTIs inpatients.

Conclusion

By adjusting the activation function and optimizer, the LSTM predicts the number of RTIs inpatients more accurately and robustly than other models. Compared with other models, LSTM models still show excellent prediction performance in the face of data with seasonal and drastic changes. The LSTM can provide a better basis for planning and management in healthcare administration.

Implication

The results of this research show that it is feasible to accurately forecast the demand for healthcare resources with seasonal distribution using a suitable forecasting model. The prediction of specific medical service volumes will be an important basis for medical management to allocate medical and health resources.

Deep Learning-Based Diffusion-Weighted Magnetic Resonance Imaging in the Diagnosis of Ischemic Penumbra in Early Cerebral Infarction

The prefiltered image was imported into the local higher-order singular value decomposition (HOSVD) denoising algorithm (GL-HOSVD)-optimized diffusion-weighted imaging (DWI) image, which was compared with the deviation correction nonlocal mean (NL mean) and low-level edge algorithm (LR + edge). Regarding the peak signal-to-noise ratio (PSNR), root mean square error (RMSE), sensitivity, specificity, accuracy, and consistency, the application effect of the GL-HOSVD algorithm in DWI was investigated, and its adoption effect in the examination of ischemic penumbra (IP) of early acute cerebral infarction (ACI) patients was evaluated. A total of 210 patients with ACI were selected as the research subjects, who were randomly rolled into two groups. Those who were checked by conventional DWI were set as the control group, and those who used DWI based on the GL-HOSVD denoising algorithm were set as the observation group, with 105 people in each. Positron emission tomography (PET) test results were set as the gold standard to evaluate the application value of the two examination methods. It was found that under different noise levels, the peak signal-to-noise ratio (PSNR) of the GL-HOSVD algorithm and the root mean square error (RMSE) of the FA parameter were better than those of the nonlocal means (NL-means) of deviation correction and low-rank edge algorithm (LR + edge). The sensitivity, specificity, accuracy, and consistency (8.76%, 81.25%, 87.62%, and 0.52) of the observation group were higher than those of the control group (57.78%, 53.33%, 57.14%, and 0.35) (P < 0.05). Moreover, the apparent diffusion coefficient (ADC) of the DWI images of the observation group was basically consistent with that of the PET images, while the control group had a poor display effect and low definition. In summary, under different noise levels, the GL-HOSVD algorithm had a good denoising effect and greatly reduced fringe artifacts. DWI after denoising had high sensitivity, specificity, accuracy, and consistency in the detection of IP, which was worthy of clinical application and promotion.

SARIMA Modelling Approach for Forecasting of Traffic Accidents

To achieve greater sustainability of the traffic system, the trend of traffic accidents in road traffic was analysed. Injuries from traffic accidents are among the leading factors in the suffering of people around the world. Injuries from road traffic accidents are predicted to be the third leading factor contributing to human deaths. Road traffic accidents have decreased in most countries during the last decade because of the Decade of Action for Road Safety 2011–2020. The main reasons behind the reduction of traffic accidents are improvements in the construction of vehicles and roads, the training and education of drivers, and advances in medical technology and medical care. The primary objective of this paper is to investigate the pattern in the time series of traffic accidents in the city of Belgrade. Time series have been analysed using exploratory data analysis to describe and understand the data, the method of regression and the Box–Jenkins seasonal autoregressive integrated moving average model (SARIMA). The study found that the time series has a pronounced seasonal character. The model presented in the paper has a mean absolute percentage error (MAPE) of 5.22% and can be seen as an indicator that the prognosis is acceptably accurate. The forecasting, in the context of number of a traffic accidents, may be a strategy to achieve different goals such as traffic safety campaigns, traffic safety strategies and action plans to achieve the objectives defined in traffic safety strategies.

Short-term forecasting of the COVID-19 outbreak in India

As the outbreak of coronavirus disease 2019 (COVID-19) is rapidly spreading in different parts of India, a reliable forecast for the cumulative confirmed cases and the number of deaths can be helpful for policymakers in making the decisions for utilizing available resources in the country. Recently, various mathematical models have been used to predict the outbreak of COVID-19 worldwide and also in India. In this article we use exponential, logistic, Gompertz growth and autoregressive integrated moving average (ARIMA) models to predict the spread of COVID-19 in India after the announcement of various unlock phases. The mean absolute percentage error and root mean square error comparative measures were used to check the goodness-of-fit of the growth models and Akaike information criterion for ARIMA model selection. Using COVID-19 pandemic data up to 20 December 2020 from India and its five most affected states (Maharashtra, Karnataka, Andhra Pradesh, Tamil Nadu and Kerala), we report 15-days-ahead forecasts for cumulative confirmed cases and the number of deaths. Based on available data, we found that the ARIMA model is the best-fitting model for COVID-19 cases in India and its most affected states.

Segmentation Effect on the Transferability of International Safety Performance Functions for Rural Roads in Egypt

This paper examines the transferability of the Safety Performance Function (SPF) of the Highway Safety Manual (HSM) and other 10 international SPFs for total crashes on rural multi-lane divided roads in Egypt. Four segmentation approaches are assessed in the transferability of the international SPFs, namely: (1) one-kilometer segments (S1); (2) homogenous sections (S2); (3) variable segments with respect to the presence of curvatures (S3); and (4) variable segments with respect to the presence of both curvatures and U-turns (S4). The Mean Absolute Deviation (MAD), Mean Prediction Bias (MPB), Mean Absolute Percentage Error (MAPE), Pearson χ2 statistic, and Z-score parameters are used to evaluate the performance of the transferred models. The overdispersion parameter (k) for each transferred model and each segmentation approach is recalibrated using the local data by the maximum likelihood method. Before estimating the transferability calibration factor (Cr), three methods were used to adjust the local crash prediction of the transferred models, namely: (1) the HSM default crash modification factors (CMFs); (2) local CMFs; and (3) recalibrating the constant term of the transferred model. The latter method is found to outperform the first two methods. Besides, the results show that the segmentation method would affect the performance of the transferability process. Moreover, the Italian SPFs based on the S1 segmentation method outperforms the HSM and all of the investigated international SPFs for transferring their models to the Egyptian rural roads.